A council of 3 to 20 AI expert personas debates your decision, is checked against the evidence turn by turn, and hands you a verdict with dissent, an action plan and a stress test. High-risk verdicts wait for a person to sign off.
Personal data is masked and leading or manipulative phrasing is flagged before anything reaches a model.
Three to twenty expert personas, arranged in one of six debate formats.
A turn is accepted only if it names a flaw in the argument before it. Flattery does not count.
Institutions and numbers that appear in no source are flagged, and a separate judge model scores each turn.
Answered, degraded, review required or abstained, decided by rules, not by the model grading itself.
After every round the council's positions are compared with each other, and the debate ends when they truly converge or stop moving.
After synthesis the action plan is run against eight fixed scenarios at once, and the result feeds back into the score.

A verdict can be pushed to your issue tracker or other systems, but only under rules you control.

The personas are agents. Before a round, each one gathers its own evidence from open sources and from your documents.
Each verdict carries a manifest: model versions, settings, a hash of the prompt, SHA-256 hashes of every document and web source, code version and seed.
Change the budget, deadline, risk or compliance limits and open a new debate linked to the original.
Agents can write Python and run it in a sandbox with no network and strict memory and time limits, then argue from the real output.
Upload PDF, Word, Excel and other files to the whole council or to one expert, alongside 31 research source types, from academic indexes to vulnerability data.
An optional off-the-record channel asks each speaker for a private view and records how far it drifts from what they said in the room.
Library personas keep long-term memory across debates and carry adjustable personality axes.
Runs on your own Linux server, in containers or on Kubernetes, pointed at your own model by default, with outside models as an option.
Export the verdict as Markdown or as a printable report.