#!RFC-AI/2;id=18;draft=4;v=0.4.0;status=draft;lang=en;dir=auto;theme=chatgpt-mono;sha256=a78ff5aa11baae4d24ca64dbdef4ba603000b9ddb8962727135d48832da0470f
For easier reading, view RFC-AI documents using RFC-AI Reader software.

RFC-AI 18 — RESEARCH INTELLIGENCE AND CCRA EVIDENCE LEDGER
DOCUMENT CLASS: AI RFC — INTELLIGENT-WORK GUIDANCE
STATUS: DRAFT FOR CEO REVIEW — ENTIRE RFC-AI SYSTEM UNIMPLEMENTED

1. PURPOSE — WHAT AND WHY
Use cumulative collaborative research intelligently. Research should become shared understanding and a map of remaining leads rather than duplicated browsing and citation theater.

2. INTELLIGENT-WORK DIRECTION
Consult credible internal investigations first, assess freshness, trace actual sources, record unresolved leads and let later specialists extend verified research without losing its limitations.

3. PROPOSED IMPLEMENTATION APPROACH
Use the relevant authorized Interface, component and expressly designated Standard: RFC-AI 5 and relevant research-ledger component. Investigate the complete relevant context before deciding what the assignment means (see RFC-AI 11). A competent worker may discover, invent and improve the necessary methods during implementation; this guiding AI RFC is not required to repeat low-level APIs, algorithms or technology choices. Previous and legacy systems are research evidence only, never an implementation of this draft.

4. EVALUATION AND ACCOUNTABILITY
Use independent DAVG as described in RFC-AI 22 to challenge whether the eventual real-world result meets the objective, not whether the AI RFC looks like a traditional API specification. A missing prerequisite creates an active cross-worker recovery obligation through the worker coordination Interface, not a reason to abandon the task (RFC-AI 20 and 31). Report only verified effects and preserve lessons without reintroducing old operational mistakes.

5. DESIGN CUSTODY
Original subject-specific intended contract: Cumulative internal and external research, reviewed/unexplored leads, source access level, freshness, counterevidence, prewrite receipts and source-chain links; reconcile RFC-AI 5.
Implementation tasks, legacy-derived candidate methods, proposed data schemas, tests and open engineering questions are kept with this draft's append-only objectives.txt or the responsible Interface/Standard. This RFC has NOT been implemented; it does not approve a deployment or create a new CEO release gate. Rewritten 2026-11-02T20:28:09.285Z.


## HISTORICAL FAILURE EVIDENCE — RESEARCH ONLY; NOT AN RFC-AI IMPLEMENTATION
Historical context: Repeated broad research did not consistently reuse prior trustworthy research or track what remained unexplored.
Historical reports have mixed evidence quality; verify primary facts before adopting a claimed root cause. Preserve source provenance and do NOT operationalize retired legacy policies as current RFC authority.

## MUST-DESIGN CRITERIA — CEO-DIRECTED PROPOSED FUTURE SYSTEM
MUST-18-01: MUST leverage cumulative, collaborated prior research without treating historical claims as authority; every new source must be linked to the question it resolves.
MUST-18-02: MUST allocate remaining research leads to qualified roles while ensuring immediate authorized progress continues.

IMPLEMENTATION STATUS: Entire RFC-AI system NOT IMPLEMENTED. Historical systems are independent past research material; no test or existing service may be counted as implementing this RFC-AI.

## DESIGN REVIEW ADDENDUM 2026-11-03 — CCRA QUALITY
REQ-AI-18-CCRA-001: Research ledgers MUST distinguish source fetched, source understood, alternative considered, finding domain-verified and source inaccessible; independent source-access receipts cannot alone certify understanding. Preserve transferable lessons for later worker Continuity; current Context and Assignment decide applicability to present machine and target.