agentic-workflows

https://github.com/user-attachments/assets/9f0239bf-20e0-459f-b137-17cce0edd1b2

This video contains AI-generated content.

---

What it does

AI Engineer Coach reads your local AI session logs and turns them into actionable insights — no data leaves your machine.

• Track progress -- practice scores, weekly trends, daily activity charts
• Detect anti-patterns -- 45 rules across prompt quality, session hygiene, code review, tool mastery, and context management
• Measure output -- AI-generated code volume by language, workspace, model, and harness
• Discover skills -- find repeated prompts and turn them into reusable skills
• Score context health — agentic readiness checks, instruction-file audits, workspace context maps

---

Installation

The extension is not published to a marketplace or Releases page, so you build the .vsix yourself and install it. Pick whichever build path fits your setup.

Path 1 -- Dev Container build (no local Node.js/npm)

Prerequisites:

• VS Code
• Dev Containers extension
• Docker or Podman

Steps:

1. Clone the repo and open it in VS Code.
2. Reopen in container.
3. Run:

npm ci
npm run package

1. Install the generated .vsix (see Install the built VSIX below).

Path 2 -- Local build

Prerequisites:

• VS Code
• Node.js and npm

Steps:

git clone https://github.com/microsoft/ai-engineering-coach.git
cd ai-engineering-coach
npm ci
npm run package

Then install the generated .vsix (see below).

Install the built VSIX

macOS / Linux

code --install-extension ai-engineer-coach-*.vsix

Windows / PowerShell

code --install-extension (Get-ChildItem . -Filter 'ai-engineer-coach-*.vsix' | Select-Object -First 1).FullName

If the CLI does not work, install it from the VS Code UI: press Ctrl+Shift+P, type Install from VSIX, then browse to the .vsix file and select it.

After install:

1. Open the command palette (Cmd+Shift+P / Ctrl+Shift+P)
2. Run AI Engineer Coach: Open Dashboard
3. Navigate pages from the sidebar, filter by workspace or harness

---

Run as a canvas in the GitHub Copilot app

The same dashboard also runs as a canvas inside the GitHub Copilot app, so you do not need VS Code to use it.

A canvas is an interactive side panel in the GitHub Copilot app. Rather than replying only in chat, the agent can open a canvas to show rich, task-specific UI that you view and interact with directly while you keep working. Extensions register their own canvases, and this repo ships one named AI Engineer Coach under .github/extensions/ai-engineer-coach/. It reuses the exact webview bundle from the VS Code extension and parses your local session logs in process, so nothing leaves your machine.

To open it:

1. Clone this repo and open it as a project in the GitHub Copilot app.
2. Build the project once:

npm install && npm run build

1. Open the AI Engineer Coach canvas. On a fresh clone it shows a setup card with the build command and reloads into the full dashboard once the build finishes. No manual reopen needed.

A few features depend on the local VS Code language model and are hidden in canvas mode: Skill Finder, Learning Center, the Level Up section, and the Context Health AI review. Everything driven by your on-disk logs (Dashboard, Timeline, Coding Moments, Output, Patterns, Anti-Patterns) works the same. App sessions show up as GitHub Copilot App and terminal sessions as GitHub Copilot CLI in the harness breakdown.

---

Pages

Observe

Measure

GitHub App

This section appears only when the local GitHub Copilot app is installed.

Issue credit percentages are rough relative estimates, not accurate AI Credit or billing figures. They normalize the locally recorded total_nano_aiu usage across linked issues to show approximately where AI usage was spent. The percentages depend on issue links inferred from local workspace and issue-reference data and must not be used for billing reconciliation. Explicit GitHub issue URLs pasted in either of the first two session turns also establish the issue link; URLs pasted later are excluded to avoid treating research links as the session's source issue. All reconciliation