# microsoft/AI-Engineering-Coach

better agentic engineering

Repository: https://github.com/microsoft/AI-Engineering-Coach
Canonical: https://ross.abutalabs.com/products/ai-engineering-coach
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T13:42:15+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 8
- inputs: {"age_days": 119, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3730, forks 520 (observed 2026-08-28T04:08:15.729653+00:00)

## What it is
A VS Code extension that analyzes local AI coding assistant session logs (across any harness) and turns them into actionable insights via a dashboard. It tracks practice scores, detects 45 anti-patterns, measures AI-generated code output, finds reusable skills, and scores context health — all locally with no data leaving the machine.

## Use cases
- analyze my AI coding assistant usage patterns
- detect anti-patterns in how I prompt AI coding tools
- measure how much code AI generates in my projects
- find repeated prompts and turn them into reusable skills
- audit my instruction files and workspace context quality
- track weekly trends in my agentic coding practice
- see which models and harnesses I use most

## When to choose
- you use AI coding assistants (Copilot, Claude Code, etc.) and want to improve your agentic engineering habits
- you want privacy-first analytics that keep session data local
- you want a single dashboard across multiple AI coding harnesses
- you want actionable coaching on prompt quality, session hygiene, and context management

## When to avoid
- you need a published marketplace extension with one-click install (you must build the .vsix yourself)
- you don't use AI coding assistants at all
- you need team-level or cloud-synced analytics rather than local, per-machine insights
- you use an editor other than VS Code 1.115+

## Facets
- artifact type: plugin
- maturity: active
- function: analytics, developer-tools, monitoring, data-visualization
- domain: developer-tools, artificial-intelligence, analytics
- platform: editor-plugin, cross-platform
- tags: vscode-extension, ai-coding-assistants, agentic-engineering, session-log-analysis, prompt-quality, local-privacy, copilot-analytics, desktop

## Member repositories
- microsoft/AI-Engineering-Coach (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:15.729653+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:29:13.777773+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/AI-Engineering-Coach (fetched 2026-08-28T04:08:15.729653+00:00, sha fee0eefe7309)
- Data as of 2026-08-30T08:39:29.467469+00:00.