The pull request reached review, but three required evidence items were still missing and two checks needed attention.

So the handoff stayed blocked.

We keep focusing on making agents smarter and more autonomous. Frankly the more I have worked on building midfleet the less I worry about what model the agent is using.
I think the harder problem was making the work survive the agent. I.e. I needed the mandate I gave the agent, to survive regardless of what happens to it.
Agents will stop. They ll hit limits, crash, lose context, or get replaced by a better model.
Completely normal.
The goal, owner, boundaries, decisions, progress and proof of completion should still be there.
Then one agent can implement.
Anpther one can review.
A human can approve.
Another agent can finish.
The worker can change without the job becoming an orphaned chat.
Agents should be replaceable. Responsibility shouldn t be.

Midfleet came out of our own frustration with multi-agent work. We were spending too much time babysitting runs, repeating context and pulling agents back toward the original intent.

Tools like Temporal, Galileo and Factory solve useful parts of the stack. The gap for us was keeping the work itself governed as it moved between agents and people.