Skip to content

Guides and resources for AI engineers: an agents course, five handbooks, a hands-on second-brain project and a vetted reading list.

4.5 KB
Raw Blame

Resources

Curated, not exhaustive. Everything here was checked in September 2026 and earns its place. Read alongside what a harness is for the vocabulary.

Foundational posts

Deep guides and talks

  • How to build an agent — Thorsten Ball. A code-editing agent in under 400 lines of Go. Do this before adopting any framework; nothing demystifies faster.

  • 12-factor agents — HumanLayer. Principles for agents that survive production: own your prompts, own your context window, small focused agents.

  • How we built our multi-agent research system — Anthropic. Orchestrator-worker patterns, and the honest admission that multi-agent burns ~15x the tokens.

  • Context rot — Chroma. The evidence that model performance degrades as input grows, long before the window fills.

  • The lethal trifecta — Simon Willison. The security frame for every agent that reads untrusted content. His ongoing blog is the best running commentary on agents generally.

  • The 2026-07-28 MCP specification — what changed when MCP went stateless, from the protocol team.

  • Improved token efficiency — Cursor. A production harness slimmed in six moves: two thirds of the system prompt deleted as models improved, tools loaded on demand (60% of static tool tokens gone), explicit cache breakpoints, sparser line numbers, subagent discipline. The rare post with numbers per change; this replication prompt applies the same audit to your own setup.

  • Palantir AIP architecture — the agent stack of a platform run inside genuinely locked-down organisations, and most of it copies to a small project: an ontology of typed objects and permitted actions instead of raw data access, one gateway in front of every model call (masking, caching, retries, token accounting), swappable models behind config, three triggers (schedule, event, API), evals inside the release cycle, every action traced. This breakdown maps each piece to what you would use at home.

Repos worth reading

  • pi — a full harness small enough to actually read; the loop, tools and extensions with no ceremony.
  • smolagents — the code-as-actions pattern in ~1,000 core lines.
  • OpenHands — how sandboxed runtimes and event streams look at production scale.
  • Claude Code docs — not a repo, but the reference harness's manual; the hooks reference alone is an education in lifecycle design.

Start here

  1. Build the naked loop. Work through Thorsten Ball's tutorial in your language of choice. One afternoon; permanently changes how you read framework docs.
  2. Read two posts. Building effective agents, then effective context engineering. Together they cover 80% of the judgement calls you will face.
  3. Adopt one harness and instrument it. Pick from the landscape, wire up a real task, and read the raw transcripts of every failure. The transcript is the curriculum; everything in this handbook is visible there.