Notes from the work
Build notes, practical systems, and a closer look at what changed. Written to help you make a decision, try something useful, or avoid learning the annoying part twice.
Showing 81 to 90 of 130 articles
Keep reading
Automation and Agents
OpenClaw reports fixes for delegated, CLI, and scheduled answers. Here is a proposed way to check what reaches each recipient and how to interpret the result.
Read the articleCreator Workflows
Suno says Speech beta generates spoken voice and background music together. Here is a proposed way to brief and review a short track without mistaking an early draft for a finished asset.
Read the articleAutomation and Agents
Saved Shell results could support a later handoff, but the intended reviewer must be able to retrieve the right output under the deployment’s publication and access settings.
Read the articleAutomation and Agents
The current Hosted approval card can accept an answer, but the captured Qwen PR says its producer does not supply the tool arguments behind the request.
Read the articleAutomation and Agents
Codex 0.160.0 adds two optional Guardian context features. Here is how to reason about a changed permission, a worker handoff and interrupted work.
Read the articleAutomation and Agents
A merged Codex pull request describes preserving earlier user restrictions in Guardian handoffs, subject to a shared message cap. Here is the operator decision it raises and the evidence still missing.
Read the articleAutomation and Agents
A confidence score cannot set your routing policy. Reviewed cases can show which mistakes an automatic rule would allow and how much work it would send to people.
Read the articleAutomation and Agents
Strands Decider 2B selects supplied options locally. Use five questions and three worked cases to decide which agent choice merits a contained trial.
Read the articleAutomation and Agents
Anthropic says Claude led 26% of its measured AI R&D work in August 2026. The figure depends on task ratings and staff-time weights; here is how to read it.
Read the articleAutomation and Agents
Use Anthropic’s scoped oversight measurements to ask what an agent can change, when people review problems, and what evidence supports wider permission.
Read the article
Follow the work
New builds, honest lessons, and practical ways to make more room for the work that needs you.
Free to read. Unsubscribe at any time. Privacy
