Resources

Ideas for work that takes time.

Read how we think about persistent execution, responsible tool use, and the evidence a result needs before it can be accepted.

JOURNAL

Read, then put the ideas to work.

Essays on durable execution, governance, evidence, and the design of accountable AI work.

Positioning

Why AI work should outlive the chat

Chat is excellent for answers. Durable work needs something that preserves intent, state, human judgment, and proof across time.

Journal · 6 min Read ↗
Product principles

A task is a contract, not a checklist

A checklist records steps. A task contract defines the result, the evidence of success, and the limits of execution.

Journal · 5 min Read ↗
Guides

How to write acceptance criteria AI can actually verify

A practical framework for separating structural checks, semantic judgments, and decisions that should remain human.

Guide · 7 min Read ↗
Engineering

How long-running AI work survives interruption

Persistent execution is built from durable state, append-only events, deterministic recovery, and clear signals between people and machines.

Journal · 7 min Read ↗
Governance

Human checkpoints: where judgment belongs

A checkpoint is a designed transfer of responsibility. It should be rare enough to respect attention and rich enough to support a real decision.

Journal · 5 min Read ↗
Governance

Governance before intelligence

A model should choose from capabilities that are allowed, not merely be asked to avoid tools that are dangerous.

Journal · 6 min Read ↗
PRIVATE PREVIEW / LIMITED ACCESS

Ready to keep the thread?

Bring one real research or analysis task to the LibreTask private preview.

Request private preview