Source record

Published by Anthropic Engineering (T1 source). The original is at https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

Anthropic describes a harness for long-running agents that work across multiple context windows, using an initializer agent to set up the environment on first run and a coding agent that makes incremental progress while leaving artifacts for the next session.

First-party Anthropic engineering write-up with a concrete two-agent pattern and linked code examples for bridging context window limits.

Cited by

No citations on record.