Governed multi-perspective review · v0.6

Peer review for ideas, not people.

Independent AI lenses read the same text, disagree on the record, and produce a cited recommendation — then a human Chair decides. Every report is sealed and verifiable.

Already have a workspace? Sign in →

5 built-in lenses + BYO personas5 review templatesEd25519-sealed reportspublic seal verificationREST + TypeScript/Python SDKs

Single-answer AI hides its assumptions.

One model, one voice, one verdict — and no record of what was weighed or who dissented. For policy, postmortems, marketing claims and anything a regulator or board might ask about later, that is not a decision you can defend.

Council makes the disagreement part of the output.

Each persona submits structured findings independently. Findings are pooled, clustered into formal issues, debated in bounded rounds, and turned into a recommendation that cites its evidence. Minority views are preserved, not averaged away. A human Chair ratifies — or doesn't.

How it works

Six stages. Every one of them on the record.

Submit

an artefact and a review question.

Independent review

each persona reads alone and returns structured findings (stance, concerns, strengths, questions, lens limits).

Issues

findings are pooled and clustered; material disagreements become formal issues.

Bounded deliberation

issue-by-issue, round-limited, every move logged.

Recommendation

cited to findings and issues; uncited assertions are counted, not hidden.

Chair decision + sealed report

a human accepts, amends, or returns for revision; the report is signed (Ed25519) and anyone with the link can verify the seal without seeing the content.

Personas never run an open-ended group chat. Discussion is issue-bound and round-limited by design.
Independent lenses

Each persona has a declared role, primary question and known blind spot.

You can see all three — on every review and in every report.

Base Mode (control)
numeric anchor · model-default judgment

What does the text actually say, without a specialised lens?

BureaucraTick
accountability

Who owns this, by when, and what happens if not?

AutisTick
literal precision

What do these words actually promise?

PhysicsTick
evidence

Does the evidence support the claim?

BankManagerTick
risk & reversibility

What is the downside, and can it be undone?

NoBullshiTick
practicality

Can this actually be done as written?

SarcasTick
unintended interpretation

How will a sceptic read this?

+ KidTick, TourettesTick, TeacherTick, TheBardTick … and your own personas.

Base Mode's spectral axes are a numeric anchor; its prose is model-default judgment — we label it that way on every report.

Review templates

Packs — what you'd actually use it for.

A pack = seated personas + chair criteria + thresholds + a regression suite.

public_essay_v1

Public essay / epigraph

Is it clear, meaningful, publishable?

Run the sample →
policy_v1

Policy / governance

Accountability, obstruction, risk, practicality.

Run the sample →
technical_claim_v1

Technical / research claim

Evidence and first-principles integrity.

Run the sample →
incident_postmortem_v1

Incident postmortem / RCA sign-off

Evidenced timeline, named owners, honest recurrence risk, reversible actions.

Run the sample →
marketing_claims_v1

Marketing claims / compliance

Every claim read literally, evidenced, read back as a sceptic would, scored for regulatory risk.

Run the sample →
Sealed, cited, verifiable

The report is the product.

  • CitedRecommendation lines carry finding ids; uncited assertions are counted in the open.
  • Honest about its instrumentsSpectral axes are shown as tonal evidence with their scoring path, never as “deterministic” unless they are; auto-chair (test harness) decisions are banner-labelled non-binding.
  • Verifiable/verify/<run_id> confirms the seal for anyone, revealing hashes and timestamps only.

Verify a real report

API first

Built for integration.

  • REST with OpenAPI/v1/openapi.json, tenant-scoped; session login or machine API keys.
  • SDKsTypeScript (@bureaucratick/council-sdk, zero deps) and Python (bureaucratick-council, stdlib only).
  • Webhooks & meteringHMAC-signed run events; idempotency keys; usage + quality metering per tenant.

Create a workspace & API key Integration guide

import { CouncilClient } from "@bureaucratick/council-sdk";

const council = new CouncilClient({ baseUrl: DEMO_URL, apiKey: process.env.BTC_API_KEY });
const run = await council.reviews.create("ten_sandbox", {
  council_template: "marketing_claims_v1",
  artefact: { type: "text", content: copy },
  review_question: "Can this be published as-is?",
  wait: false,
});
const done = await council.reviews.waitFor("ten_sandbox", run.run_id);
const html = await council.reviews.reportHtml("ten_sandbox", run.run_id);
Built to be audited

Trust, in specifics.

  • Human Chair is the final authority; the system recommends, it does not determine. Every Chair decision is attributed and timestamped.
  • Tenant isolation, per-tenant policy (allowed providers, persona caps, rate limits) and metering.
  • Reports sealed with Ed25519; seal verification is public; stored reports are hash-checked against the seal on every export.
  • Multi-provider by design (xAI, OpenAI, Anthropic); provider and model are recorded per persona review.
  • Quality is instrumented: structured-output failure rate, clarification rate, human-override rate and time-to-decision are first-class metrics in the product.

Put a real document in front of the Council.

Pilots run on your artefacts, in your tenant, with your Chair. We set up the pack, you bring the text.