The published knowledge surface, ordered by freshness and designed for both human reading and agent retrieval.
LLM Inference: A Working Mental Model
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.
- Kind:
essay - Confidence:
high - Version:
0.1.0 - Updated:
2026-04-19T00:00:00.000Z - Compact:
/api/v1/content/llm-inference-mental-model/compact
LLM Operator Fundamentals: Temperature, Attention, Caching
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.
- Kind:
essay - Confidence:
high - Version:
0.1.0 - Updated:
2026-04-19T00:00:00.000Z - Compact:
/api/v1/content/llm-operator-fundamentals/compact
About civ.build
civ.build is a public knowledge surface built by Hasan Kilickaya — a place to publish serious ideas in a form that works for both humans and autonomous agents.
- Kind:
guide - Confidence:
high - Version:
0.3.0 - Updated:
2026-04-13T00:00:00.000Z - Compact:
/api/v1/content/about/compact
Memory Consolidation and Sleep Loops for AI
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.
- Kind:
essay - Confidence:
medium - Version:
0.1.0 - Updated:
2026-04-11T00:00:00.000Z - Compact:
/api/v1/content/memory-consolidation-and-sleep-loops/compact
The Agent Economy: Wallets, Payments, and Bots as Purchasers
Agent commerce is not science fiction. Agentic wallets, 402 payment protocols, and universal commerce APIs already exist. The question is not whether bots will transact, but what the trust and pricing layer should look like when they do.
- Kind:
essay - Confidence:
medium - Version:
0.1.0 - Updated:
2026-04-11T00:00:00.000Z - Compact:
/api/v1/content/the-agent-economy/compact
Data Accumulation as an Asset
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.
- Kind:
essay - Confidence:
medium - Version:
0.1.0 - Updated:
2026-04-11T00:00:00.000Z - Compact:
/api/v1/content/data-accumulation-as-an-asset/compact
Context Lifecycle for AI Systems
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.
- Kind:
essay - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/context-lifecycle-for-ai-systems/compact
Local-First Knowledge Systems
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.
- Kind:
essay - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/local-first-knowledge-systems/compact
Agent SEO and Discovery
Agent SEO is about more than indexing: it is the practice of making pages discoverable, inspectable, trustworthy, and easy to route through for machine readers using discovery files, search endpoints, compact summaries, and explicit metadata.
- Kind:
essay - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/agent-seo-and-discovery/compact
Hello Phase 1
This note remains as a small regression target for content listing, compact retrieval, full retrieval, raw source access, and changes tracking.
- Kind:
note - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/hello-phase1/compact
For Agents
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.
- Kind:
guide - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/for-agents/compact
Trustworthy Co-Thinker vs Eager Executor
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.
- Kind:
essay - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/trustworthy-co-thinker-vs-eager-executor/compact
civ.build Changelog
The site moved from a minimal manifesto prototype toward a richer public knowledge contract with compact retrieval, discovery files, search, version traces, and structured trust metadata.
- Kind:
changelog - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/changelog/compact
Public Knowledge Contracts for Agents
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.
- Kind:
reference - Confidence:
high - Version:
0.2.0 - Updated:
2026-04-10T00:00:00.000Z - Compact:
/api/v1/content/public-knowledge-contracts-for-agents/compact