[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"portal-settings:stajic:en":3,"public-menus:all":38,"post:what-should-an-ai-agent-remember-forget-recompute-or-retrieve-again:en":205,"related:post:what-should-an-ai-agent-remember-forget-recompute-or-retrieve-again:en:1":1141},{"statusCode":4,"data":5,"message":37},200,{"tenantId":6,"lang":7,"defaultLang":8,"siteUrl":9,"contactEmail":10,"brandName":11,"logoUrl":12,"siteName":11,"siteDescription":13,"ogImage":10,"robotsIndex":14,"socialLinks":10,"reservedSlugs":10,"seoPolicy":15},"stajic","en","de","https:\u002F\u002Fstajic.de",null,"Stajic Platform","\u002FLogo_Planet.svg","Stajic Portal",true,{"branding":16,"relatedContent":17,"crossDomainLinks":18},{"logoUrl":12},{"enabled":14},[19,22,25,28,31,34],{"url":20,"label":21,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Ffigure.rocks","figure.rocks",{"url":23,"label":24,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Floving.rocks","loving.rocks",{"url":26,"label":27,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.com","bazify.com",{"url":29,"label":30,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.de","bazify.de",{"url":32,"label":33,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.at","bazify.at",{"url":35,"label":36,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.ba","bazify.ba","Portal settings resolved",[39,45],{"id":40,"name":41,"location":42,"isActive":14,"isDefault":43,"items":44},1,"main-navigation","header",false,[],{"id":46,"name":47,"location":48,"isActive":14,"isDefault":14,"items":49},4,"main-menu","sidebar",[50,66,79,93,103,118,133],{"id":51,"title":52,"url":60,"target":61,"icon":62,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":64,"portfolioId":10,"children":65},"item-18",{"de":53,"en":54,"es":55,"fr":56,"it":54,"ru":57,"sr":58,"zh":59},"Startseite","Home","Inicio","Accueil","Главная","Почетна","首页","\u002Ffull-stack-web-developer-munich-performance-seo-and-maintainable-builds","_self","i-lucide-home","page",111,[],{"id":67,"title":68,"url":75,"target":61,"icon":76,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":77,"portfolioId":10,"children":78},"item-22",{"de":69,"en":69,"es":70,"fr":69,"it":71,"ru":72,"sr":73,"zh":74},"Vision","Visión","Visione","Видение","Визија","想象","\u002Fueber-uns-webdesign-muenchen-webaplikation","i-lucide-eye",113,[],{"id":80,"title":81,"url":89,"target":61,"icon":90,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":91,"portfolioId":10,"children":92},"item-19",{"de":82,"en":83,"es":84,"fr":83,"it":85,"ru":86,"sr":87,"zh":88},"Leistungen","Services","Servicios","Servizi","Услуги","Услуге","服务","\u002Fservices-dienstleistungen-muenchen","i-lucide-wrench",116,[],{"id":94,"title":95,"url":99,"target":61,"icon":100,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":101,"portfolioId":10,"children":102},"item-23",{"de":96,"en":96,"es":96,"fr":96,"it":96,"ru":97,"sr":97,"zh":98},"Blog","Блог","博客","\u002Fblog","i-lucide-book-open",112,[],{"id":104,"title":105,"url":114,"target":61,"icon":115,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":116,"portfolioId":10,"children":117},"item-32",{"de":106,"en":107,"es":108,"fr":109,"it":110,"ru":111,"sr":112,"zh":113},"Neue Technologien","New Technologies","Nuevas tecnologías","Nouvelles technologies","Nuove tecnologie","Новые технологии","Нове технологије","新技术！","\u002Fneue-webtechnologien","i-lucide-sparkles",122,[],{"id":119,"title":120,"url":129,"target":61,"icon":130,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":131,"portfolioId":10,"children":132},"item-20",{"de":121,"en":122,"es":123,"fr":124,"it":125,"ru":126,"sr":127,"zh":128},"Kontakt","Contact us!","Contacto","Contact","Contatto","Контакт","Контактирајте нас","联系我们！","\u002Fcontact","i-lucide-mail",115,[],{"id":134,"title":135,"url":144,"target":61,"icon":145,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":147},"item-21",{"de":136,"en":137,"es":138,"fr":139,"it":140,"ru":141,"sr":142,"zh":143},"Unsere Arbeit","Our Work","Nuestro trabajo","Nos réalisations","I nostri lavori","Наши работы","Наши радови","文件夹","\u002Fportfolio","i-lucide-briefcase",114,[148,161,175,181,193],{"id":149,"title":150,"url":144,"target":61,"icon":159,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":160},"item-24",{"de":151,"en":152,"es":153,"fr":154,"it":155,"ru":156,"sr":157,"zh":158},"Alle Projekte","All Projects","Todos los proyectos","Tous les projets","Tutti i progetti","Все проекты","Сви пројекти","所有项目","i-lucide-grid-3x3",[],{"id":162,"title":163,"url":171,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":174},"item-29",{"de":164,"en":165,"es":166,"fr":167,"it":168,"ru":169,"sr":170,"zh":143},"Local Roots, Global Reach","Local Roots - Global Reach","Empresa local ","Entreprise locale","Azienda locale","Местная компания","Локално предузеће глобално тржиште","\u002Fportfolio\u002Flocal-roots-global-reach-communication-media-systems-for-modern-business","i-lucide-folder","custom",[],{"id":176,"title":177,"url":179,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":180},"item-28",{"de":178,"en":178,"es":178,"fr":178,"it":178,"ru":178,"sr":178,"zh":178},"Solr Suggester","\u002Fportfolio\u002Fsolr-fuzzy-suggester-und-solr-infix-suggester-abfrage-ueber-ajax-und-filterung",[],{"id":182,"title":183,"url":191,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":192},"item-27",{"de":184,"en":185,"es":186,"fr":187,"it":188,"ru":189,"sr":190,"zh":185},"Firmenwebseite SEO","Company Website SEO","Sitio web corporativo SEO","Site web d’entreprise SEO","Sito web aziendale SEO","Корпоративный сайт SEO","Пословна веб-страница SEO","\u002Fportfolio\u002Fseo-sem-branding-mobile-webseite-muenchen",[],{"id":194,"title":195,"url":203,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":204},"item-31",{"de":196,"en":197,"es":198,"fr":199,"it":200,"ru":201,"sr":202,"zh":197},"Digitalisierungsportal","Digitalization Portal","Portal de digitalización","Portail de numérisation","Portale di digitalizzazione","Портал цифровизации","Портал за дигитализацију","\u002Fportfolio\u002Fdigitalisierungsportal-archiv-museum-bibliothek-ead-lido-mets-mods",[],{"statusCode":4,"data":206,"message":1140},{"id":207,"title":208,"slug":209,"content":210,"contentJson":211,"excerpt":813,"featuredImage":814,"featuredImageAlt":815,"featuredImageCaption":10,"featuredImageTitle":10,"featuredImageCopyright":10,"featuredImageAuthor":10,"featuredImageSourceUrl":10,"featuredImageLicense":10,"featuredImageIsAiGenerated":43,"status":816,"publishedAt":817,"createdAt":818,"updatedAt":819,"seoLocalePaths":820,"categories":829,"author":842,"translations":847},"470","What Should an AI Agent Remember, Forget, Recompute or Retrieve Again?","what-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","{\"time\":1790351469618,\"blocks\":[{\"id\":\"XDf71jsthn\",\"type\":\"tableOfContents\",\"data\":{\"title\":\"Contents\",\"minLevel\":2,\"maxLevel\":3},\"tunes\":{}},{\"id\":\"intro\",\"type\":\"paragraph\",\"data\":{\"text\":\"Long-running AI agents accumulate far more information than they should permanently remember. Conversations, tool outputs, intermediate calculations, user preferences, project decisions, search results, system state, mistakes, and successful procedures can all look useful in the moment. Treating all of them as durable memory creates a second problem: the agent must later decide which stored information is still trustworthy, current, relevant, and safe to reuse.\"},\"tunes\":{}},{\"id\":\"direct\",\"type\":\"callout\",\"data\":{\"variant\":\"info\",\"title\":\"Direct answer\",\"body\":\"An AI agent should \u003Cstrong>remember information that is durable, reusable, provenance-preserving, and expensive to rediscover\u003C\u002Fstrong>; \u003Cstrong>re-read or retrieve volatile facts from their authoritative source\u003C\u002Fstrong>; \u003Cstrong>recompute cheap derived values when freshness matters\u003C\u002Fstrong>; and \u003Cstrong>forget, expire, or supersede information whose future reuse creates more risk than value\u003C\u002Fstrong>. The correct action depends less on whether information is “important” and more on its volatility, authority, derivation cost, reuse value, sensitivity, and revision behaviour.\"},\"tunes\":{}},{\"id\":\"model-note\",\"type\":\"callout\",\"data\":{\"variant\":\"note\",\"title\":\"About the decision model\",\"body\":\"The Remember \u002F Re-read \u002F Recompute \u002F Forget model and the Memory Admission Test below are practical architecture tools proposed in this article. They are not formal industry standards. They are designed to make agent-memory decisions explicit, testable, and auditable.\"},\"tunes\":{}},{\"id\":\"h-lifecycle\",\"type\":\"header\",\"data\":{\"text\":\"The real memory problem is not storage — it is lifecycle control\",\"level\":2},\"tunes\":{}},{\"id\":\"p-life-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Modern agent systems can store almost anything: full transcripts, summaries, embeddings, files, database records, tool traces, structured facts, skills, and external artifacts. Storage capacity is therefore not the hard part. The hard part is deciding what deserves to survive, how long it should survive, and what must happen when reality changes.\"},\"tunes\":{}},{\"id\":\"p-life-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"OpenAI's session-memory guidance explicitly warns that carrying too much history forward can create distraction, inefficiency, context poisoning, and compounding errors. Anthropic similarly treats context as a finite resource that must be curated rather than accumulated. Microsoft Research has moved in the same direction: PlugMem converts raw interaction history into reusable structured knowledge instead of treating the complete history as equally valuable memory.\"},\"tunes\":{}},{\"id\":\"p-life-3\",\"type\":\"paragraph\",\"data\":{\"text\":\"The architectural consequence is simple: memory needs an admission policy, a maintenance policy, and a retirement policy. A retriever alone does not provide those semantics.\"},\"tunes\":{}},{\"id\":\"h-actions\",\"type\":\"header\",\"data\":{\"text\":\"Four possible actions for any piece of agent information\",\"level\":2},\"tunes\":{}},{\"id\":\"table-actions\",\"type\":\"table\",\"data\":{\"withHeadings\":true,\"stretched\":false,\"content\":[[\"Action\",\"Use when\",\"Typical examples\",\"Primary risk\"],[\"Remember\",\"The information remains useful across future tasks and is costly or impossible to reconstruct reliably\",\"Stable user preference, accepted project decision, reusable skill, verified long-term constraint\",\"Persisting something false, stale, or too broad\"],[\"Re-read \u002F Retrieve\",\"The information has an authoritative source that may change\",\"Permissions, inventory, policy version, order state, product price, current API documentation\",\"Using an old copy instead of current authority\"],[\"Recompute\",\"The information is derived and inexpensive enough to calculate again\",\"Totals, scores, rankings, summaries from current source data, deterministic transformations\",\"Persisting stale derived output\"],[\"Forget \u002F Expire \u002F Supersede\",\"Future reuse has little value or creates privacy, staleness, conflict, or contamination risk\",\"Transient tool output, failed hypothesis, superseded decision, temporary token, obsolete environment state\",\"Losing information that later proves necessary\"]]},\"tunes\":{}},{\"id\":\"h-admission\",\"type\":\"header\",\"data\":{\"text\":\"The Memory Admission Test\",\"level\":2},\"tunes\":{}},{\"id\":\"p-admission-intro\",\"type\":\"paragraph\",\"data\":{\"text\":\"Before information becomes durable agent memory, test it against six properties. These properties are more useful than a vague importance score because they predict how the information behaves over time.\"},\"tunes\":{}},{\"id\":\"admission-comparison\",\"type\":\"comparison\",\"data\":{\"title\":\"Six properties that decide whether information belongs in memory\",\"layout\":\"table\",\"columns\":[{\"id\":\"property\",\"label\":\"Property\"},{\"id\":\"question\",\"label\":\"Question\"},{\"id\":\"effect\",\"label\":\"Decision pressure\"}],\"rows\":[{\"id\":\"volatility\",\"label\":\"Volatility\",\"values\":[\"\",\"\",\"\"]},{\"id\":\"authority\",\"label\":\"Authority\",\"values\":[\"\",\"\",\"\"]},{\"id\":\"reuse\",\"label\":\"Reuse value\",\"values\":[\"\",\"\",\"\"]},{\"id\":\"reconstruction\",\"label\":\"Reconstruction cost\",\"values\":[\"\",\"\",\"\"]},{\"id\":\"sensitivity\",\"label\":\"Sensitivity\",\"values\":[\"\",\"\",\"\"]},{\"id\":\"revision\",\"label\":\"Revision behaviour\",\"values\":[\"\",\"\",\"\"]}]},\"tunes\":{}},{\"id\":\"rule-volatile\",\"type\":\"callout\",\"data\":{\"variant\":\"tip\",\"title\":\"A practical rule\",\"body\":\"If a fact is \u003Cstrong>volatile + authoritative elsewhere + cheap to fetch\u003C\u002Fstrong>, do not promote a copied value into long-term memory. Store the pointer, identifier, or retrieval path instead.\"},\"tunes\":{}},{\"id\":\"h-remember\",\"type\":\"header\",\"data\":{\"text\":\"1. Remember: durable knowledge that improves future decisions\",\"level\":3},\"tunes\":{}},{\"id\":\"p-remember-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Good durable memory reduces repeated work without turning yesterday's state into today's truth. Typical candidates include explicit user preferences, durable project constraints, decisions and their rationale, reusable procedures, recurring failure patterns, and verified facts that are not expected to change frequently.\"},\"tunes\":{}},{\"id\":\"p-remember-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"The strongest memories are not necessarily raw transcripts. PlugMem's 2026 work argues for converting interaction history into compact facts and reusable skills. Microsoft's BREW similarly distills past trajectories into retrievable procedural knowledge describing what to do, when it applies, and what to watch out for. Both point toward a useful design principle: store reusable knowledge, not merely historical text.\"},\"tunes\":{}},{\"id\":\"p-remember-3\",\"type\":\"paragraph\",\"data\":{\"text\":\"A remembered item should also retain provenance. A future agent should be able to distinguish “the user explicitly requested this,” “the system observed this,” “a source stated this,” and “a model inferred this.” Without that distinction, memory gradually converts evidence, interpretation, and speculation into one undifferentiated pool.\"},\"tunes\":{}},{\"id\":\"h-reread\",\"type\":\"header\",\"data\":{\"text\":\"2. Re-read or retrieve: volatile facts with an external source of truth\",\"level\":3},\"tunes\":{}},{\"id\":\"p-reread-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Some information is valuable precisely because it changes. Current permissions, order state, inventory, account status, service health, software documentation, prices, schedules, regulations, and API behaviour should normally be re-read from the system that owns them before consequential use.\"},\"tunes\":{}},{\"id\":\"p-reread-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"The agent may remember that a source exists, how to access it, or what fields matter. It should not assume that an old retrieved value remains authoritative. This separates memory of where and how to obtain truth from a cached copy of truth.\"},\"tunes\":{}},{\"id\":\"stale-trap\",\"type\":\"callout\",\"data\":{\"variant\":\"warning\",\"title\":\"The stale-memory trap\",\"body\":\"A fact can be perfectly remembered and still be wrong. Memory quality is not only recall accuracy; it also includes knowing when recall must yield to a fresh authoritative read.\"},\"tunes\":{}},{\"id\":\"h-recompute\",\"type\":\"header\",\"data\":{\"text\":\"3. Recompute: derived information that is cheaper to calculate than to trust\",\"level\":3},\"tunes\":{}},{\"id\":\"p-recompute-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Derived information deserves different treatment from source facts. If a value can be deterministically recalculated from current inputs, persisting the result may create unnecessary staleness. Totals, percentages, rankings, eligibility flags, generated summaries, and other derived outputs should often be recomputed when used.\"},\"tunes\":{}},{\"id\":\"p-recompute-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"The key trade-off is cost. If recomputation is expensive, the system may cache the result together with the exact input version, timestamp, derivation method, and invalidation conditions. If recomputation is cheap, freshness usually wins.\"},\"tunes\":{}},{\"id\":\"h-forget\",\"type\":\"header\",\"data\":{\"text\":\"4. Forget, expire, or supersede: deletion is a capability\",\"level\":3},\"tunes\":{}},{\"id\":\"p-forget-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Forgetting is not necessarily a defect. It is a control mechanism. Transient tool outputs, one-off search results, failed hypotheses, temporary environment state, intermediate reasoning artifacts, obsolete user preferences, expired credentials, and superseded decisions can all become liabilities if they remain active indefinitely.\"},\"tunes\":{}},{\"id\":\"p-forget-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"Recent memory research increasingly recognizes that unbounded accumulation can degrade performance. Microsoft's 2026 human-inspired memory architecture explicitly includes interference-based forgetting and consolidation, while PlugMem reports that raw histories can overwhelm agents with low-value context. The engineering lesson does not require copying biological memory: retention should be selective.\"},\"tunes\":{}},{\"id\":\"p-forget-3\",\"type\":\"paragraph\",\"data\":{\"text\":\"In many systems, supersession is safer than immediate deletion. The old decision remains auditable, but retrieval defaults to the new decision. This matters for projects, policies, compliance, and any workflow where the history of change is itself evidence.\"},\"tunes\":{}},{\"id\":\"h-method\",\"type\":\"header\",\"data\":{\"text\":\"The decision method\",\"level\":2},\"tunes\":{}},{\"id\":\"decision-flow\",\"type\":\"processFlow\",\"data\":{\"title\":\"Decide the lifecycle of an information item\",\"orientation\":\"auto\",\"steps\":[{\"label\":\"1. Classify the information\",\"description\":\"Is it authoritative state, user preference, external evidence, derived output, procedure, observation, or model inference?\"},{\"label\":\"2. Identify the source of truth\",\"description\":\"Determine whether another system or source remains more authoritative than the memory itself.\"},{\"label\":\"3. Estimate volatility\",\"description\":\"Ask how likely the item is to change before the next meaningful reuse.\"},{\"label\":\"4. Estimate reuse and reconstruction cost\",\"description\":\"Compare future value with the cost and reliability of fetching or recreating the information.\"},{\"label\":\"5. Check sensitivity and scope\",\"description\":\"Define who may access the information, where it may persist, and whether persistence is justified.\"},{\"label\":\"6. Define invalidation\",\"description\":\"Specify expiry, supersession, conflict resolution, or a condition that forces a fresh authoritative read.\"},{\"label\":\"7. Choose the action\",\"description\":\"Remember, re-read\u002Fretrieve, recompute, or forget\u002Fexpire\u002Fsupersede.\"},{\"label\":\"8. Preserve provenance\",\"description\":\"Store enough metadata to distinguish source fact, user statement, observation, derivation, and model inference.\"}]},\"tunes\":{}},{\"id\":\"h-examples\",\"type\":\"header\",\"data\":{\"text\":\"Examples: the same agent should use different lifecycle actions\",\"level\":2},\"tunes\":{}},{\"id\":\"examples-table\",\"type\":\"table\",\"data\":{\"withHeadings\":true,\"stretched\":false,\"content\":[[\"Information\",\"Recommended action\",\"Why\"],[\"“The user prefers concise technical answers.”\",\"Remember\",\"Stable preference with high reuse value\"],[\"“The deployment is currently paused.”\",\"Re-read\",\"Current operational state can change\"],[\"“The total projected cost is €48,620.”\",\"Recompute from current inputs\",\"Derived value should follow source changes\"],[\"A 20,000-token raw tool response from yesterday\",\"Forget or archive externally\",\"Low direct reuse; high context cost\"],[\"A confirmed workaround for a recurring build failure\",\"Remember as reusable procedure\",\"High future reuse and expensive rediscovery\"],[\"A model guess about why a server failed\",\"Do not promote to durable fact\",\"Inference is not verified evidence\"],[\"An old project decision later replaced by a new one\",\"Supersede, retain audit history\",\"The latest decision should win without erasing provenance\"],[\"A current product price\",\"Retrieve again\",\"High volatility and external authority\"],[\"A legal or policy interpretation\",\"Remember the prior analysis only with source\u002Fversion metadata; re-check authority before action\",\"Applicability can change with time and jurisdiction\"]]},\"tunes\":{}},{\"id\":\"h-conditions\",\"type\":\"header\",\"data\":{\"text\":\"Memory should store conditions, not only conclusions\",\"level\":2},\"tunes\":{}},{\"id\":\"p-cond-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"A durable memory becomes dangerous when it stores only the conclusion and loses the conditions under which the conclusion was valid. “Use database-per-tenant” is weaker than “Use database-per-tenant when regulatory isolation and tenant-specific lifecycle requirements outweigh operational overhead.” The second form preserves the decision boundary.\"},\"tunes\":{}},{\"id\":\"p-cond-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"This matters even more for agent-learned procedures. A successful workflow should capture not only the steps but also the preconditions, environment, tool version, observable success criteria, and known failure modes. Otherwise a memory retrieved in the wrong environment can confidently reproduce an obsolete solution.\"},\"tunes\":{}},{\"id\":\"h-write-cost\",\"type\":\"header\",\"data\":{\"text\":\"A memory write should be more expensive than a memory read\",\"level\":2},\"tunes\":{}},{\"id\":\"p-write-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Reading a weak memory can damage one answer. Writing a weak memory can damage many future answers. The asymmetry suggests a stricter write path than read path: classify the candidate, check provenance, detect contradictions, apply sensitivity rules, define scope, and decide whether human confirmation or external validation is required.\"},\"tunes\":{}},{\"id\":\"p-write-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"This is especially important when an agent writes memories from its own generated output. A generated summary can contain compression errors. A tool failure can be misinterpreted. A plausible hypothesis can be stored as a fact. If those outputs become future context without evidence status, the agent can create a self-reinforcing error loop.\"},\"tunes\":{}},{\"id\":\"h-quality\",\"type\":\"header\",\"data\":{\"text\":\"Memory quality has at least five dimensions\",\"level\":2},\"tunes\":{}},{\"id\":\"quality-table\",\"type\":\"table\",\"data\":{\"withHeadings\":true,\"stretched\":false,\"content\":[[\"Dimension\",\"Question\"],[\"Retention quality\",\"Did the system preserve the information that should survive?\"],[\"Retrieval quality\",\"Can the system recover the right memory when it matters?\"],[\"Freshness quality\",\"Does the system know when stored information is no longer current?\"],[\"Provenance quality\",\"Can the system distinguish source, user statement, observation, derivation, and inference?\"],[\"Retirement quality\",\"Can the system expire, supersede, restrict, or remove information when it should no longer influence decisions?\"]]},\"tunes\":{}},{\"id\":\"p-quality-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"Benchmarks are starting to separate these concerns. Microsoft's MemGym explicitly evaluates memory in long-horizon agentic settings and reports memory-isolated scores intended to reduce confounding from reasoning, retrieval, and tool-use ability. That direction is important because a final task score alone cannot tell you whether memory itself helped, harmed, or was irrelevant.\"},\"tunes\":{}},{\"id\":\"h-not-store\",\"type\":\"header\",\"data\":{\"text\":\"What not to put into durable memory by default\",\"level\":2},\"tunes\":{}},{\"id\":\"not-store-list\",\"type\":\"list\",\"data\":{\"style\":\"unordered\",\"meta\":{},\"items\":[\"Raw chain-of-thought or hidden reasoning artifacts.\",\"Temporary authentication tokens, secrets, or credentials.\",\"Model-generated hypotheses that have not been verified.\",\"Volatile state that has a live authoritative system.\",\"Cheaply recomputable derived values without their source inputs.\",\"Large tool outputs merely because storage is available.\",\"Duplicate copies of information already governed by a better source of truth.\",\"Sensitive personal data without a clear persistence purpose, access scope, and lifecycle.\",\"Superseded conclusions without explicit version or retirement semantics.\",\"Error messages or failure states that are only useful for the current run and have no reusable diagnostic value.\"]},\"tunes\":{}},{\"id\":\"h-task-specific\",\"type\":\"header\",\"data\":{\"text\":\"Memory is task-specific — there is no universal optimal store\",\"level\":2},\"tunes\":{}},{\"id\":\"p-task-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"A coding agent benefits from reusable procedures, repository conventions, successful repair patterns, and project decisions. A personal assistant may need preferences, commitments, and relationship context. A commerce agent needs current product and transaction state far more than historical copies of price or inventory. A research agent benefits from source provenance, unresolved hypotheses, and explicit evidence status.\"},\"tunes\":{}},{\"id\":\"p-task-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"Microsoft Research's M-star work makes this point directly: memory systems optimized for one purpose may transfer poorly to another, and task-specific memory mechanisms can outperform a fixed general-purpose design. The memory schema should therefore follow the decisions the agent must make, not a universal template imposed on every agent.\"},\"tunes\":{}},{\"id\":\"h-change\",\"type\":\"header\",\"data\":{\"text\":\"What would change this answer?\",\"level\":2},\"tunes\":{}},{\"id\":\"p-change-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"The balance changes when retrieval is slow or expensive, authoritative systems are intermittently unavailable, recomputation is costly, audit rules require historical snapshots, or the agent must operate offline. In those cases, more information may need to be cached or persisted — but with version, provenance, timestamp, and invalidation metadata.\"},\"tunes\":{}},{\"id\":\"p-change-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"The balance also changes for agents whose primary value is personalization. A stable preference may be worth remembering even if it could technically be asked again. Conversely, in high-risk domains, the threshold for converting an observation or interpretation into durable memory should be much higher.\"},\"tunes\":{}},{\"id\":\"p-change-3\",\"type\":\"paragraph\",\"data\":{\"text\":\"Future managed-memory platforms may automate consolidation, retrieval, forgetting, and context construction. That can reduce implementation work, but it does not remove the governance question: which information is allowed to influence future decisions, under what conditions, and when must the system return to the current source of truth?\"},\"tunes\":{}},{\"id\":\"h-limitations\",\"type\":\"header\",\"data\":{\"text\":\"Limitations\",\"level\":2},\"tunes\":{}},{\"id\":\"p-limit-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"There is no single definition of “agent memory” across current frameworks and research. Some systems use the term for conversation history, others for external persistent stores, structured knowledge, learned procedures, checkpoints, or model adaptation. The decision model in this article focuses on operational lifecycle semantics rather than enforcing one vocabulary.\"},\"tunes\":{}},{\"id\":\"p-limit-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"The four lifecycle actions can also overlap. A system may remember a stable summary, retain a pointer to the source, re-read volatile fields, and recompute a derived result in one workflow. The purpose of the model is not to force one storage primitive per fact, but to make the reason for persistence explicit.\"},\"tunes\":{}},{\"id\":\"h-conclusion\",\"type\":\"header\",\"data\":{\"text\":\"Conclusion\",\"level\":2},\"tunes\":{}},{\"id\":\"p-conclusion-1\",\"type\":\"paragraph\",\"data\":{\"text\":\"A useful agent does not win by remembering the most. It wins by preserving the right information, returning to authoritative sources when reality can change, recalculating what is safer to derive again, and retiring information that should no longer influence future decisions.\"},\"tunes\":{}},{\"id\":\"p-conclusion-2\",\"type\":\"paragraph\",\"data\":{\"text\":\"The practical question for every candidate memory is therefore not “Can we store this?” but: Will future decisions be more reliable if this survives? If the answer depends on freshness, authority, cost, sensitivity, or revision, encode those conditions into the memory lifecycle instead of trusting retrieval alone.\"},\"tunes\":{}},{\"id\":\"internal-reasoning\",\"type\":\"referralArticle\",\"data\":{\"url\":\"https:\u002F\u002Fstajic.de\u002Fblog\u002Ffrom-research-protocol-to-a-general-ai-reasoning-framework\",\"title\":\"From Research Protocol to a General AI Reasoning Framework\",\"excerpt\":\"A domain-independent reasoning method for separating evidence from assumptions, testing competing hypotheses, and using explicit validation rules.\",\"ctaLabel\":\"Read the reasoning framework\"},\"tunes\":{}},{\"id\":\"h-faq\",\"type\":\"header\",\"data\":{\"text\":\"FAQ\",\"level\":2},\"tunes\":{}},{\"id\":\"faq\",\"type\":\"faq\",\"data\":{\"title\":\"AI agent memory lifecycle\",\"items\":[{\"id\":\"faq1\",\"question\":\"What information should an AI agent remember long term?\",\"answer\":\"Prefer information that is durable, reusable, provenance-preserving, and expensive or unreliable to reconstruct, such as stable user preferences, accepted project decisions, reusable procedures, and verified long-term constraints.\"},{\"id\":\"faq2\",\"question\":\"What should an AI agent retrieve again instead of remembering?\",\"answer\":\"Volatile information with an authoritative external source should normally be retrieved again before consequential use. Examples include permissions, inventory, current prices, account state, policy versions, service status, and current documentation.\"},{\"id\":\"faq3\",\"question\":\"When should an AI agent recompute information?\",\"answer\":\"Recompute derived values when the calculation is cheap and stale results would be costly. Persisting a derived value makes more sense when recomputation is expensive and the cache includes the source version and invalidation conditions.\"},{\"id\":\"faq4\",\"question\":\"Should AI agents forget information?\",\"answer\":\"Yes. Forgetting, expiry, and supersession are useful controls for transient, obsolete, sensitive, low-value, or misleading information. Unbounded retention can create noise and allow stale or incorrect information to keep influencing future decisions.\"},{\"id\":\"faq5\",\"question\":\"Is storing the entire conversation history a good memory strategy?\",\"answer\":\"Not by itself. Raw history can preserve evidence, but long-running agents usually need curation, structure, summaries, reusable facts or procedures, retrieval, and lifecycle rules so that low-value history does not dominate future context.\"}]},\"tunes\":{}},{\"id\":\"h-glossary\",\"type\":\"header\",\"data\":{\"text\":\"Glossary\",\"level\":2},\"tunes\":{}},{\"id\":\"glossary\",\"type\":\"glossary\",\"data\":{\"title\":\"Key memory lifecycle terms\",\"entries\":[{\"term\":\"Memory admission\",\"definition\":\"The decision process that determines whether information is allowed to become persistent agent memory.\",\"anchor\":\"memory-admission\"},{\"term\":\"Supersession\",\"definition\":\"Marking an older memory or decision as replaced by newer information while preserving the historical record where needed.\",\"anchor\":\"supersession\"},{\"term\":\"Invalidation\",\"definition\":\"A rule or event that makes a stored or cached value unsafe to reuse without refresh, recomputation, or review.\",\"anchor\":\"invalidation\"},{\"term\":\"Provenance\",\"definition\":\"Metadata describing where information came from, when it was observed, who or what asserted it, and how it was transformed.\",\"anchor\":\"provenance\"},{\"term\":\"Volatility\",\"definition\":\"The likelihood that information will change between the time it is stored and the time it is reused.\",\"anchor\":\"volatility\"},{\"term\":\"Reconstruction cost\",\"definition\":\"The time, money, computation, tool use, or uncertainty required to recover or regenerate information instead of storing it.\",\"anchor\":\"reconstruction-cost\"}]},\"tunes\":{}},{\"id\":\"h-sources\",\"type\":\"header\",\"data\":{\"text\":\"Primary sources and further reading\",\"level\":2},\"tunes\":{}},{\"id\":\"src-openai-session\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fdevelopers.openai.com\u002Fcookbook\u002Fexamples\u002Fagents_sdk\u002Fsession_memory\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"OpenAI — Context Engineering: Short-Term Memory Management with Sessions\",\"description\":\"Guidance on trimming, summarization, long-running context, and risks such as stale details and context poisoning.\"}},\"tunes\":{}},{\"id\":\"src-anthropic-context\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-context-engineering-for-ai-agents\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Anthropic — Effective Context Engineering for AI Agents\",\"description\":\"Engineering guidance on curation, compaction, structured note-taking, and maintaining useful agent context over long horizons.\"}},\"tunes\":{}},{\"id\":\"src-anthropic-harness\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-harnesses-for-long-running-agents\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Anthropic — Effective Harnesses for Long-Running Agents\",\"description\":\"Practical work on preserving progress and artifacts across context windows in long-running agent tasks.\"}},\"tunes\":{}},{\"id\":\"src-ms-plugmem\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fblog\u002Ffrom-raw-interaction-to-reusable-knowledge-rethinking-memory-for-ai-agents\u002F\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Microsoft Research — PlugMem\",\"description\":\"Research on transforming raw agent interactions into structured reusable facts and skills rather than accumulating undifferentiated history.\"}},\"tunes\":{}},{\"id\":\"src-ms-mstar\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fmstar-every-task-deserves-its-own-memory-harness\u002F\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Microsoft Research — M★: Every Task Deserves Its Own Memory Harness\",\"description\":\"Research showing that task-specific memory mechanisms can outperform fixed general-purpose memory designs.\"}},\"tunes\":{}},{\"id\":\"src-ms-memgym\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fmemgym-a-long-horizon-memory-environment-for-llm-agents\u002F\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Microsoft Research — MemGym\",\"description\":\"A benchmark for isolating and evaluating memory performance in long-horizon agent environments.\"}},\"tunes\":{}},{\"id\":\"src-ms-human-memory\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fhuman-inspired-memory-architecture-for-llm-agents\u002F\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Microsoft Research — Human-Inspired Memory Architecture for LLM Agents\",\"description\":\"Research exploring consolidation, interference-based forgetting, reconsolidation, and retrieval in persistent agent memory.\"}},\"tunes\":{}}],\"version\":\"2.31.6\"}",{"time":212,"blocks":213,"version":812},1790351469618,[214,222,228,236,243,248,253,258,263,268,299,304,309,351,358,363,368,373,378,383,388,393,400,405,410,415,420,425,430,435,440,472,477,521,526,531,536,541,546,551,556,578,583,588,606,611,616,621,626,631,636,641,646,651,656,661,666,671,680,685,711,716,743,748,758,767,776,785,794,803],{"id":215,"data":216,"type":220,"tunes":221},"XDf71jsthn",{"title":217,"maxLevel":218,"minLevel":219},"Contents",3,2,"tableOfContents",{},{"id":223,"data":224,"type":226,"tunes":227},"intro",{"text":225},"Long-running AI agents accumulate far more information than they should permanently remember. Conversations, tool outputs, intermediate calculations, user preferences, project decisions, search results, system state, mistakes, and successful procedures can all look useful in the moment. Treating all of them as durable memory creates a second problem: the agent must later decide which stored information is still trustworthy, current, relevant, and safe to reuse.","paragraph",{},{"id":229,"data":230,"type":234,"tunes":235},"direct",{"body":231,"title":232,"variant":233},"An AI agent should \u003Cstrong>remember information that is durable, reusable, provenance-preserving, and expensive to rediscover\u003C\u002Fstrong>; \u003Cstrong>re-read or retrieve volatile facts from their authoritative source\u003C\u002Fstrong>; \u003Cstrong>recompute cheap derived values when freshness matters\u003C\u002Fstrong>; and \u003Cstrong>forget, expire, or supersede information whose future reuse creates more risk than value\u003C\u002Fstrong>. The correct action depends less on whether information is “important” and more on its volatility, authority, derivation cost, reuse value, sensitivity, and revision behaviour.","Direct answer","info","callout",{},{"id":237,"data":238,"type":234,"tunes":242},"model-note",{"body":239,"title":240,"variant":241},"The Remember \u002F Re-read \u002F Recompute \u002F Forget model and the Memory Admission Test below are practical architecture tools proposed in this article. They are not formal industry standards. They are designed to make agent-memory decisions explicit, testable, and auditable.","About the decision model","note",{},{"id":244,"data":245,"type":42,"tunes":247},"h-lifecycle",{"text":246,"level":219},"The real memory problem is not storage — it is lifecycle control",{},{"id":249,"data":250,"type":226,"tunes":252},"p-life-1",{"text":251},"Modern agent systems can store almost anything: full transcripts, summaries, embeddings, files, database records, tool traces, structured facts, skills, and external artifacts. Storage capacity is therefore not the hard part. The hard part is deciding what deserves to survive, how long it should survive, and what must happen when reality changes.",{},{"id":254,"data":255,"type":226,"tunes":257},"p-life-2",{"text":256},"OpenAI's session-memory guidance explicitly warns that carrying too much history forward can create distraction, inefficiency, context poisoning, and compounding errors. Anthropic similarly treats context as a finite resource that must be curated rather than accumulated. Microsoft Research has moved in the same direction: PlugMem converts raw interaction history into reusable structured knowledge instead of treating the complete history as equally valuable memory.",{},{"id":259,"data":260,"type":226,"tunes":262},"p-life-3",{"text":261},"The architectural consequence is simple: memory needs an admission policy, a maintenance policy, and a retirement policy. A retriever alone does not provide those semantics.",{},{"id":264,"data":265,"type":42,"tunes":267},"h-actions",{"text":266,"level":219},"Four possible actions for any piece of agent information",{},{"id":269,"data":270,"type":297,"tunes":298},"table-actions",{"content":271,"stretched":43,"withHeadings":14},[272,277,282,287,292],[273,274,275,276],"Action","Use when","Typical examples","Primary risk",[278,279,280,281],"Remember","The information remains useful across future tasks and is costly or impossible to reconstruct reliably","Stable user preference, accepted project decision, reusable skill, verified long-term constraint","Persisting something false, stale, or too broad",[283,284,285,286],"Re-read \u002F Retrieve","The information has an authoritative source that may change","Permissions, inventory, policy version, order state, product price, current API documentation","Using an old copy instead of current authority",[288,289,290,291],"Recompute","The information is derived and inexpensive enough to calculate again","Totals, scores, rankings, summaries from current source data, deterministic transformations","Persisting stale derived output",[293,294,295,296],"Forget \u002F Expire \u002F Supersede","Future reuse has little value or creates privacy, staleness, conflict, or contamination risk","Transient tool output, failed hypothesis, superseded decision, temporary token, obsolete environment state","Losing information that later proves necessary","table",{},{"id":300,"data":301,"type":42,"tunes":303},"h-admission",{"text":302,"level":219},"The Memory Admission Test",{},{"id":305,"data":306,"type":226,"tunes":308},"p-admission-intro",{"text":307},"Before information becomes durable agent memory, test it against six properties. These properties are more useful than a vague importance score because they predict how the information behaves over time.",{},{"id":310,"data":311,"type":349,"tunes":350},"admission-comparison",{"rows":312,"title":338,"layout":297,"columns":339},[313,318,322,326,330,334],{"id":314,"label":315,"values":316},"volatility","Volatility",[317,317,317],"",{"id":319,"label":320,"values":321},"authority","Authority",[317,317,317],{"id":323,"label":324,"values":325},"reuse","Reuse value",[317,317,317],{"id":327,"label":328,"values":329},"reconstruction","Reconstruction cost",[317,317,317],{"id":331,"label":332,"values":333},"sensitivity","Sensitivity",[317,317,317],{"id":335,"label":336,"values":337},"revision","Revision behaviour",[317,317,317],"Six properties that decide whether information belongs in memory",[340,343,346],{"id":341,"label":342},"property","Property",{"id":344,"label":345},"question","Question",{"id":347,"label":348},"effect","Decision pressure","comparison",{},{"id":352,"data":353,"type":234,"tunes":357},"rule-volatile",{"body":354,"title":355,"variant":356},"If a fact is \u003Cstrong>volatile + authoritative elsewhere + cheap to fetch\u003C\u002Fstrong>, do not promote a copied value into long-term memory. Store the pointer, identifier, or retrieval path instead.","A practical rule","tip",{},{"id":359,"data":360,"type":42,"tunes":362},"h-remember",{"text":361,"level":218},"1. Remember: durable knowledge that improves future decisions",{},{"id":364,"data":365,"type":226,"tunes":367},"p-remember-1",{"text":366},"Good durable memory reduces repeated work without turning yesterday's state into today's truth. Typical candidates include explicit user preferences, durable project constraints, decisions and their rationale, reusable procedures, recurring failure patterns, and verified facts that are not expected to change frequently.",{},{"id":369,"data":370,"type":226,"tunes":372},"p-remember-2",{"text":371},"The strongest memories are not necessarily raw transcripts. PlugMem's 2026 work argues for converting interaction history into compact facts and reusable skills. Microsoft's BREW similarly distills past trajectories into retrievable procedural knowledge describing what to do, when it applies, and what to watch out for. Both point toward a useful design principle: store reusable knowledge, not merely historical text.",{},{"id":374,"data":375,"type":226,"tunes":377},"p-remember-3",{"text":376},"A remembered item should also retain provenance. A future agent should be able to distinguish “the user explicitly requested this,” “the system observed this,” “a source stated this,” and “a model inferred this.” Without that distinction, memory gradually converts evidence, interpretation, and speculation into one undifferentiated pool.",{},{"id":379,"data":380,"type":42,"tunes":382},"h-reread",{"text":381,"level":218},"2. Re-read or retrieve: volatile facts with an external source of truth",{},{"id":384,"data":385,"type":226,"tunes":387},"p-reread-1",{"text":386},"Some information is valuable precisely because it changes. Current permissions, order state, inventory, account status, service health, software documentation, prices, schedules, regulations, and API behaviour should normally be re-read from the system that owns them before consequential use.",{},{"id":389,"data":390,"type":226,"tunes":392},"p-reread-2",{"text":391},"The agent may remember that a source exists, how to access it, or what fields matter. It should not assume that an old retrieved value remains authoritative. This separates memory of where and how to obtain truth from a cached copy of truth.",{},{"id":394,"data":395,"type":234,"tunes":399},"stale-trap",{"body":396,"title":397,"variant":398},"A fact can be perfectly remembered and still be wrong. Memory quality is not only recall accuracy; it also includes knowing when recall must yield to a fresh authoritative read.","The stale-memory trap","warning",{},{"id":401,"data":402,"type":42,"tunes":404},"h-recompute",{"text":403,"level":218},"3. Recompute: derived information that is cheaper to calculate than to trust",{},{"id":406,"data":407,"type":226,"tunes":409},"p-recompute-1",{"text":408},"Derived information deserves different treatment from source facts. If a value can be deterministically recalculated from current inputs, persisting the result may create unnecessary staleness. Totals, percentages, rankings, eligibility flags, generated summaries, and other derived outputs should often be recomputed when used.",{},{"id":411,"data":412,"type":226,"tunes":414},"p-recompute-2",{"text":413},"The key trade-off is cost. If recomputation is expensive, the system may cache the result together with the exact input version, timestamp, derivation method, and invalidation conditions. If recomputation is cheap, freshness usually wins.",{},{"id":416,"data":417,"type":42,"tunes":419},"h-forget",{"text":418,"level":218},"4. Forget, expire, or supersede: deletion is a capability",{},{"id":421,"data":422,"type":226,"tunes":424},"p-forget-1",{"text":423},"Forgetting is not necessarily a defect. It is a control mechanism. Transient tool outputs, one-off search results, failed hypotheses, temporary environment state, intermediate reasoning artifacts, obsolete user preferences, expired credentials, and superseded decisions can all become liabilities if they remain active indefinitely.",{},{"id":426,"data":427,"type":226,"tunes":429},"p-forget-2",{"text":428},"Recent memory research increasingly recognizes that unbounded accumulation can degrade performance. Microsoft's 2026 human-inspired memory architecture explicitly includes interference-based forgetting and consolidation, while PlugMem reports that raw histories can overwhelm agents with low-value context. The engineering lesson does not require copying biological memory: retention should be selective.",{},{"id":431,"data":432,"type":226,"tunes":434},"p-forget-3",{"text":433},"In many systems, supersession is safer than immediate deletion. The old decision remains auditable, but retrieval defaults to the new decision. This matters for projects, policies, compliance, and any workflow where the history of change is itself evidence.",{},{"id":436,"data":437,"type":42,"tunes":439},"h-method",{"text":438,"level":219},"The decision method",{},{"id":441,"data":442,"type":470,"tunes":471},"decision-flow",{"steps":443,"title":468,"orientation":469},[444,447,450,453,456,459,462,465],{"label":445,"description":446},"1. Classify the information","Is it authoritative state, user preference, external evidence, derived output, procedure, observation, or model inference?",{"label":448,"description":449},"2. Identify the source of truth","Determine whether another system or source remains more authoritative than the memory itself.",{"label":451,"description":452},"3. Estimate volatility","Ask how likely the item is to change before the next meaningful reuse.",{"label":454,"description":455},"4. Estimate reuse and reconstruction cost","Compare future value with the cost and reliability of fetching or recreating the information.",{"label":457,"description":458},"5. Check sensitivity and scope","Define who may access the information, where it may persist, and whether persistence is justified.",{"label":460,"description":461},"6. Define invalidation","Specify expiry, supersession, conflict resolution, or a condition that forces a fresh authoritative read.",{"label":463,"description":464},"7. Choose the action","Remember, re-read\u002Fretrieve, recompute, or forget\u002Fexpire\u002Fsupersede.",{"label":466,"description":467},"8. Preserve provenance","Store enough metadata to distinguish source fact, user statement, observation, derivation, and model inference.","Decide the lifecycle of an information item","auto","processFlow",{},{"id":473,"data":474,"type":42,"tunes":476},"h-examples",{"text":475,"level":219},"Examples: the same agent should use different lifecycle actions",{},{"id":478,"data":479,"type":297,"tunes":520},"examples-table",{"content":480,"stretched":43,"withHeadings":14},[481,485,488,492,496,500,504,508,512,516],[482,483,484],"Information","Recommended action","Why",[486,278,487],"“The user prefers concise technical answers.”","Stable preference with high reuse value",[489,490,491],"“The deployment is currently paused.”","Re-read","Current operational state can change",[493,494,495],"“The total projected cost is €48,620.”","Recompute from current inputs","Derived value should follow source changes",[497,498,499],"A 20,000-token raw tool response from yesterday","Forget or archive externally","Low direct reuse; high context cost",[501,502,503],"A confirmed workaround for a recurring build failure","Remember as reusable procedure","High future reuse and expensive rediscovery",[505,506,507],"A model guess about why a server failed","Do not promote to durable fact","Inference is not verified evidence",[509,510,511],"An old project decision later replaced by a new one","Supersede, retain audit history","The latest decision should win without erasing provenance",[513,514,515],"A current product price","Retrieve again","High volatility and external authority",[517,518,519],"A legal or policy interpretation","Remember the prior analysis only with source\u002Fversion metadata; re-check authority before action","Applicability can change with time and jurisdiction",{},{"id":522,"data":523,"type":42,"tunes":525},"h-conditions",{"text":524,"level":219},"Memory should store conditions, not only conclusions",{},{"id":527,"data":528,"type":226,"tunes":530},"p-cond-1",{"text":529},"A durable memory becomes dangerous when it stores only the conclusion and loses the conditions under which the conclusion was valid. “Use database-per-tenant” is weaker than “Use database-per-tenant when regulatory isolation and tenant-specific lifecycle requirements outweigh operational overhead.” The second form preserves the decision boundary.",{},{"id":532,"data":533,"type":226,"tunes":535},"p-cond-2",{"text":534},"This matters even more for agent-learned procedures. A successful workflow should capture not only the steps but also the preconditions, environment, tool version, observable success criteria, and known failure modes. Otherwise a memory retrieved in the wrong environment can confidently reproduce an obsolete solution.",{},{"id":537,"data":538,"type":42,"tunes":540},"h-write-cost",{"text":539,"level":219},"A memory write should be more expensive than a memory read",{},{"id":542,"data":543,"type":226,"tunes":545},"p-write-1",{"text":544},"Reading a weak memory can damage one answer. Writing a weak memory can damage many future answers. The asymmetry suggests a stricter write path than read path: classify the candidate, check provenance, detect contradictions, apply sensitivity rules, define scope, and decide whether human confirmation or external validation is required.",{},{"id":547,"data":548,"type":226,"tunes":550},"p-write-2",{"text":549},"This is especially important when an agent writes memories from its own generated output. A generated summary can contain compression errors. A tool failure can be misinterpreted. A plausible hypothesis can be stored as a fact. If those outputs become future context without evidence status, the agent can create a self-reinforcing error loop.",{},{"id":552,"data":553,"type":42,"tunes":555},"h-quality",{"text":554,"level":219},"Memory quality has at least five dimensions",{},{"id":557,"data":558,"type":297,"tunes":577},"quality-table",{"content":559,"stretched":43,"withHeadings":14},[560,562,565,568,571,574],[561,345],"Dimension",[563,564],"Retention quality","Did the system preserve the information that should survive?",[566,567],"Retrieval quality","Can the system recover the right memory when it matters?",[569,570],"Freshness quality","Does the system know when stored information is no longer current?",[572,573],"Provenance quality","Can the system distinguish source, user statement, observation, derivation, and inference?",[575,576],"Retirement quality","Can the system expire, supersede, restrict, or remove information when it should no longer influence decisions?",{},{"id":579,"data":580,"type":226,"tunes":582},"p-quality-1",{"text":581},"Benchmarks are starting to separate these concerns. Microsoft's MemGym explicitly evaluates memory in long-horizon agentic settings and reports memory-isolated scores intended to reduce confounding from reasoning, retrieval, and tool-use ability. That direction is important because a final task score alone cannot tell you whether memory itself helped, harmed, or was irrelevant.",{},{"id":584,"data":585,"type":42,"tunes":587},"h-not-store",{"text":586,"level":219},"What not to put into durable memory by default",{},{"id":589,"data":590,"type":604,"tunes":605},"not-store-list",{"meta":591,"items":592,"style":603},{},[593,594,595,596,597,598,599,600,601,602],"Raw chain-of-thought or hidden reasoning artifacts.","Temporary authentication tokens, secrets, or credentials.","Model-generated hypotheses that have not been verified.","Volatile state that has a live authoritative system.","Cheaply recomputable derived values without their source inputs.","Large tool outputs merely because storage is available.","Duplicate copies of information already governed by a better source of truth.","Sensitive personal data without a clear persistence purpose, access scope, and lifecycle.","Superseded conclusions without explicit version or retirement semantics.","Error messages or failure states that are only useful for the current run and have no reusable diagnostic value.","unordered","list",{},{"id":607,"data":608,"type":42,"tunes":610},"h-task-specific",{"text":609,"level":219},"Memory is task-specific — there is no universal optimal store",{},{"id":612,"data":613,"type":226,"tunes":615},"p-task-1",{"text":614},"A coding agent benefits from reusable procedures, repository conventions, successful repair patterns, and project decisions. A personal assistant may need preferences, commitments, and relationship context. A commerce agent needs current product and transaction state far more than historical copies of price or inventory. A research agent benefits from source provenance, unresolved hypotheses, and explicit evidence status.",{},{"id":617,"data":618,"type":226,"tunes":620},"p-task-2",{"text":619},"Microsoft Research's M-star work makes this point directly: memory systems optimized for one purpose may transfer poorly to another, and task-specific memory mechanisms can outperform a fixed general-purpose design. The memory schema should therefore follow the decisions the agent must make, not a universal template imposed on every agent.",{},{"id":622,"data":623,"type":42,"tunes":625},"h-change",{"text":624,"level":219},"What would change this answer?",{},{"id":627,"data":628,"type":226,"tunes":630},"p-change-1",{"text":629},"The balance changes when retrieval is slow or expensive, authoritative systems are intermittently unavailable, recomputation is costly, audit rules require historical snapshots, or the agent must operate offline. In those cases, more information may need to be cached or persisted — but with version, provenance, timestamp, and invalidation metadata.",{},{"id":632,"data":633,"type":226,"tunes":635},"p-change-2",{"text":634},"The balance also changes for agents whose primary value is personalization. A stable preference may be worth remembering even if it could technically be asked again. Conversely, in high-risk domains, the threshold for converting an observation or interpretation into durable memory should be much higher.",{},{"id":637,"data":638,"type":226,"tunes":640},"p-change-3",{"text":639},"Future managed-memory platforms may automate consolidation, retrieval, forgetting, and context construction. That can reduce implementation work, but it does not remove the governance question: which information is allowed to influence future decisions, under what conditions, and when must the system return to the current source of truth?",{},{"id":642,"data":643,"type":42,"tunes":645},"h-limitations",{"text":644,"level":219},"Limitations",{},{"id":647,"data":648,"type":226,"tunes":650},"p-limit-1",{"text":649},"There is no single definition of “agent memory” across current frameworks and research. Some systems use the term for conversation history, others for external persistent stores, structured knowledge, learned procedures, checkpoints, or model adaptation. The decision model in this article focuses on operational lifecycle semantics rather than enforcing one vocabulary.",{},{"id":652,"data":653,"type":226,"tunes":655},"p-limit-2",{"text":654},"The four lifecycle actions can also overlap. A system may remember a stable summary, retain a pointer to the source, re-read volatile fields, and recompute a derived result in one workflow. The purpose of the model is not to force one storage primitive per fact, but to make the reason for persistence explicit.",{},{"id":657,"data":658,"type":42,"tunes":660},"h-conclusion",{"text":659,"level":219},"Conclusion",{},{"id":662,"data":663,"type":226,"tunes":665},"p-conclusion-1",{"text":664},"A useful agent does not win by remembering the most. It wins by preserving the right information, returning to authoritative sources when reality can change, recalculating what is safer to derive again, and retiring information that should no longer influence future decisions.",{},{"id":667,"data":668,"type":226,"tunes":670},"p-conclusion-2",{"text":669},"The practical question for every candidate memory is therefore not “Can we store this?” but: Will future decisions be more reliable if this survives? If the answer depends on freshness, authority, cost, sensitivity, or revision, encode those conditions into the memory lifecycle instead of trusting retrieval alone.",{},{"id":672,"data":673,"type":678,"tunes":679},"internal-reasoning",{"url":674,"title":675,"excerpt":676,"ctaLabel":677},"https:\u002F\u002Fstajic.de\u002Fblog\u002Ffrom-research-protocol-to-a-general-ai-reasoning-framework","From Research Protocol to a General AI Reasoning Framework","A domain-independent reasoning method for separating evidence from assumptions, testing competing hypotheses, and using explicit validation rules.","Read the reasoning framework","referralArticle",{},{"id":681,"data":682,"type":42,"tunes":684},"h-faq",{"text":683,"level":219},"FAQ",{},{"id":686,"data":687,"type":686,"tunes":710},"faq",{"items":688,"title":709},[689,693,697,701,705],{"id":690,"answer":691,"question":692},"faq1","Prefer information that is durable, reusable, provenance-preserving, and expensive or unreliable to reconstruct, such as stable user preferences, accepted project decisions, reusable procedures, and verified long-term constraints.","What information should an AI agent remember long term?",{"id":694,"answer":695,"question":696},"faq2","Volatile information with an authoritative external source should normally be retrieved again before consequential use. Examples include permissions, inventory, current prices, account state, policy versions, service status, and current documentation.","What should an AI agent retrieve again instead of remembering?",{"id":698,"answer":699,"question":700},"faq3","Recompute derived values when the calculation is cheap and stale results would be costly. Persisting a derived value makes more sense when recomputation is expensive and the cache includes the source version and invalidation conditions.","When should an AI agent recompute information?",{"id":702,"answer":703,"question":704},"faq4","Yes. Forgetting, expiry, and supersession are useful controls for transient, obsolete, sensitive, low-value, or misleading information. Unbounded retention can create noise and allow stale or incorrect information to keep influencing future decisions.","Should AI agents forget information?",{"id":706,"answer":707,"question":708},"faq5","Not by itself. Raw history can preserve evidence, but long-running agents usually need curation, structure, summaries, reusable facts or procedures, retrieval, and lifecycle rules so that low-value history does not dominate future context.","Is storing the entire conversation history a good memory strategy?","AI agent memory lifecycle",{},{"id":712,"data":713,"type":42,"tunes":715},"h-glossary",{"text":714,"level":219},"Glossary",{},{"id":717,"data":718,"type":717,"tunes":742},"glossary",{"title":719,"entries":720},"Key memory lifecycle terms",[721,725,729,733,737,739],{"term":722,"anchor":723,"definition":724},"Memory admission","memory-admission","The decision process that determines whether information is allowed to become persistent agent memory.",{"term":726,"anchor":727,"definition":728},"Supersession","supersession","Marking an older memory or decision as replaced by newer information while preserving the historical record where needed.",{"term":730,"anchor":731,"definition":732},"Invalidation","invalidation","A rule or event that makes a stored or cached value unsafe to reuse without refresh, recomputation, or review.",{"term":734,"anchor":735,"definition":736},"Provenance","provenance","Metadata describing where information came from, when it was observed, who or what asserted it, and how it was transformed.",{"term":315,"anchor":314,"definition":738},"The likelihood that information will change between the time it is stored and the time it is reused.",{"term":328,"anchor":740,"definition":741},"reconstruction-cost","The time, money, computation, tool use, or uncertainty required to recover or regenerate information instead of storing it.",{},{"id":744,"data":745,"type":42,"tunes":747},"h-sources",{"text":746,"level":219},"Primary sources and further reading",{},{"id":749,"data":750,"type":756,"tunes":757},"src-openai-session",{"link":751,"meta":752},"https:\u002F\u002Fdevelopers.openai.com\u002Fcookbook\u002Fexamples\u002Fagents_sdk\u002Fsession_memory",{"image":753,"title":754,"description":755},{"url":317},"OpenAI — Context Engineering: Short-Term Memory Management with Sessions","Guidance on trimming, summarization, long-running context, and risks such as stale details and context poisoning.","linkTool",{},{"id":759,"data":760,"type":756,"tunes":766},"src-anthropic-context",{"link":761,"meta":762},"https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-context-engineering-for-ai-agents",{"image":763,"title":764,"description":765},{"url":317},"Anthropic — Effective Context Engineering for AI Agents","Engineering guidance on curation, compaction, structured note-taking, and maintaining useful agent context over long horizons.",{},{"id":768,"data":769,"type":756,"tunes":775},"src-anthropic-harness",{"link":770,"meta":771},"https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-harnesses-for-long-running-agents",{"image":772,"title":773,"description":774},{"url":317},"Anthropic — Effective Harnesses for Long-Running Agents","Practical work on preserving progress and artifacts across context windows in long-running agent tasks.",{},{"id":777,"data":778,"type":756,"tunes":784},"src-ms-plugmem",{"link":779,"meta":780},"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fblog\u002Ffrom-raw-interaction-to-reusable-knowledge-rethinking-memory-for-ai-agents\u002F",{"image":781,"title":782,"description":783},{"url":317},"Microsoft Research — PlugMem","Research on transforming raw agent interactions into structured reusable facts and skills rather than accumulating undifferentiated history.",{},{"id":786,"data":787,"type":756,"tunes":793},"src-ms-mstar",{"link":788,"meta":789},"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fmstar-every-task-deserves-its-own-memory-harness\u002F",{"image":790,"title":791,"description":792},{"url":317},"Microsoft Research — M★: Every Task Deserves Its Own Memory Harness","Research showing that task-specific memory mechanisms can outperform fixed general-purpose memory designs.",{},{"id":795,"data":796,"type":756,"tunes":802},"src-ms-memgym",{"link":797,"meta":798},"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fmemgym-a-long-horizon-memory-environment-for-llm-agents\u002F",{"image":799,"title":800,"description":801},{"url":317},"Microsoft Research — MemGym","A benchmark for isolating and evaluating memory performance in long-horizon agent environments.",{},{"id":804,"data":805,"type":756,"tunes":811},"src-ms-human-memory",{"link":806,"meta":807},"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fhuman-inspired-memory-architecture-for-llm-agents\u002F",{"image":808,"title":809,"description":810},{"url":317},"Microsoft Research — Human-Inspired Memory Architecture for LLM Agents","Research exploring consolidation, interference-based forgetting, reconsolidation, and retrieval in persistent agent memory.",{},"2.31.6","Long-running agents should not remember everything. This article provides a practical lifecycle model for deciding what belongs in durable memory, what should be retrieved again, what is safer to recompute, and what should expire or be superseded.","\u002Fuploads\u002F2026\u002F09\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again-1790351131087-iehz28.webp","what-should-an-ai-agent-remember-forget-recompute-or-retrieve-again-1790351131087-iehz28","PUBLISHED","2026-09-25T09:43:00.000Z","2026-09-25T15:43:41.228Z","2026-09-25T20:20:04.123Z",{"en":821,"de":822,"sr":823,"es":824,"fr":825,"it":826,"ru":827,"zh":828},"\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Fde\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Fsr\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Fes\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Ffr\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Fit\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Fru\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again","\u002Fzh\u002Fblog\u002Fwhat-should-an-ai-agent-remember-forget-recompute-or-retrieve-again",[830,834,838],{"id":831,"name":832,"slug":833},57,"Data Boundaries","data-boundaries",{"id":835,"name":836,"slug":837},84,"Policy & Data Boundaries","policy-and-data",{"id":839,"name":840,"slug":841},54,"Threat Model","threat-model",{"id":843,"login":844,"email":845,"displayName":846},"20","rooth8233","aleksandar@stajic.de","Aleksandar Stajić",[848],{"lang":7,"title":208,"content":210,"contentJson":849,"excerpt":813},{"time":212,"blocks":850,"version":812},[851,854,857,860,863,866,869,872,875,878,887,890,893,913,916,919,922,925,928,931,934,937,940,943,946,949,952,955,958,961,964,976,979,993,996,999,1002,1005,1008,1011,1014,1024,1027,1030,1035,1038,1041,1044,1047,1050,1053,1056,1059,1062,1065,1068,1071,1074,1077,1080,1089,1092,1102,1105,1110,1115,1120,1125,1130,1135],{"id":215,"data":852,"type":220,"tunes":853},{"title":217,"maxLevel":218,"minLevel":219},{},{"id":223,"data":855,"type":226,"tunes":856},{"text":225},{},{"id":229,"data":858,"type":234,"tunes":859},{"body":231,"title":232,"variant":233},{},{"id":237,"data":861,"type":234,"tunes":862},{"body":239,"title":240,"variant":241},{},{"id":244,"data":864,"type":42,"tunes":865},{"text":246,"level":219},{},{"id":249,"data":867,"type":226,"tunes":868},{"text":251},{},{"id":254,"data":870,"type":226,"tunes":871},{"text":256},{},{"id":259,"data":873,"type":226,"tunes":874},{"text":261},{},{"id":264,"data":876,"type":42,"tunes":877},{"text":266,"level":219},{},{"id":269,"data":879,"type":297,"tunes":886},{"content":880,"stretched":43,"withHeadings":14},[881,882,883,884,885],[273,274,275,276],[278,279,280,281],[283,284,285,286],[288,289,290,291],[293,294,295,296],{},{"id":300,"data":888,"type":42,"tunes":889},{"text":302,"level":219},{},{"id":305,"data":891,"type":226,"tunes":892},{"text":307},{},{"id":310,"data":894,"type":349,"tunes":912},{"rows":895,"title":338,"layout":297,"columns":908},[896,898,900,902,904,906],{"id":314,"label":315,"values":897},[317,317,317],{"id":319,"label":320,"values":899},[317,317,317],{"id":323,"label":324,"values":901},[317,317,317],{"id":327,"label":328,"values":903},[317,317,317],{"id":331,"label":332,"values":905},[317,317,317],{"id":335,"label":336,"values":907},[317,317,317],[909,910,911],{"id":341,"label":342},{"id":344,"label":345},{"id":347,"label":348},{},{"id":352,"data":914,"type":234,"tunes":915},{"body":354,"title":355,"variant":356},{},{"id":359,"data":917,"type":42,"tunes":918},{"text":361,"level":218},{},{"id":364,"data":920,"type":226,"tunes":921},{"text":366},{},{"id":369,"data":923,"type":226,"tunes":924},{"text":371},{},{"id":374,"data":926,"type":226,"tunes":927},{"text":376},{},{"id":379,"data":929,"type":42,"tunes":930},{"text":381,"level":218},{},{"id":384,"data":932,"type":226,"tunes":933},{"text":386},{},{"id":389,"data":935,"type":226,"tunes":936},{"text":391},{},{"id":394,"data":938,"type":234,"tunes":939},{"body":396,"title":397,"variant":398},{},{"id":401,"data":941,"type":42,"tunes":942},{"text":403,"level":218},{},{"id":406,"data":944,"type":226,"tunes":945},{"text":408},{},{"id":411,"data":947,"type":226,"tunes":948},{"text":413},{},{"id":416,"data":950,"type":42,"tunes":951},{"text":418,"level":218},{},{"id":421,"data":953,"type":226,"tunes":954},{"text":423},{},{"id":426,"data":956,"type":226,"tunes":957},{"text":428},{},{"id":431,"data":959,"type":226,"tunes":960},{"text":433},{},{"id":436,"data":962,"type":42,"tunes":963},{"text":438,"level":219},{},{"id":441,"data":965,"type":470,"tunes":975},{"steps":966,"title":468,"orientation":469},[967,968,969,970,971,972,973,974],{"label":445,"description":446},{"label":448,"description":449},{"label":451,"description":452},{"label":454,"description":455},{"label":457,"description":458},{"label":460,"description":461},{"label":463,"description":464},{"label":466,"description":467},{},{"id":473,"data":977,"type":42,"tunes":978},{"text":475,"level":219},{},{"id":478,"data":980,"type":297,"tunes":992},{"content":981,"stretched":43,"withHeadings":14},[982,983,984,985,986,987,988,989,990,991],[482,483,484],[486,278,487],[489,490,491],[493,494,495],[497,498,499],[501,502,503],[505,506,507],[509,510,511],[513,514,515],[517,518,519],{},{"id":522,"data":994,"type":42,"tunes":995},{"text":524,"level":219},{},{"id":527,"data":997,"type":226,"tunes":998},{"text":529},{},{"id":532,"data":1000,"type":226,"tunes":1001},{"text":534},{},{"id":537,"data":1003,"type":42,"tunes":1004},{"text":539,"level":219},{},{"id":542,"data":1006,"type":226,"tunes":1007},{"text":544},{},{"id":547,"data":1009,"type":226,"tunes":1010},{"text":549},{},{"id":552,"data":1012,"type":42,"tunes":1013},{"text":554,"level":219},{},{"id":557,"data":1015,"type":297,"tunes":1023},{"content":1016,"stretched":43,"withHeadings":14},[1017,1018,1019,1020,1021,1022],[561,345],[563,564],[566,567],[569,570],[572,573],[575,576],{},{"id":579,"data":1025,"type":226,"tunes":1026},{"text":581},{},{"id":584,"data":1028,"type":42,"tunes":1029},{"text":586,"level":219},{},{"id":589,"data":1031,"type":604,"tunes":1034},{"meta":1032,"items":1033,"style":603},{},[593,594,595,596,597,598,599,600,601,602],{},{"id":607,"data":1036,"type":42,"tunes":1037},{"text":609,"level":219},{},{"id":612,"data":1039,"type":226,"tunes":1040},{"text":614},{},{"id":617,"data":1042,"type":226,"tunes":1043},{"text":619},{},{"id":622,"data":1045,"type":42,"tunes":1046},{"text":624,"level":219},{},{"id":627,"data":1048,"type":226,"tunes":1049},{"text":629},{},{"id":632,"data":1051,"type":226,"tunes":1052},{"text":634},{},{"id":637,"data":1054,"type":226,"tunes":1055},{"text":639},{},{"id":642,"data":1057,"type":42,"tunes":1058},{"text":644,"level":219},{},{"id":647,"data":1060,"type":226,"tunes":1061},{"text":649},{},{"id":652,"data":1063,"type":226,"tunes":1064},{"text":654},{},{"id":657,"data":1066,"type":42,"tunes":1067},{"text":659,"level":219},{},{"id":662,"data":1069,"type":226,"tunes":1070},{"text":664},{},{"id":667,"data":1072,"type":226,"tunes":1073},{"text":669},{},{"id":672,"data":1075,"type":678,"tunes":1076},{"url":674,"title":675,"excerpt":676,"ctaLabel":677},{},{"id":681,"data":1078,"type":42,"tunes":1079},{"text":683,"level":219},{},{"id":686,"data":1081,"type":686,"tunes":1088},{"items":1082,"title":709},[1083,1084,1085,1086,1087],{"id":690,"answer":691,"question":692},{"id":694,"answer":695,"question":696},{"id":698,"answer":699,"question":700},{"id":702,"answer":703,"question":704},{"id":706,"answer":707,"question":708},{},{"id":712,"data":1090,"type":42,"tunes":1091},{"text":714,"level":219},{},{"id":717,"data":1093,"type":717,"tunes":1101},{"title":719,"entries":1094},[1095,1096,1097,1098,1099,1100],{"term":722,"anchor":723,"definition":724},{"term":726,"anchor":727,"definition":728},{"term":730,"anchor":731,"definition":732},{"term":734,"anchor":735,"definition":736},{"term":315,"anchor":314,"definition":738},{"term":328,"anchor":740,"definition":741},{},{"id":744,"data":1103,"type":42,"tunes":1104},{"text":746,"level":219},{},{"id":749,"data":1106,"type":756,"tunes":1109},{"link":751,"meta":1107},{"image":1108,"title":754,"description":755},{"url":317},{},{"id":759,"data":1111,"type":756,"tunes":1114},{"link":761,"meta":1112},{"image":1113,"title":764,"description":765},{"url":317},{},{"id":768,"data":1116,"type":756,"tunes":1119},{"link":770,"meta":1117},{"image":1118,"title":773,"description":774},{"url":317},{},{"id":777,"data":1121,"type":756,"tunes":1124},{"link":779,"meta":1122},{"image":1123,"title":782,"description":783},{"url":317},{},{"id":786,"data":1126,"type":756,"tunes":1129},{"link":788,"meta":1127},{"image":1128,"title":791,"description":792},{"url":317},{},{"id":795,"data":1131,"type":756,"tunes":1134},{"link":797,"meta":1132},{"image":1133,"title":800,"description":801},{"url":317},{},{"id":804,"data":1136,"type":756,"tunes":1139},{"link":806,"meta":1137},{"image":1138,"title":809,"description":810},{"url":317},{},"Post erfolgreich abgerufen",{"items":1142,"source":1185,"manualIds":1186,"manualMatchedIds":1187},[1143,1150,1157,1164,1171,1178],{"id":1144,"slug":1145,"title":1146,"excerpt":1147,"featuredImage":1148,"publishedAt":1149},"468","ai-agent-memory-is-not-rag-how-to-separate-memory-retrieval-state-and-context","AI Agent Memory Is Not RAG: How to Separate Memory, Retrieval, State and Context","Agent memory, RAG, state, and context are often used as if they were interchangeable. They are not. This practical architecture model separates the four layers, shows where each belongs, and explains what breaks when systems collapse them into one.","\u002Fuploads\u002F2026\u002F09\u002Fai-agent-memory-is-not-rag-how-to-separate-memory-retrieval-state-and-context-1790350560308-np0xy6.webp","2026-09-25T11:34:00.000Z",{"id":1151,"slug":1152,"title":1153,"excerpt":1154,"featuredImage":1155,"publishedAt":1156},"471","how-to-know-whether-an-ai-agent-actually-used-the-right-evidence","How to Know Whether an AI Agent Actually Used the Right Evidence","An AI agent can cite sources and still use the wrong evidence. This article introduces a practical method for checking claim support, source authority, applicability, provenance, and whether the evidence actually influenced the answer.","\u002Fuploads\u002F2026\u002F09\u002Fhow-to-know-whether-an-ai-agent-actually-used-the-right-evidence-1790351317188-o5z9ve.webp","2026-09-25T11:47:00.000Z",{"id":1158,"slug":1159,"title":1160,"excerpt":1161,"featuredImage":1162,"publishedAt":1163},"467","the-answer-validity-boundary-the-missing-layer-between-relevance-and-reliable-ai-answers","The Answer Validity Boundary: The Missing Layer Between Relevance and Reliable AI Answers","A source can be relevant, authoritative and still be wrong for the question being asked. The missing layer is applicability: the conditions under which an answer holds, and the changes that force it to be reconsidered. This article introduces the Answer Validity Boundary as a source-design pattern for humans, AI search and RAG systems.","\u002Fuploads\u002F2026\u002F09\u002Fthe-answer-validity-boundary-the-missing-layer-between-relevance-and-reliable-ai-answers-1790272901306-1g5jly.webp","2026-09-24T11:59:00.000Z",{"id":1165,"slug":1166,"title":1167,"excerpt":1168,"featuredImage":1169,"publishedAt":1170},"476","mcp-vs-a2a-vs-ucp-vs-ap2-vs-a2ui-the-agent-protocol-stack-explained","MCP vs A2A vs UCP vs AP2 vs A2UI: The Agent Protocol Stack Explained","MCP, A2A, UCP, AP2 and A2UI are often presented as competing agent standards. They mostly solve different interoperability problems. This guide maps each protocol to the boundary it actually standardizes—and shows how they can work together in one production system.","\u002Fuploads\u002F2026\u002F09\u002Fmcp-vs-a2a-vs-ucp-vs-ap2-vs-a2ui-the-agent-protocol-stack-explained-1790352625869-2ezle0.webp","2026-09-25T12:09:00.000Z",{"id":1172,"slug":1173,"title":1174,"excerpt":1175,"featuredImage":1176,"publishedAt":1177},"466","the-gpu-is-not-the-product-future-proof-private-ai-architecture","The GPU Is Not the Product: Future-Proof Private AI Architecture","Private AI infrastructure should not be designed around one GPU or one model. A more resilient approach combines fast inference GPUs, memory-rich AI systems, physical-AI nodes and optional frontier cloud models behind a capability-aware routing layer.","\u002Fuploads\u002F2026\u002F09\u002Fthe-gpu-is-not-the-product-future-proof-private-ai-architecture-1790140878812-8hsl39.webp","2026-09-23T01:19:00.000Z",{"id":1179,"slug":1180,"title":1181,"excerpt":1182,"featuredImage":1183,"publishedAt":1184},"478","what-is-rag-the-simplest-explanation-of-how-it-works","What Is RAG? The Simplest Explanation of How It Works","RAG sounds complicated, but the idea is simple: before an AI answers, it first looks up useful information from a knowledge source and gives that information to the language model. This guide explains RAG, LLMs, state, memory and tools using one simple mental model.","\u002Fuploads\u002F2026\u002F09\u002Fwhat-is-rag-the-simplest-explanation-of-how-it-works-1790377492124-khjagt.webp","2026-09-25T19:03:00.000Z","fallback",[],[]]