The useful part of AI coding agents is not that they can type code quickly. It is that they can explore alternatives, take on bounded work, and surface implementation options a human can review.
The weak part is everything around that: context preparation, safety boundaries, diff review, verification, retry decisions, and the question of what evidence survives after a run finishes.
That is the shape of Consortio. I want agent work to look less like a long chat transcript and more like an engineering workflow:
- Express the task as durable intent.
- Run candidates in isolated workspaces.
- Capture plans, critiques, diffs, proof results, and reports.
- Keep ranking downstream of verification.
- Export the selected work only when a human can inspect what happened.
The interesting product problem is not "which model is best?" It is how different agents, reviewers, judges, deterministic checks, and a human owner can work together without turning the process into noise.
That is where the interface has to earn its keep. It should show disagreement, unresolved risk, and evidence without making the user read every raw artifact by hand.