brain.quietlyos.org . Phase 0 . foundation surface

The Brain grows because it gets corrected.

Approved, Approved+Reinforcement, or Redirected+Reinforcement... every major session ends with a human writing the WHY that compounds the Brain's judgment.

Without the loop, you have a logger. With it, you have an apprentice that gets more capable every week.

We built it this way because we know our own weaknesses well. If you build something different, it'll be because you know yours.

Phase 0 is the foundation. The Brain itself runs as a future Phase 2 deliverable. Today the page is honest about what is shipped and what is coming. The reinforcement loop is the load-bearing mechanism; the runtime is downstream of it.

01 How it works

One mechanism. Three verdicts.

Every decision the Brain makes carries a WHY at the moment of choice. Not retroactive. Not assembled later. The reasoning is captured in the same breath as the choice it explains.

At the end of every major session, a decision making member or team reads the report. Each call gets one of three verdicts. The corpus updates from each one differently, and the trust meter for that decision category moves accordingly.

Approved

silent

Reviewer reads the WHY at moment of decision and accepts. The choice and the reasoning matched the established pattern.

Corpus effect
No update. The original WHY was correct.
Trust meter effect
Ticks up for that decision category.

Approved + Reinforcement

with WHY

Reviewer accepts AND adds context that strengthens the pattern. The reasoning was right; now it is also more durable.

Corpus effect
Corpus appends the strengthening context. A named preference may emerge if the pattern repeats.
Trust meter effect
Ticks up. The category becomes safer to handle autonomously.

Redirected + Reinforcement

with WHY

Reviewer disagrees and explains why. The redirect is itself reinforcement. Teaching, not punishment.

Corpus effect
Corpus rewrites with the reviewer's WHY. The rule changes for next time.
Trust meter effect
Ticks down. The category re-escalates on similar future decisions until trust rebuilds.

The 'plus Reinforcement' on both Approved and Redirected is intentional. A redirect with a written WHY is reinforcement; the corpus learns from the correction the same way it learns from a strengthened approval. The reviewer is the teacher, not the gate.

Why WHY-at-time-of-decision

Retroactive reasoning lets a system rationalize bad choices. WHY captured before the choice is committed binds the reasoning to the moment. It is the discipline that makes the corpus honest.

Why a trust meter per category

Global agreement-rate hides the categories drifting away from the reviewer's actual preferences. Per-category subdivision keeps the calibration honest. A category that loses trust re-escalates on its next decision until it rebuilds.

02 Architecture

OS plus Brain. Wisdom Library is separate.

The Operating Standard clarifies WHO an organization is. The Brain clarifies HOW it decides. The Wisdom Library, a separate artifact, holds what the organization knows.

Conflating those three flattens the architecture and the corpus loses precision. The distinction is small to read and load-bearing in practice. The Brain reads from the Operating Standard for constitutional rules; it reads from the Wisdom Library for relevant context; it writes to its own ledger and corpus.

OPERATING STANDARDQOSWHO an org isvalues . voice . branduniverse . interconnectcontent . tools . peoplequietlyos.orgADVISOR BRAINBrainHOW it decideschoices . WHY-at-timeverdicts . reinforcementtrust meter . corpusbrain.quietlyos.orgWISDOM LIBRARYWisdomwhat it KNOWStool wisdom librariescaptured insights . booksarticles . conceptsseparate artifactreadsreads
Three distinct artifacts. The Brain reads from the Operating Standard (constitutional rules) and from the Wisdom Library (relevant context). It does not claim either's territory.

What the Brain reads

  • Constitutional rules from the Operating Standard schemas
  • Relevant context from the Wisdom Library
  • Precedent: prior decisions, prior verdicts, prior WHYs

What the Brain writes

  • New ledger entries with WHY at the moment of choice
  • Corpus updates when a verdict adds reinforcement
  • Trust meter recalculations per decision category

Three weights, three behaviors

  • HARD RULES: constitutional. Never overridden.
  • SOFT PREFERENCES: learned. Grow via reinforcement.
  • NOVEL: cold-start. Always escalate to the human.
03 Build map

Foundations to open standard. Every node in the journey.

The Brain map follows the same JSON-source-of-truth, deterministic-renderer, drift-validator pattern the Operating Standard uses for its own development map. Reuse, not fork. 7 of 27 nodes shipped (25%).

You are here

Shipped 7 of 27 (25%)

Planned 20

Milestones

A ... Schema Layer Complete 3 of 3 remaining
decisions.v1 schema, report-format template, and append helper all shipped. The Brain has a JSON contract and a writer.
B ... Runtime + Reinforcement Operational 12 of 12 remaining
First overnight run completed and verdicted via the three-verdict mechanism. The Brain is load-bearing; the corpus compounds across sessions.
C ... Brain v1 Complete 20 of 20 remaining
Every p1 through p5 node shipped. Calibration is routine. Open standard published. First supporter has forked. The Brain pattern is a transferable QOS reference implementation.

p0 Origin & Foundations (7/7)

What the Brain stands on before code. Master capture, OS+Brain companion framing locked in memory, three-verdict reinforcement loop, role-based reviewer design call, share-not-sell voice discipline, public-site launch plan. Phase 0 is the architectural ground truth.

  • shipped
    p0.brain.master-capture Master Architectural Capture

    Captures the full Brain architecture: Strategy C autonomous-overnight orchestrator, three-verdict reinforcement loop, decision-ledger schema sketch, anti-patterns, success metrics, integration points with existing systems, phased build plan.

  • shipped
    p0.brain.os-companion OS + Brain Companion Framing

    Locks the Brain as the operational HOW-layer that complements QOS. QOS clarifies WHO an organization is (schemas); Brain clarifies HOW it decides (choices + WHY). Wisdom Library is a separate artifact handling what the org KNOWS, not part of the Brain's territory.

  • shipped
    p0.brain.role-based-reviewer Role-Based Reviewer Design

    Forward-looking design call: decisions.v1 schema must support multiple reviewers and role-based routing from day one. A future supporter adopting the Brain might have a small board, not a single founder. Schema needs reviewer (role + identity) and verdict.signed_by from the start.

  • shipped
    p0.brain.share-not-sell Share-Not-Sell Voice Discipline

    Named corpus preference enforcing no-competitive-framing on all public-facing QWF content. Frame work as 'what fits our weaknesses and strengths,' never 'better than what others do.' Underneath: invitation, not argument. Reader's first job is Know Thyself.

  • shipped
    p0.brain.site-launch-plan brain.quietlyos.org Launch Plan

    Phased launch plan for the public Brain home. Separate-repo decision (QuietlyWorking/quietly-brain), CF Pages + SvelteKit, subdomain CNAME, six Phase 0 sections, seven new components, day-one node tree, three-sweep anonymity discipline, mission-thesis hero copy locked.

  • shipped
    p0.brain.site-phase-0 brain.quietlyos.org Phase 0 Public Launch

    Build and ship the public Phase 0 surface of brain.quietlyos.org per the launch plan. Six sections (hero, how-it-works, architecture, build map, what-goes-here-next, open standard), seven components, supporter sweep + em-dash scrub at build, CF Pages deploy, DNS CNAME, SSL, cross-link with quietlyos.org footer.

    Depends on: p0.brain.site-launch-plan

  • shipped
    p0.brain.three-verdict-loop Three-Verdict Reinforcement Loop

    Locks the three verdict states (Approved / Approved+Reinforcement / Redirected+Reinforcement) and their effects on corpus and trust meter. Names the redirect itself as a reinforcement event when paired with WHY.

p1 Schema Layer (0/3)

decisions.v1 schema, the report-format template, the append-decision helper script. The JSON contract for every Brain entry, plus the writer.

  • planned
    p1.brain.append-script append_decision.py Helper

    Python helper script that appends a decisions.v1 entry to the ledger with WHY, trust weight, and trace. Validates against decisions.v1 schema before write. Returns structured result.

    Depends on: p1.brain.decisions-v1

  • planned
    p1.brain.decisions-v1 decisions.v1 Schema

    JSON Schema (Draft 2020-12) defining the decision-ledger entry shape: id, context, call, WHY-at-time-of-decision (required), expected outcome, trust weight (HARD-RULE / SOFT-PREFERENCE / NOVEL), verdict (pending / approved / approved-with-reinforcement / redirected), feedback (TIG's WHY on redirect), trace (commits, files, HQ items, dev-map nodes), reviewer (role + identity), verdict.signed_by.

  • planned
    p1.brain.report-format Report Format Template

    Locked template for end-of-session Brain reports. Required: Non-technical description first per call, top-N call detail, action table at end, open-questions section, cross-build observations. Format requirement no-silent-approval-during-formation enforced until trust meters stabilize.

    Depends on: p1.brain.decisions-v1

p2 Runtime (0/5)

The headless Claude Agent SDK runner that reads a build plan, queries the corpus at decision time, logs WHY, pauses on novel decisions and escalates to HQ, stages commits without pushing. The Brain becomes load-bearing here.

  • planned
    p2.brain.commit-staging Commit Staging (No Push)

    Brain stages commits but never pushes to main. TIG green-lights pushes during morning review. The zero-autonomous-commits gate from CLAUDE.md applies absolutely.

    Depends on: p2.brain.headless-runner

  • planned
    p2.brain.corpus-query Corpus Query at Decision Time

    Decision-time lookup against memory/feedback_*.md files plus prior decision-ledger entries. Returns relevant SOFT PREFERENCES and precedent decisions for the Brain to reason against.

    Depends on: p2.brain.headless-runner

  • planned
    p2.brain.first-overnight-run First Successful Overnight Run

    Inaugural autonomous overnight run executes a real build plan (likely a future schema checkpoint), produces ledger entries, queues HQ escalations as needed, stages commits. Morning review verifies the run via the report format.

    Depends on: p2.brain.corpus-query,p2.brain.surprise-pause,p2.brain.commit-staging

  • planned
    p2.brain.headless-runner Headless Claude Agent SDK Runner

    Long-running Claude Agent SDK process that reads a build plan, executes checkpoints, calls append_decision.py at every decision point, surfaces escalations to HQ, stages commits without pushing.

    Depends on: p1.brain.decisions-v1,p1.brain.append-script

  • planned
    p2.brain.surprise-pause Surprise Pause + HQ Escalation

    When the Brain hits a NOVEL decision (not in corpus, not a HARD RULE), it pauses the run, files an HQ item with full context, and waits for TIG's verdict. No autonomous resolution of novel calls.

    Depends on: p2.brain.headless-runner

p3 Reinforcement UI (0/4)

The interface that closes the loop. Batch review surface, three-verdict mechanism (Approved / Approved+Reinforcement / Redirected+Reinforcement), trust-meter calculation, corpus update on redirect.

  • planned
    p3.brain.batch-review Batch Review Surface (HQ Filter View)

    HQ Command Center filter view that surfaces every Brain ledger entry awaiting verdict, grouped by session, with the report format pre-rendered. TIG (or designated reviewer) verdicts in 5 to 10 minutes.

    Depends on: p2.brain.first-overnight-run

  • planned
    p3.brain.corpus-update-on-redirect Corpus Update on Redirect

    When a verdict is Redirected+Reinforcement, the writer updates the relevant memory file with TIG's WHY. Append for new categories, rewrite for existing rules. Decrement trust meter.

    Depends on: p3.brain.verdict-mechanism

  • planned
    p3.brain.trust-meter-calc Trust Meter Calculation

    Per-decision-category agreement-rate over the last 20 decisions. High (90%+) auto-handles, medium (70-89%) flags for spot-check, low (<70%) re-escalates. Subcategorization prevents over-generalization.

    Depends on: p3.brain.verdict-mechanism

  • planned
    p3.brain.verdict-mechanism Three-Verdict Mechanism

    Reviewer interface that captures Approved / Approved+Reinforcement (with WHY) / Redirected+Reinforcement (with WHY). TIG-only signature. Append-only ledger; no edits to past verdicts.

    Depends on: p3.brain.batch-review

p4 Calibration (0/4)

Per-category trust meters, stale-corpus detection, random-sample spot-check on high-trust decisions, prompt-injection integrity protections.

  • planned
    p4.brain.per-category-trust Per-Category Trust Subdivision

    Subdivide trust meter into specific decision shapes (e.g., 'cascade naming for forbidden patterns' vs 'cascade naming for vocabulary alternatives') so high agreement in one shape does not inflate trust in adjacent shapes.

    Depends on: p3.brain.trust-meter-calc

  • planned
    p4.brain.prompt-injection-integrity Prompt Injection Integrity Checks

    Signed ledger entries (agent-id + commit hash). Append-only ledger. TIG-only verdict signatures. Random-sample integrity checks against known-clean baseline.

    Depends on: p1.brain.decisions-v1

  • planned
    p4.brain.spot-check-high-trust Random-Sample Spot-Check on High-Trust Decisions

    Every batch report random-samples a few HIGH-TRUST decisions for explicit verdict ('the Brain says this was 95% confidence... do you actually agree?'). Track over-approval as its own metric.

    Depends on: p3.brain.verdict-mechanism

  • planned
    p4.brain.stale-corpus-detection Stale Corpus Detection (90-Day Rule)

    Every memory file gets a last-reinforced timestamp. Decisions in categories not reinforced for 90 days re-escalate to TIG. Stale rules expire safely instead of compounding silently.

    Depends on: p3.brain.corpus-update-on-redirect

p5 Open Standard (0/4)

The Brain pattern published as a public QOS reference implementation. Documentation, governance license, adopt-page with fork instructions, first supporter adopter.

  • planned
    p5.brain.adopt-page Adopt-The-Brain Page

    Public page on brain.quietlyos.org with concrete fork-it instructions: clone the schema, scaffold a corpus, plug into your decision rights structure, run your first batch review. Includes worked examples from QWF (anonymized) and any consenting supporter adopters.

    Depends on: p5.brain.public-pattern-doc,p5.brain.governance-license

  • planned
    p5.brain.first-supporter-fork First Supporter Fork

    First non-QWF organization adopts the Brain pattern using the published schema + adopt page. Their corpus stays private; HARD RULES inherited from QOS public standard; SOFT PREFERENCES are theirs.

    Depends on: p5.brain.adopt-page

  • planned
    p5.brain.governance-license Governance License

    Open-source license under which the Brain pattern (schema + reference implementation) is published. Aligns with the broader QOS license decision (currently '[pending governance]').

    Depends on: p5.brain.public-pattern-doc

  • planned
    p5.brain.public-pattern-doc Brain Pattern Documentation

    Public documentation of the Brain pattern as a QOS reference implementation. Lives at brain.quietlyos.org; covers schema, runtime, reinforcement loop, anti-patterns, success metrics, fork-it instructions.

    Depends on: p2.brain.first-overnight-run,p3.brain.corpus-update-on-redirect

Note

The map is authored at 005 Operations/Standards/roadmap/BRAIN.development-map.json in the QWU backoffice and copied into this repo on each update. Schema reuse: validates against qos_development_map.v1.schema.json (no Brain-specific fork in Phase 0). Identity differentiation via identity.shortName: "BRAIN". Map version v1.0.0. Public render with supporter-anonymity sweep, youth sweep, and em-dash scrub applied at build time.

04 What goes here next

Honest about today. Naming what is coming.

Phase 0 ships the foundation. The Brain runtime, the live ledger, the trust meters, and the named-preferences corpus are all downstream. Each lights up at its own phase and gets its own surface here.

The placeholders below name the coming surfaces and the phase that ships them. No mocked data. The page tells the truth about today.

Live Decisions

Phase 2 . anonymized ledger entries
Phase 2 placeholder

This is where anonymized decision-ledger entries will render. Each entry leads with a non-technical description, then surfaces the choice, the WHY at the moment of decision, the verdict, and the date. Three sweeps (supporter, youth, TIG-personal) run at render time. Lights up in Phase 2, once the Brain runtime ships.

Trust Meters

Phase 3 . per-category agreement rate
Phase 3 placeholder

Per-category agreement-rate bars over the last 20 decisions. High-trust categories handle autonomously; medium flag for spot-check; low re-escalate. Subcategorization prevents trust inflation. Lights up in Phase 3, once the verdict mechanism and trust-meter calculation ship.

Named Preferences

Phase 3 . corpus entries with reinforcement history
Phase 3 placeholder

Named preferences with their reinforcement history. Each entry lists the sessions where the preference was reinforced or redirected, plus its last-reinforced timestamp for stale-corpus detection at the 90-day mark. Lights up in Phase 3, alongside the verdict mechanism.

05 Open standard

Built to be forked. Quietly.

The Brain pattern is one road through the same country many builders cross. We chose it because we know our own weaknesses well. If you build something different, it'll be because you know yours.

The schema for ledger entries (decisions.v1) ships in the next phase and will live in the Operating Standard schema gallery. Once it ships, the contract is portable: clone the schema, plug it into your decision-rights structure, run your first batch review with your own corpus.

Where the standard lives

The Operating Standard is the public home for QWF's machine-readable identity layer. The Brain pattern lands there as a reference implementation when the schema, runtime, and reinforcement mechanism stabilize.

Visit the Operating Standard

Source on GitHub

The repo for this site, the build map JSON, and the build-time sweeps are public. Read what we did and why we did it. Use what fits. Leave what does not.

github.com/QuietlyWorking/quietly-brain

License pending governance. The QWF Advisor Brain pattern, schema, and reference implementation will publish under the same license as the broader Operating Standard once that decision lands.