Epistemic observatory and continuously updated machine intelligence utility predictor.
Find a file
tegwick 6da2245581 Record Grok-by-forward and the ChatGPT email gap for IR-WP-0010.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1170398@bnt-lap001
Assistant-Session: 622cd705-cb31-4322-ba08-dd42e44fa583
2026-10-05 16:24:19 +02:00
.claude/rules Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
catalog Review IR-WP-0004 evidence gaps and capture provider profile metadata 2026-09-14 15:46:33 +02:00
compendium Add an unverified Eureka Machine lead and park its ideas as nudges. 2026-10-04 14:24:02 +02:00
concepts Added some comments and perspective to review later 2026-09-14 22:19:43 +02:00
data New observations 2026-10-04 18:26:02 +02:00
digests New observations 2026-10-04 18:26:02 +02:00
docs Define reviewed publications and record the field-sampling frame. 2026-10-04 14:51:01 +02:00
examples Add portable evidence bundles and budgeted OpenRouter trials 2026-09-13 23:50:19 +02:00
frontier Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
history Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
intelligence_radar Define reviewed publications and record the field-sampling frame. 2026-10-04 14:51:01 +02:00
nudges Define reviewed publications and record the field-sampling frame. 2026-10-04 14:51:01 +02:00
ops Define reviewed publications and record the field-sampling frame. 2026-10-04 14:51:01 +02:00
policies Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
registry Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
research Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
task-router Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
tests Define reviewed publications and record the field-sampling frame. 2026-10-04 14:51:01 +02:00
tools Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
watchlist Add an unverified Eureka Machine lead and park its ideas as nudges. 2026-10-04 14:24:02 +02:00
workplans Record Grok-by-forward and the ChatGPT email gap for IR-WP-0010. 2026-10-05 16:24:19 +02:00
.custodian-brief.md chore(consistency): sync task status from DB [auto] 2026-10-05 01:39:38 +02:00
.gitignore Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
.repo-classification.yaml Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
AGENTS.md Build reproducible capability advisor and scheduled source capture 2026-09-13 23:07:41 +02:00
ArchitectureBlueprint.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
BenchmarkCatalog.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
C3ResearchDeliverablesStandard.md Research deliverbles standard, concept on earned equity, data collection and digests added 2026-09-14 22:04:44 +02:00
CLAUDE.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
GOAL.md Close IR-WP-0004 and separate credential billing and research follow-ups 2026-09-14 15:56:57 +02:00
IntelligenceConceptModel.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
INTENT.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
LICENSE Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
Makefile Add portable evidence bundles and budgeted OpenRouter trials 2026-09-13 23:50:19 +02:00
README.md Retain unarchived ChatGPT and Grok briefs from the local inbox. 2026-10-04 14:24:03 +02:00
ResearchProgram.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
SCOPE.md Retain unarchived ChatGPT and Grok briefs from the local inbox. 2026-10-04 14:24:03 +02:00
SourceCatalog.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
TaskModelEvaluationMethod.md Integrate founding explorations and bootstrap operational radar 2026-09-13 22:42:09 +02:00
WORK-RECORDS.md chore(consistency): refresh the work-record index 2026-10-05 01:42:28 +02:00

Intelligence Radar

Epistemic observatory and task-specific machine intelligence capability and economics advisor.

The v0.2 implementation combines a Compendium, a source-capture Radar, and an executable Capability Advisor. Read INTENT, scope, and the operating contracts.

Run locally

Requires Python 3.11+ and Make. No package installation or API key is needed.

make check
make demo-advisor
python3 -m intelligence_radar ingest catalog/sources.json
python3 -m intelligence_radar advise examples/source-backed-task.json \
  --catalog catalog/reviewed-2026-09-13.json --as-of 2026-09-13
python3 -m intelligence_radar import-briefs
python3 -m intelligence_radar --help

import-briefs retains ChatGPT and Grok automation exports from the local inbox named in ops/schedule.json, skipping that folder's archive/ directory. run-due does this on the same timer. The retained copies are unverified briefs in digests/external/.

The advisor selects five measurements, checks constraints, ranks evidenced profiles, estimates workload cost scenarios, and records outcomes for empirical success bounds. Saved recommendations can be rendered with report and verified with replay. The source-backed example makes evidence gaps visible; the synthetic demo exercises complete ranking without claiming real model performance.

Source captures retain original bytes and retrieval receipts. Changed sources create review-needed observations. Daily/weekly jobs run through run-due; health shows results. See scheduling and data contracts.

Knowledge and operations

Path Purpose
IntelligenceConceptModel.md, compendium/ Concept model and accessible theory maps
ArchitectureBlueprint.md, ResearchProgram.md Target architecture and research program
BenchmarkCatalog.md, catalog/ Candidate measurement instruments; imported seeds need verification
SourceCatalog.md, watchlist/ Source discovery and editorial coverage
TaskModelEvaluationMethod.md, policies/, task-router/ Authoritative method, policies, and operational templates
data/observations/ Immutable, content-addressed observation envelopes
digests/, frontier/, research/ Dated editorial artifacts; imported drafts are marked unverified
ops/ Runbook, cadence, and scheduling status
history/ Unmodified source archives and checksums
docs/integration-review.md Evaluation, conflicts, and integration decisions
workplans/ Canonical Coulomb work records projected into Statehub
nudges/ Raw ideas kept for a later look, with the context they came from. Not work records.

Imported September 2026 rankings and prices are research leads, not validated recommendations. The local user timer is managed separately from the historical external automation IDs.

Statehub: domain infotech, topic custodian, prefix IR-WP-. Commit workplan edits, then run make sync (pushes commits and reconciles Statehub). See agent instructions.