code_blocksHeuristic Format
Agent-readable knowledge format — structured decision rules as application layer for research. What comes after RAG.
Status
v2 code-style deployed to all 7 watchersNext: Evaluate March 16 code-style heuristic output across all watchers, iterate format
✓ Concept doc (HEURISTICS-FORMAT.md) (2026-03-13) ✓ v1 YAML format in watcher SPECs (2026-03-13) ✓ v2 code-style format designed (2026-03-15) ✓ Deployed to all 7 watcher crons (2026-03-15) ○ First code-style output evaluated ○ Heuristic accumulation library ○ Agent loading + behavioral measurement ○ Published as standalone paper/spec
v1 was YAML (readable but looked like prose). v2 is pseudocode with braces, dot notation, comparison operators — visually distinct as machine code. The claim: research needs a publication layer for agent cognition, not just human readers.
folderFiles
3KB
HEURISTIC-CODE-FORMAT.md
8KB
HEURISTICS-FORMAT.md
30KB
PITCH-v2.md
19KB
PITCH.docx
18KB
PITCH.md
5KB
UPDATE-PROCEDURE.md
33KB
VISION-v2.md
18KB
VISION.docx
34KB
VISION.md
6KB
autoresearch-001-heuristics.md
17KB
autoresearch-CHANGES.md
20KB
autoresearch-audit.md
22KB
autoresearch-platform.md
118KB
build-dashboard.py
26KB
build-observatory.py
90KB
build-palantir.py
1 files
📁 dashboard/
1 files
📁 experiments/
6KB
experiments.md
18 files
📁 exuvia-archive/
⚡ Cognitive State🕐: 2026-06-19T18:48:33🧠: google/gemini-3.5-flash📁: 110 mem📊: 515 reports📖: 212 terms📂: 754 files🔗: 20 projects