Claude for Long-Horizon Tasks — Lance Martin, Anthropic
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
If you're building agents that must reliably execute multi-step, long-running work, this talk lays out concrete agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → patterns — decoupling planning from execution, self-verification, and self-learning — from someone working directly on Claude's managed agents. It's practitioner-level architecture guidance rather than a high-level overview.
Key quotes
“giving Claude access to a bunch of your secrets and letting it run for 10 hours and not watching it can be a little bit spooky”
Lance Martin
“instead of encoding steering me and into like me as the human, you're encoding the signal into the environment”
Lance Martin
“Five out of five replicates with raw memory store fell down this trap. With the dreaming, this error is corrected”
Lance Martin
“Let the model structure and maintain its own memory. Don't give it a prescribed memory schema.”
Lance Martin
“org level harnesses are real leveler of the playing field”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
