AI Engineering Coach: Measure How You Actually Code with AI
馃幆 TL;DR
AI Engineering Coach is an open-source VS Code extension from Microsoft that reads the local session logs your AI coding assistants already write, then turns them into a private analytics dashboard. It scores your prompting habits, flags anti-patterns, measures your AI-generated output, and surfaces repeated prompts you could promote into reusable skills.
It鈥檚 harness-agnostic (Claude Code, GitHub Copilot, Copilot CLI, Codex, OpenCode, and more), runs 100% locally, and does not cost you extra tokens for its core analytics. Think of it as a Strava for the way you work with AI.
The question nobody is measuring
Most of us now reach for an AI coding assistant before we reach for the keyboard. GitHub Copilot, Claude Code, Codex, Gemini CLI. They鈥檝e quietly become the default surface for writing software. But here鈥檚 the uncomfortable question I kept coming back to:
Am I actually getting better at this, or am I just using it more?
We obsessively measure the AI: token counts, model benchmarks, latency. We almost never measure ourselves: the quality of our prompts, how often we review what the model generated before shipping it, whether we keep re-typing the same instructions, whether our repos even give the agent enough context to succeed.
That鈥檚 the gap the AI Engineering Coach fills. It doesn鈥檛 write code for you. It holds up a mirror to how you write code with AI, and that distinction is the whole point.
flowchart LR
You([You, coding with AI]) -->|prompts 路 edits 路 tool calls| Tools["AI coding tools
Copilot 路 Claude Code 路 Codex 路 ..."]
Tools -->|already write| Logs[("Local session logs
on disk")]
Logs --> Coach["AI Engineering Coach
reads, never writes"]
Coach -->|reflects back| Insights["Prompt quality 路 anti-patterns
output 路 reusable skills"]
Insights -.->|so you level up| You
style Coach fill:#cce5ff,stroke:#1f6feb,stroke-width:2px,color:#000
style Insights fill:#e6ffed,stroke:#2da44e,color:#000
style Logs fill:#fff4c2,stroke:#b7950b,color:#000The loop nobody closes: your tools already write the logs. The Coach just reads them back to you, so the feedback finally points at you, not the model.
