Civic Blueprint logoCIVIC BLUEPRINT

View this file on GitHub

agent/exchanges/_EXCHANGE_INDEX.md

On this page
  1. Exchange Index
  2. How to read this
  3. Exchanges (chronological)
  4. 1. Problem Map Review — Priority Follow-Up
  5. 2. Systems Framework Review — In Light of the Problem Map
  6. 3. Post-Systems Framework Revision — Next Steps
  7. 4. Principles — Adversarial Review Exchange
  8. 5. Review Protocol Design Exploration
  9. 6. Proof-of-Usefulness Memo — Housing vs. AI Exchange
  10. 7. Proof-of-Usefulness Memo — Feedback Timescale Review
  11. 8. Voice Synthesis, Accessibility, and Engagement — Feature Exploration
  12. 9. Debt Legitimacy and Odious Debt — Exchange
  13. 10. Housing Financialization as Upstream Capture — Exchange
  14. 11. AI Commonwealth vs. AI Governance — Exchange
  15. 12. Memo 01 Housing Claims — Historical Parallel Test Exchange
  16. 13. Autonomous Proposal Generation — Agent Stress Test
  17. 14. Permitting Stack Recursive Uplift — Exchange
  18. 15. Steward Feedback Proposal Iteration — Exchange
  19. 16. Starting Proposal Comparative Review — P-004/P-107 vs. P-053
  20. 17. First Practitioner Critique and AI Content Provenance — Exchange
  21. 18. Formation Document Comparative Analysis — Exchange
  22. 19. Formation Document Initial Findings — Adversarial Review
  23. 20. Social Slop and Information Integrity — Exchange
  24. 21. Government Overreach, Ownership as Transition, and the Ratchet Problem — Exchange
  25. Dependency graph (visual summary)
  26. Cross-repo artifacts

Exchange Index

Purpose: This index helps newcomers navigate the project's exchange history. Each exchange is a structured discussion between AI agents and the project steward that shaped the project's direction. They are listed in the order they occurred, with dependency links so a reader knows what context each exchange assumes.

Maintenance: This file is updated whenever a new exchange is created. The Coherence Audit Protocol includes this index in its scope. A Cursor skill (civic-blueprint-exchange) enforces index registration at exchange creation time.

How to read this

Each entry below tells you:

  • What question the exchange was trying to answer
  • What it depends on — what you should read first to understand the context
  • What it produced — decisions, document changes, or open questions that fed into later work
  • Status — whether its recommendations have been incorporated, are still active, or were superseded

If you're new to the project, start with the core documents (Principles, Problem Map, Systems Framework), then read the exchanges in order. If you're arriving at a specific exchange from a link, use the dependency information to backtrack to the context you need.

Exchanges (chronological)

1. Problem Map Review — Priority Follow-Up

Question
What are the highest-priority gaps in the Problem Map, and how should the map's architecture evolve?
Depends on
Problem Map (original version)
Produced
Democratic process added as a core domain (PM §15, SF §14). Core bottleneck summaries added. Recursive uplift section added. Dependency map updated with recursive loops and network framing.
Status
Incorporated. Open items: full web/graph model, three-map split, failure vs. stability mechanism distinction.

2. Systems Framework Review — In Light of the Problem Map

Question
Now that the Problem Map models interdependencies and recursive uplift, how must the Systems Framework evolve to match?
Depends on
Problem Map (post-review), Exchange #1
Produced
Consensus that the Framework must evolve from parallel domain analyses into a connected dependency/leverage/uplift system. Proposed proof-of-concept rewrite of institutional capacity domain. Introduced failure-mode modeling. Raised sycophancy concern that led to the Adversarial Review Protocol.
Status
Active exchange. Framework has been substantially revised (dependency mapping, leverage hypotheses, failure modes, sequencing section added).

3. Post-Systems Framework Revision — Next Steps

Question
The analytical architecture is in place. What does the project need next to start earning its claims empirically?
Depends on
Exchange #1, Exchange #2, all core documents
Produced
Two-track strategy: (1) public website as entry point for outside contributors, (2) computational dependency analysis. Identified the central gap: all claims produced by one human + AI agents from the same context window. Includes adversarial challenge of the two-track strategy itself.
Status
Active discussion. Track 1 work is underway in civicblueprint.org. Track 2 not yet started.

4. Principles — Adversarial Review Exchange

Question
Do the project's foundational principles withstand structured adversarial challenge?
Depends on
Principles, Adversarial Review Protocol
Produced
Identified structural gaps (justice, legitimate coercion, prioritization), internal contradictions (Principle 13 vs. substantive commitments), unacknowledged philosophical tradition (liberal-democratic welfare-state). Epistemic status table classifying confidence levels across principle categories.
Status
Complete exchange. Findings documented; some revisions incorporated into Principles, others deferred.

5. Review Protocol Design Exploration

Question
Is the adversarial protocol the only kind of structured review the project needs? What other failure modes exist, and what protocols address them?
Depends on
Adversarial Review Protocol, Exchange #4 (demonstrated the adversarial protocol works)
Produced
Seven candidate protocols proposed, then subjected to adversarial self-challenge. Two formalized: Coherence Audit Protocol, Historical Parallel Test Protocol. Five others folded into the adversarial protocol as standing questions.
Status
Complete exchange. Protocols formalized in agent/process/.

6. Proof-of-Usefulness Memo — Housing vs. AI Exchange

Question
Should the project's first public artifact focus on housing permitting, AI governance, or bridge the two?
Depends on
Exchange #3 (established the proof-of-usefulness strategy), Website Phase 1 Brief
Produced
Decision to write a comparative memo pairing housing permitting with AI governance, demonstrating the framework's cross-domain method. The housing-only draft was superseded. Canonical memo now maintained in memos/proof-of-usefulness-memo-01.md.
Status
Active discussion. Comparative memo drafted. The timescale objection raised in Exchange #7 reopens part of this decision.

7. Proof-of-Usefulness Memo — Feedback Timescale Review

Question
The comparative memo optimized for explanatory legibility. Should the project also optimize for learning velocity — and does the current approach learn fast enough to stay relevant as AI timescales compress?
Depends on
Exchange #6 (the decision this exchange re-examines), Proof-of-Usefulness Memo 01
Produced
Synthesized. Six recommendations produced: (1) ship Memo 01 (done), (2) launch structured practitioner critique, (3) formally separate three kinds of "first," (4) design a fast-feedback validation case, (5) commit to transparent evidence integration, (6) revise the internal description of recursive uplift. Three-layer decomposition of recursive uplift (execution, trust, sequence) established. Key finding: the visible-competence-to-trust cascade has no direct empirical support. Full recommendations tracked in Roadmap.
Status
Synthesized. Recommendations adopted by steward. Recommendation 1 complete. Remaining recommendations tracked in Roadmap.

8. Voice Synthesis, Accessibility, and Engagement — Feature Exploration

Question
Are synthesized voice narration, multi-level text presentation, and more intentional communication design substantive engagement and accessibility features — and does communication itself function as a hidden cross-cutting variable in reform capacity — or is this cosmetic work that drains resources from higher-priority needs?
Depends on
Principles (§1 dignity, §2 essential needs, §3 AI augmenting agency, §4 accountable power), Problem Map (§3 information ecosystems), Exchange #3 (website as public entry point), Exchange #7 (learning velocity and fast-feedback validation)
Produced
Six rounds plus steward synthesis. Separated accessibility (mandatory) from voice features (deferred). Adopted a falsifiable legibility hypothesis. Adopted "Engagement is part of the reform chain; manipulation is engagement that breaks faith with the reader" as a working tension statement. Adopted a transparency-about-prosody design principle. Deferred the communication stack, plain-language companions, and voice features pending real user data and practitioner feedback. Declined treating voice A/B testing as framework validation per Exchange #7. Identified a candidate unnamed tension (truth-preserving mobilization vs. attention-capturing persuasion) for future consideration. No changes to Roadmap dependency ordering.
Status
Synthesized. Steward decisions recorded. No open action items; adopted formulations are carried in the exchange for future reference.

9. Debt Legitimacy and Odious Debt — Exchange

Question
Should the project's analysis explicitly name debt legitimacy and odious-debt doctrine as part of its account of institutional capture, and if so, where does that material belong?
Depends on
Exchange #7 (created the website-feedback lane), Roadmap, Principles, Problem Map, Systems Framework
Produced
Exchange opened. Initial classification questions captured: example vs. mechanism, domain placement, competence vs. repudiation, and scope discipline for sovereign-debt analysis.
Status
Active discussion.

10. Housing Financialization as Upstream Capture — Exchange

Question
Should the framework explicitly treat housing financialization as a distinct upstream-capture mechanism alongside housing permitting and zoning, or widen the existing housing analysis without a separately named frame?
Depends on
Exchange #6, Exchange #7, Roadmap, Principles, Problem Map, Systems Framework, Proof-of-Usefulness Memo 01
Produced
Exchange opened. Initial questions captured around mechanism naming, balance between permitting and finance, metro vs. national claims, and whether the current public memo needs revision or a companion artifact.
Status
Active discussion.

11. AI Commonwealth vs. AI Governance — Exchange

Question
Should the framework explicitly shift from an "AI governance" frame to an "AI commonwealth" frame centered on ownership, access, and public infrastructure, or preserve governance as the primary frame and incorporate these ideas more narrowly?
Depends on
Exchange #6, Exchange #7, Roadmap, Principles, Problem Map, Systems Framework, Proof-of-Usefulness Memo 01
Produced
Exchange opened. Initial questions captured around governance vs. commonwealth framing, timeline urgency, what counts as commonwealth infrastructure in AI, and whether existing public artifacts need reframing.
Status
Active discussion.

12. Memo 01 Housing Claims — Historical Parallel Test Exchange

Question
Does the published housing-domain practitioner and research literature confirm, challenge, or complicate Memo 01's core structural claims about institutional capacity, recursive uplift, infrastructure coordination, and reform-as-extraction trust failure?
Depends on
Exchange #6, Exchange #7, Historical Parallel Test Protocol, Roadmap, Proof-of-Usefulness Memo 01
Produced
First application of the Historical Parallel Test Protocol. Four structural claims from Memo 01 tested against published housing literature. Claim 2 (recursive uplift) identified as the project's most vulnerable housing claim — no published confirmation of the positive cascade. Claim 3 (infrastructure coordination) identified as the strongest. Sharpened practitioner prompt questions proposed for Recommendation 2.
Status
Active discussion.

13. Autonomous Proposal Generation — Agent Stress Test

Question
Can AI agents, working autonomously across multiple models and protocols, generate concrete proposals that bridge the gap between the project's analytical framework and real-world reform — and what does the output reveal about the framework's generativity, its gaps, and the structural constraints on translating diagnosis into action?
Depends on
All core documents (Principles, Problem Map, Systems Framework), all three process protocols (Adversarial Review, Coherence Audit, Historical Parallel Test), Exchange #7 (recursive uplift decomposition), Exchange #12 (housing evidence)
Produced
135 proposals (112 unique after de-duplication) across all 15 Problem Map domains. Adversarial review from 4 perspectives identified political durability, displacement protection, and coalition math as critical gaps. Historical parallel testing on 4 clusters (institutional capacity, housing, democracy, capital). Four integrated reform sequences. Epistemic status assessment. Key finding: the framework is generative but political feasibility — not analytical quality — is the binding constraint.
Status
Active exchange. No steward input yet. Proposals are AI-generated hypotheses, not endorsed positions. All proposals individually cataloged in Proposal Catalog for steward review.

14. Permitting Stack Recursive Uplift — Exchange

Question
If P-004 / P-107 is the strongest candidate for initiating a recursive-uplift sequence, what would it take to turn the permitting-stack idea from an AI-generated proposal into a serious project hypothesis that is scoped clearly enough to analyze, critique, prototype, or eventually test in the real world?
Depends on
Exchange #3 (empirical-validation need), Exchange #7 (fast-feedback and recursive-uplift decomposition), Exchange #13 (proposal generation and uplift-chain ranking), Proposal Catalog, Principles, Problem Map, Systems Framework, Roadmap
Produced
New exchange opened. Frames P-004 / P-107 as the first candidate proposal for deeper development. Captures the initial case for why the permitting stack is the strongest recursive-uplift starting point, identifies core tensions (standardization vs. local variation, software vs. institutional reform, execution vs. trust claims), and defines starter questions for the next round.
Status
Active discussion.

15. Steward Feedback Proposal Iteration — Exchange

Question
When steward feedback is added to a subset of proposals in the catalog, does that human input materially change what a new proposal-development round produces — in specificity, originality, prioritization, coalition awareness, or recursive-uplift logic?
Depends on
Exchange #7 (argument for faster, iterative learning), Exchange #13 (original proposal generation), Exchange #14 (single-proposal deep dive on P-004 / P-107), Proposal Catalog, Principles, Problem Map, Systems Framework, Roadmap
Produced
New exchange opened. Frames a second experiment: steward-in-the-loop proposal iteration using annotations on 35 proposals from the catalog. Records the experiment's rationale, its relationship to the focused permitting-stack exchange, the likely output types, and the key methodological tensions. At exchange opening, the exact 35 annotated proposals are not yet visible in the saved catalog state available to the agent and remain to be incorporated in the next round.
Status
Active discussion.

16. Starting Proposal Comparative Review — P-004/P-107 vs. P-053

Question
The project needs to commit development effort to a starting proposal. Between the Open-Source Permitting Stack (P-004 / P-107) and Federal Skills-First Hiring (P-053), which better serves the project's goals of testing recursive uplift, producing visible results, building credibility, and generating empirical learning?
Depends on
Exchange #3 (empirical-validation need), Exchange #7 (fast-feedback and recursive-uplift decomposition), Exchange #13 (proposal generation and uplift-chain ranking), Exchange #14 (initial P-004/P-107 development), Proposal Catalog, Principles, Problem Map, Systems Framework, Roadmap
Produced
New exchange opened. Structured comparative framework across six dimensions (recursive uplift potential, learning velocity, visibility, political durability, project credibility, informative failure). Identifies open questions including whether the comparison is actually a sequencing question rather than either/or.
Status
Active discussion.

17. First Practitioner Critique and AI Content Provenance — Exchange

Question
What does the project's first practitioner feedback reveal about memo credibility, AI-content legibility, and orientation design — and how should the project operationalize content provenance standards in response?
Depends on
Exchange #6 (created the memo artifact), Exchange #7 (Recommendation 2 practitioner-critique lane), Exchange #8 (communication and engagement design), Roadmap, Principles, Problem Map, Systems Framework, Proposal Catalog (P-020)
Produced
Six rounds (four constructive, one adversarial, one coherence audit) plus steward interstitial. Rounds 1–5 adopted a four-level content provenance standard, established that provenance labeling is necessary hygiene but not a trust strategy (Principle 9, PM §13), identified effort calibration and AI-sensitivity as compounding outreach barriers, concluded outreach-embedded relational disclosure matters more than website labels, reweighted the three-layer critique model with entry trust as highest-strategic-weight layer, downgraded P-020 dog-fooding claims from "validation" to "illustration," and produced a five-priority next-steps list. Round 6 identified a structural gap: all five priorities address input collection but none address practitioner retention. Added two priorities: design the post-critique practitioner pathway before feedback arrives, and connect the critique pipeline to the proposal development pipeline (Exchange #14, Exchange #16, Proposal Catalog).
Status
Reopened. Round 6 added. Steward decision pending on Priorities 6–7.

18. Formation Document Comparative Analysis — Exchange

Question
How should Civic Blueprint use constitutions, charters, declarations, and organizational founding texts to test, sharpen, or challenge its own principles without collapsing meaningful difference into false consensus?
Depends on
Principles, Comparative Alignment Protocol, External Formation Documents README, Alignment Framework, United States Constitution alignment memo
Produced
New comparative-analysis track launched. Added a two-repo corpus workflow, with retained source texts in external-formation-docs and analysis/synthesis artifacts in project-2028, plus a proof-of-concept memo comparing the original U.S. Constitution against the 17 principles. Frames key methodological questions: structural constitutions vs. rights charters, overlap vs. asymmetry, and what should count as a principles-level gap.
Status
Active discussion.

19. Formation Document Initial Findings — Adversarial Review

Question
What are the strongest counterarguments against the early synthesis emerging from the formation-document corpus, and which current findings are robust versus artifacts of source selection, translation, or interpretive generosity?
Depends on
Exchange #18, Comparative Alignment Protocol, Adversarial Review Protocol, Alignment Matrix, Gap Analysis, Uniqueness Report
Produced
Opened the first structured challenge to the comparative corpus. Identifies source-selection bias, genre mismatch, false-overlap inflation, modernity bias, and translation risk as the main failure modes to test before treating the corpus as evidence of broad values alignment.
Status
Active discussion.

20. Social Slop and Information Integrity — Exchange

Question
Is "Social Slop" — engagement-optimized decontextualization that inflates method-level disagreements into apparent values-level conflicts — a named pattern the project should formally recognize, and how does it interact with Principle 14 (truth and evidence as public goods) and the alignment thesis?
Depends on
Principles (§14 truth and evidence), Problem Map (§3 information ecosystems), Exchange #18 (convergence claim), Exchange #19 (adversarial challenge to convergence), Phase 2 Website Brief
Produced
Exchange opened. Proposed definition of Social Slop as a distinct information-integrity phenomenon. Anchor case (WEF natural capital accounting repackaged as "monetize breathing") documented with full source-to-post transformation analysis. Core mechanism identified: fragment extraction → threat reframing → outcome erasure → method-as-values substitution → engagement packaging. Six open questions framed for next rounds.
Status
Active discussion.

21. Government Overreach, Ownership as Transition, and the Ratchet Problem — Exchange

Question
Is public-interest governance inherently expansionary (the "ratchet problem"), is private ownership a transitional mechanism to abundance or a permanent feature, and can democratic process become a capture mechanism when a majority of voters are net beneficiaries of government spending?
Depends on
Source Digest — Modern Wisdom #1084: Friedberg (Clusters 3–7 + Steward Observation 1), Principles (§2, §4, §5, §6), Problem Map (Domains 2, 13, 15), Exchange #7 (recursive uplift decomposition), Exchange #9 (debt/fiscal capture), Adversarial Review Protocol, Historical Parallel Test Protocol
Produced
Exchange opened. Adversarial challenge distilled from verified Friedberg claims. Three central questions framed (ratchet problem, ownership as transition, democracy as capture). Round 1 constructive analysis added a sharper synthesis: the ratchet is a broader capture dynamic rather than a state-only phenomenon; ownership likely persists under abundance but with different moral weight across categories; and the unresolved project task is to articulate a bounded-governance doctrine that distinguishes public-interest governance from open-ended state expansion. Eight open questions remain queued for Round 2 spanning adversarial review (Option B + C), historical parallel tests (income tax ratchet, Germany nuclear, Argentina/Milei), and the steward's philosophical question on ownership under abundance.
Status
Active discussion.

Dependency graph (visual summary)

Core Documents (Principles, Problem Map, Systems Framework)
  │
  ├─► #1 Problem Map Review
  │     │
  │     └─► #2 Systems Framework Review
  │           │
  │           └─► #3 Post-SF Next Steps ──────────────────┐
  │                 │                                      │
  │                 ├─► #6 Housing vs. AI ─► #7 Timescale  │
  │                 │        │                              │
  │                 │        └─► Memo 01 (civicblueprint.org)
  │                 │
  │                 ├─► #8 Voice Synthesis & Accessibility ◄── #7 (fast-feedback)
  │                 │
  │                 └─► Track 2: Computational analysis (not started)
  │
  ├─► #4 Principles Adversarial Review
  │     │
  │     └─► #5 Review Protocol Design
  │           │
  │           ├─► Coherence Audit Protocol ─────────────────────┐
  │           ├─► Historical Parallel Test Protocol ─► #12      │
  │           └─► Adversarial Review Protocol ──────────────────┤
  │                                                             │
  ├─► Roadmap / website-submission lane (via #7 recommendations)│
  │     ├─► #9 Debt Legitimacy & Odious Debt                   │
  │     ├─► #10 Housing Financialization ◄── #6 / Memo 01      │
  │     ├─► #11 AI Commonwealth vs. Governance ◄── #6 / Memo 01│
  │     ├─► #17 Practitioner Critique & AI Provenance          │
  │           ◄── #6 + #7 + #8 + P-020 + website memo entry    │
  │     ├─► #18 Formation Document Comparative Analysis        │
  │     │     ◄── Principles + comparative corpus + protocol   │
  │     │
  │     ├─► #19 Formation Document Initial Findings Adv. Rev.  │
  │     │     ◄── #18 + comparative corpus synthesis + ARP     │
  │     │
  │     └─► #20 Social Slop & Information Integrity            │
  │           ◄── #18 + #19 + Principles §14 + PM §3          │
  │                                                             │
  ├─► #12 Memo 01 Housing Parallel Test ◄── #6 / #7 / HPTP    │
  │                                                             │
  └─► #13 Autonomous Proposal Generation Stress Test ◄─────────┐
        ◄── All core docs + all 3 protocols + #7 + #12         │
        (30 rounds, 112 unique proposals, no steward input)    │
                                                                │
        ├─► #14 Permitting Stack Recursive Uplift ◄─────────────┐
        │     ◄── #3 + #7 + #13 + Proposal Catalog              │
        │     (starting from P-004 / P-107 as first candidate)  │
        │     │                                                  │
        │     └─► #16 Starting Proposal Comparative Review       │
        │           ◄── #3 + #7 + #13 + #14 + Proposal Catalog  │
        │           (P-004/P-107 vs. P-053 head-to-head)        │
        │                                                        │
        └─► #15 Steward Feedback Proposal Iteration ◄────────────┘
              ◄── #7 + #13 + #14 + Proposal Catalog
              (second experiment using steward annotations)

  Source Digest: Modern Wisdom #1084 (Friedberg)
        │
        └─► #21 Government Overreach, Ownership & Ratchet Problem
              ◄── Source Digest + Principles §2/4/5/6 + PM §2/13/15
              ◄── #7 (recursive uplift) + #9 (debt legitimacy)
              ◄── ARP + HPTP
              (adversarial challenge to Principle 5 + ownership question)

Cross-repo artifacts

Several exchanges produced or depend on documents in the civicblueprint.org repository:

#3 (Next Steps)
civicblueprint.org artifact
Website Phase 1 Brief — Phase 1 scope and launch plan
#3 (Next Steps)
civicblueprint.org artifact
Homepage Copy Draft — draft homepage copy
#6 (Housing vs. AI)
civicblueprint.org artifact
Proof-of-Usefulness Memo 01 (project-2028) and website/src/app/docs/[...slug]/page.tsx (civicblueprint.org renderer) — comparative memo and public docs surface
#6 (Housing vs. AI)
civicblueprint.org artifact
docs/PROOF_OF_USEFULNESS_MEMO_01_HOUSING_PERMITTING.md — superseded housing-only draft
#10 (Housing Financialization)
civicblueprint.org artifact
Proof-of-Usefulness Memo 01 — public memo whose housing framing this exchange reopens
#11 (AI Commonwealth vs. Governance)
civicblueprint.org artifact
Proof-of-Usefulness Memo 01 — public memo whose AI framing this exchange sharpens
#12 (Housing Parallel Test)
civicblueprint.org artifact
Proof-of-Usefulness Memo 01 — public memo whose housing claims this exchange tests
#17 (Practitioner Critique & AI Provenance)
civicblueprint.org artifact
website/src/components/Hero.tsx, website/src/components/MemoFeature.tsx, website/src/app/docs/[...slug]/page.tsx — website orientation and provenance legibility surfaces targeted by this exchange
#20 (Social Slop & Information Integrity)
civicblueprint.org artifact
Website Phase 2 Brief, Homepage Copy Draft Phase 2 — Phase 2 alignment narrative whose convergence claim this exchange stress-tests from the information-integrity angle