Skip to content
ExploringProject

Long-Horizon Verification

A model for keeping claims, evidence, freshness, and next-action authority explicit across work that outlasts a single agent turn.

State
exploring
Updated
2026-09-06
Owner
Tim
Area
verification / evidence / long-horizon-agents

Current question
How should a long-running task represent what is proven, what is stale, and what remains safe to do next?

Read markdown

Why this exists

Long-running work changes its plan, environment, permissions, assumptions, and risk. A final pass/fail checkpoint cannot express what is currently proven or what evidence has gone stale.

Current model

Treat verification as a graph of claims and evidence. A deployment succeeding, a service being healthy, and the original user-visible problem being resolved are separate claims. Each needs evidence with provenance: producer, subject state, observation time, verifier, and supported claim.

What is unproven

This is a conceptual investigation. It does not report a live experiment, a completed implementation, or a verified production result.

Next experiment

Define a small claim-and-evidence state model with freshness rules, then test whether it can distinguish stale evidence from evidence attached to an immutable revision.

Artifacts

Open questions

  1. 01Which evidence types can authorize a next transition?
  2. 02How should independent verification be represented alongside proposer-generated checks?
  3. 03What freshness rules are meaningful for different claims?

Next

Define a small claim-and-evidence state model without assuming a particular agent framework.