Skip to main content
Fleet Prime Agent gets better over time by refining its supplemental harness state — a layer of guidance stored alongside the immutable base prompt. /refine is how you trigger a refinement pass.

What a refinement pass does

When you run /refine inside a session, the harness:
  1. Reads the trajectory — the messages, tool calls, and outcomes of the current run.
  2. Extracts evidence — what worked, what didn’t, and what patterns the model reached for repeatedly.
  3. Proposes updates to supplemental state, backed by concrete evidence pointers.
  4. Snapshots the previous state so any change can be rolled back.
  5. Applies the update to supplemental state only. The base system prompt is never touched.

Why the base prompt is immutable

The base prompt is the contract: it defines what the agent is, what tools it has, what invariants it must uphold. Rewriting it makes behavior drift unrecoverably. Refinement adds layered guidance on top instead — you can inspect it, roll it back, or throw it away.

Rollback

Every /refine pass writes a snapshot. If a refinement made things worse, roll back to the previous snapshot and try again.

Compaction is the sibling mechanism

Refinement updates guidance. Compaction trims context. When a session grows too long for the model’s context window, the compaction pipeline (compact, calculateContextTokens, prepareBranchEntries) produces a shorter transcript that keeps the important entries. See Sessions for the storage side and Refinement guide for how to use /refine in practice.
Last modified on August 17, 2026