AI Agents (#agents)

10 Oct 202627 min read

Build an AI agent from scratch in Python: tools, the observe-decide-act loop, state, planning, error handling, termination and verification.

9 Oct 202629 min read

Beyond better prompts: how to design, assemble, optimize and manage the information an LLM needs to solve a task.

8 Oct 202619 min read

Bringing it all together: how to design caching as a first-class part of an AI system, from keys and versions to reliability, cost and rollout.

21 Sep 202619 min read

Agent state, plans, tool and API results, workflow steps, checkpoints, idempotent writes and scoped sharing: caching the work an agent does.

14 Sep 202617 min read

Caching for chat: conversation history, sessions, summaries, user memory, context fingerprints and responses, without leaking or going stale.

10 Sep 202616 min read

Caching for agents: tool results, workflow steps, state, checkpoints, MCP tools and resources, idempotency, and keeping it all safe.

7 Sep 202615 min read

KV, prompt, semantic, embedding, retrieval, reranking, tool, API, conversation and agent state caches: what each saves and how to key it safely.