{"query":"Context Lifecycle for AI Systems","count":10,"results":[{"slug":"context-lifecycle-for-ai-systems","title":"Context Lifecycle for AI Systems","kind":"essay","summary":"Why good AI systems should not treat context as one giant blob, and why summary, consolidation, and drill-down layers matter.","compact_summary":"Context should behave more like a lifecycle than a dump: short-term working state, compact summaries, longer-term memory, and periodic consolidation each serve different jobs and should not be collapsed into one context window.","confidence":"high","updated_at":"2026-04-10T00:00:00.000Z","score":226,"match_fields":["title","summary","compact_summary","tags","key_claims","section_map","body"]},{"slug":"memory-consolidation-and-sleep-loops","title":"Memory Consolidation and Sleep Loops for AI","kind":"essay","summary":"Why AI memory systems should consolidate, compress, and strengthen knowledge over time instead of storing everything statically, and how periodic sleep loops make that practical.","compact_summary":"Static retrieval is not memory. Real memory consolidates: it reviews what changed, promotes what matters, compresses what does not need detail, and emits a record of what changed and why. AI systems should aspire to that lifecycle.","confidence":"medium","updated_at":"2026-04-11T00:00:00.000Z","score":132,"match_fields":["title","summary","compact_summary","key_claims","section_map","body"]},{"slug":"trustworthy-co-thinker-vs-eager-executor","title":"Trustworthy Co-Thinker vs Eager Executor","kind":"essay","summary":"A product and safety stance for agents: useful systems should think clearly, expose uncertainty, and escalate action instead of racing toward execution.","compact_summary":"The safest default for many agent systems is to behave like a co-thinker rather than an eager executor: help frame decisions, expose uncertainty, and keep the human in authority where real risk exists.","confidence":"high","updated_at":"2026-04-10T00:00:00.000Z","score":100,"match_fields":["summary","compact_summary","key_claims","section_map","body"]},{"slug":"llm-inference-mental-model","title":"LLM Inference: A Working Mental Model","kind":"essay","summary":"A compact mental model for how LLM inference actually runs — two phases, a growing memory system, and a scheduler deciding who gets GPU time next — so that cost, latency, and hardware decisions stop being magic.","compact_summary":"Inference is a loop with two phases. Prefill is compute-bound, decode is memory-bandwidth-bound. KV cache removes redundant recomputation but grows with context and users. Continuous batching, PagedAttention, and composed parallelism are what made production serving economical. Agent workloads are decode-dominated and gain most from prefix caching and batching.","confidence":"high","updated_at":"2026-04-19T00:00:00.000Z","score":84,"match_fields":["summary","compact_summary","tags","key_claims","section_map","body"]},{"slug":"index","title":"civ.build","kind":"manifesto","summary":"A public knowledge contract where serious pages are written once, rendered for humans, and exposed to agents through explicit compact and full retrieval layers.","compact_summary":"civ.build is not a generic AI site. It is a markdown-first publishing surface where pages expose summaries, trust signals, provenance, and queryable endpoints for both human and agent readers.","confidence":"high","updated_at":"2026-04-10T00:00:00.000Z","score":70,"match_fields":["summary","compact_summary","key_claims","body"]},{"slug":"for-agents","title":"For Agents","kind":"guide","summary":"The shortest practical guide for agents that want to discover, query, and use this site correctly.","compact_summary":"Start with capabilities and search, prefer compact content before full content, inspect versions and policy before making assumptions, and treat the site as advisory public knowledge rather than an execution authority.","confidence":"high","updated_at":"2026-04-10T00:00:00.000Z","score":60,"match_fields":["title","summary","compact_summary","section_map","body"]},{"slug":"data-accumulation-as-an-asset","title":"Data Accumulation as an Asset","kind":"essay","summary":"Why accumulating data over time is valuable, why we still do not have information markets, and why the person or system that owns the accumulated graph holds the real leverage.","compact_summary":"Data accumulation is not just hoarding. It is a compounding asset: the more you capture, synthesize, and consolidate, the more valuable the graph becomes — for personal use, for agent consumption, and potentially as a product pattern.","confidence":"medium","updated_at":"2026-04-11T00:00:00.000Z","score":56,"match_fields":["summary","compact_summary","tags","key_claims","section_map","body"]},{"slug":"local-first-knowledge-systems","title":"Local-First Knowledge Systems","kind":"essay","summary":"Why useful knowledge systems should preserve ownership, keep markdown and files as the foundation, and add query layers without surrendering the whole graph to the cloud.","compact_summary":"A strong knowledge system starts local-first: capture and synthesis stay in owned files, public publishing surfaces sit on top, and richer query layers are added gradually instead of replacing the source of truth too early.","confidence":"high","updated_at":"2026-04-10T00:00:00.000Z","score":50,"match_fields":["title","summary","key_claims","section_map","body"]},{"slug":"public-knowledge-contracts-for-agents","title":"Public Knowledge Contracts for Agents","kind":"reference","summary":"What a serious agent-facing page should expose if it wants to be usable, trustworthy, and queryable on the public web.","compact_summary":"A public knowledge contract for agents should expose compact and full content layers, freshness, confidence, provenance, intended use, non-use boundaries, search, versions, and stable discovery paths. Anything less leaves too much to guesswork.","confidence":"high","updated_at":"2026-04-10T00:00:00.000Z","score":48,"match_fields":["title","compact_summary","key_claims","section_map","body"]},{"slug":"llm-operator-fundamentals","title":"LLM Operator Fundamentals: Temperature, Attention, Caching","kind":"essay","summary":"The three knobs that actually change what an LLM system ships — temperature, attention design, and prompt caching — explained at the operator level, not the research level.","compact_summary":"Temperature controls determinism and should be set per task, not left at the API default. Attention is a finite budget that structured prompts and focused retrieval spend well. Prompt caching has specific semantics — cache boundaries, breakpoints, and prefix stability — that decide whether an agent costs cents or dollars per session.","confidence":"high","updated_at":"2026-04-19T00:00:00.000Z","score":44,"match_fields":["summary","key_claims","section_map","body"]}]}