Evidence runtime for autonomous agent task management

Grainulator, an evidence runtime for autonomous agent task management, enables AI models to incorporate independent checks and recorded evidence into their workflows, with a playground and local command-line tool that reproduces an evidence freshness bug fix and supports sending failed checks back to an adapter for retries. The tool, available via a session export and local checkout, does not establish a general accuracy or speed advantage based on local comparisons on Astra and Fable.

Research and verification for AI work Keep your model. Raise the standard. Bring evidence, independent checks, and useful corrections into the work your model already does. Keep the reasoning behind the result, so you can pick it up, question it, and move it forward. Open the playground /playground/ See what a check catches Good yesterday. Still good today? A check passes. The work moves on. Then the evidence changes—and the old approval no longer holds. Explore a real bug we fixed in Grainulator: catching that mismatch before a stale brief goes out. Follow the evidence Inspecting the recorded check… The trace is a small local file. There are no model requests or timed animations. — - Checked content - — - Current content - — Where Grainulator fits A stronger process. With your existing tools. Your model brings the intelligence. Grainulator brings a record of the evidence, checks you define, and a way to turn failures into the next useful step. 1. 01 Start with the workBring your question, task, and constraints. Keep the model and workspace you already use. 2. 02 Make “done” testableChoose an independent test or verifier. See what passed, what failed, and what remains uncertain. 3. 03 Give the next attempt a reasonFeed failed checks back to the model. Set limits on retries and keep the record of each attempt. From playground to real work Find your setup. Take it with you. Choose your model and research settings in the playground. Export the session, then continue from your local checkout with the context and completed passes intact. node bin/grainulator.js research --session session.json --dir ./research-session Download session.json from the playground, then run this from your local checkout. Uses your provider key and continues the remaining passes. What you can verify today The trace reproduces an evidence freshness bug and verifies that the updated guard blocks stale output. The command runner can send failed checks back to an adapter for another attempt. Support for a particular model depends on that adapter or host. Local comparisons on Astra and Fable measured answer correctness, formatting, elapsed time, and model usage. Some runs improved formatting; the results do not establish a general accuracy or speed advantage. The verifier rejected candidates that failed its checks. Reproduce the trace with node scripts/record-handoff.mjs . The adapter contract is in docs/ADAPTERS.md in the dogfood checkout.