Every source behind Sahar Carmel’s How to Build Agents lecture. A place to revisit the ideas, follow the references, and give your agent the full story.
Eight agents, one Discord server, and a lot of scar tissue.
“You don't ask agents to behave. You make misbehavior impossible.”
A sub-agent is a tool. An agent is a worker. The moment you have workers you are re-deriving the firm: division of labor, coordination cost, an org chart that lives in a config file.
Handoffs have types (notify, request, delegate, broadcast) and are governed in code by five rails: no self-notification, a policy of rank, per-agent rate limits, cooldowns between pairs, and a chain-depth cap.
The context window is RAM, not disk. Memory is written by a separate model after the fact, indexed, consolidated on a schedule, and it still rots. An HR agent reviews the drift; a human disposes.
Readiness comes before the agent. The one question that predicts survival: how does the team respond the first time it fails?
Where's the full write-up, the rules, the smells, the failures?
Building Agents in ProductionTrove library
From the library
Building Agents in Production
This is the book the talk was cut from: seven chapters on shipping agents inside a real company, each ending with rules an agent can apply and smells you can diagnose your own system with.
Prompting is the cheapest lever you have. Use both playbooks.
“Fix context before you fix the model.”
Anthropic: be clear and direct, show examples, structure with XML tags, give the model a role, and reach for chain-of-thought only when it earns its keep. Every model family has its own chapter because the quirks differ.
OpenAI: outcome-first prompts, the six core strategies, a structured template (personality, goal, success criteria, constraints), and the reasoning-model rules that invert some older advice.
In Claude Code specifically: effort levels, adaptive thinking, session structure, and when the model should stop and ask instead of pushing through.
Where do I read the guides without forty browser tabs?
Anthropic Prompting Best PracticesAnthropic
From the library
Anthropic Prompting Best Practices
Anthropic
The official guides are linked below. Anthropic's prompting guide is also in Trove, so your agent can read it and cite the page.
Twenty-four Anthropic engineering posts in one book: thematic digests up front, then the full text of the eleven posts the talk leaned on, one per page.
