Loom / July 3, 2026

Run records and review checkpoints

A clearer model for connecting an agent's claim of progress with the checks and artifacts behind it.

This update sharpened Loom's approach to run records. Commands, checks, previews, and failures are useful only when a reviewer can see what question they answer.

The goal is not to preserve an exhaustive transcript. It is to keep the evidence needed to assess a change close to the task, including clear signals when a check is incomplete or a risk remains open.

That makes review more proportionate: quick when the evidence is clear, and deliberate when the task needs closer attention.

Open the Loom page

Recent updates

August 1, 2026

Loom

Loom public preview

Loom is now available as an open-source starting point for teams experimenting with persistent, reviewable agent work.

June 5, 2026

Loom

Workspace recovery and handoff

A task should be inexpensive to resume after an interruption, whether the next operator is a person or another agent.