Eval Trace Knowledge Base
updated: 2026-07-17
Covers
Workflow, agent, and model-behavior evaluation; traces; context-overfitting detection; reliability metrics; evidence gates; style-transfer checks; and quality read-outs.
Not Covered
General observability unrelated to behavior/workflow quality; product analytics unless used as an evaluation surface; model-training infrastructure except where it changes the evaluation contract.
Current As Of
2026-07-17 — active. Includes context-overfitting, the Eval Trace prototype, workflow-quality mapping, LLM style-transfer evaluation, the LKY Voice objective-plus-blind-listening gate, and the LKY Avatar factual-accuracy/persona-quality/fabrication separation.
Workflow, agent, and model-behavior evaluation; traces; context-overfitting detection; reliability metrics; evidence gates; style-transfer checks; and quality read-outs.
Structure
raw/— raw Markdown provenance mirror for agents and source inspection.wiki/— synthesized knowledge pages: concepts, entities, summaries, and syntheses.- Schema and maintenance rules: see
CLAUDE.md.
Usage
- Add new sources: update canonical source notes in
pixi-vault, then compile into this namespace. - Ask questions: agents read this wiki and cite raw/source paths.
- Publish: regenerate
pixi-wiki, run tests, then live-verify raw and HTML routes.
Eval Trace¶
Active namespace for evidence quality, behavior/workflow evaluation, reliability, and claim boundaries.
Canonical Source Roots¶
Projects/Eval Trace/Index.mdKnowledge/concepts/context-overfitting.mdKnowledge/concepts/style-transfer-evaluation.mdProjects/LKY Avatar/Index.md
Crosslinks¶
- agent-workflows
- pixi-vault
- ai-native-product-surfaces
- local-ai-infrastructure
Public Output Contract¶
When published to pixi-wiki, this namespace should expose:
/raw/eval-trace/README.md
/raw/eval-trace/wiki/index.md
/wiki/eval-trace/README.md
/wiki/eval-trace/wiki/index.md
Maintenance¶
- Edit canonical source notes first.
- Use
Wiki Compiler Maps/Namespace Wiki Compiler Map.mdfor routing decisions. - Do not compile Daily Notes directly unless promoted or verified.