microsoft/What-I-Did-Copilot

microsoft/What-I-Did-Copilot

Description: Your impact report — what you built, the skills augmented, and the ROI delivered

Language: Python

License: MIT

Stars: 33

Forks: 8

Open issues: 0

Created: 2026-03-30T20:52:26Z

Pushed: 2026-06-11T04:19:46Z

Default branch: main

Fork: no

Archived: no

README:

---

Try it now

Pick whichever matches how you use Copilot — all three install and run the same thing.

Option A — Copilot CLI plugin *(requires the GitHub Copilot CLI)*

In any Copilot CLI session:

/plugin install whatidid@awesome-copilot

Then just run:

whatidid # defaults to a 7-day lookback

Option B — VS Code chat plugin via `@agentPlugins` *(Awesome Copilot marketplace)*

1. Open the Command Palette → `Chat: Plugins` *(or type `@agentPlugins` in the Extensions search view)*. 2. Search `whatidid` → click Install. 3. In Copilot Chat, just ask: > *"give me a 7-day Copilot report"* · *"whatidid this month"* · *"summarize what Copilot helped me with today"*

> 💡 Power user tip: the plugin is a full Python checkout under > ~/.copilot/installed-plugins/awesome-copilot/whatidid/ (Windows: %USERPROFILE%\.copilot\...). > cd there and run python whatidid.py --30D directly. Note this is the marketplace-pinned release — see *Updating* below to refresh, or use Option C for true latest-main.

Option C — Clone the repo *(maximum control, dev-mode)*

Open a terminal (Windows Terminal, Terminal.app, or your favourite shell — including VS Code's built-in terminal), then:

gh auth login # one-time: authenticate to GitHub (enables AI analysis)
git clone https://github.com/microsoft/What-I-Did-Copilot.git
cd What-I-Did-Copilot
python whatidid.py # defaults to a 7-day lookback

Prerequisites: Python 3.10+, [`git`](https://git-scm.com/), and [GitHub CLI (`gh`)](https://cli.github.com/). See the [full requirements table](#requirements) below.

That's it. A report opens in your browser showing your last 7 days with Copilot.

🔄 Already installed? Update to the latest release

The plugin ships new features and methodology tweaks regularly — refresh whichever way you installed:

| You installed via… | How to update | |---|---| | Option A — Copilot CLI plugin | In a Copilot CLI session, run /plugin update whatidid@awesome-copilot. | | Option B — VS Code `@agentPlugins` | Open the Command Palette → `Chat: Plugins` (or @agentPlugins), find `whatidid`, and click Update. If no Update button appears, the marketplace already has you on the latest. | | Option C — Cloned repo | cd into your clone and run git pull. |

> The CLI plugin and VS Code plugin install the same marketplace package — updating one will not update the other. If you use both, run both update steps.

---

What you'll see

| | | |---|---| | ✅ Goals & leverage | Every project with human effort equivalents — see that a 10-min session replaced 3 hours of work. *What did Copilot actually deliver?* | | 📦 Artifacts produced | Scripts, reports, docs, configs — counted and categorized. *What tangible output came out of your AI sessions?* | | 🧠 Skills augmented | Hours mapped across 20+ roles — engineer, analyst, designer, architect. *What skills did Copilot make accessible to you?* | | 🎯 Collaboration style | A donut chart breaks active time across 9 work modes — Designing, Analyzing, Reviewing, Researching, Learning, Building, Refining, Course-correcting, Delegating — with labels next to each slice. *How are you directing AI, and where are the skills you need to grow as a manager of AI?* | | ⏰ Activity heatmap | When you collaborate and how your day breaks down. *When is AI most useful in your workflow?* | | 📐 Estimation evidence | Transparent methodology grounded in [13 peer-reviewed sources](docs/effort-estimation-methodology.md). *Why should anyone trust these numbers?* | | 💸 Credit-burn patterns | Every flagged pattern cites the Anthropic / OpenAI / GitHub guidance it implements — with clickable sources. *Where am I burning credits, and what does the published guidance say?* See the [credit-optimization methodology](docs/credit-optimization.md). |

> 📊 A note on the numbers. Credit and cost figures are estimates, calculated from the token counts in your local session logs and GitHub's published per-model rates. They give an accurate picture of the *shape* of your AI usage, but your actual GitHub bill can differ depending on your plan, included credit allowance, and billing details that aren't visible in local logs.

---

🆕 What's new in this release

• Learning intent expansion — the classifier now catches genuine learning queries: *"how do I X"*, *"help me understand"*, *"what's the best way to..."*, *"tell me about"*, *"pros and cons of..."*, *"primer on..."*, plus dozens more phrasings. A hand-holding bypass routes *"I don't understand how X works"* to Learning instead of Course-correcting.
• New methodology doc — [docs/credit-optimization.md](docs/credit-optimization.md) synthesizes credit-burn pattern the tool detects with the exact Anthropic / OpenAI / GitHub source it implements, including short excerpts.
• AI Investment and Consumption Patterns — new sub-segments for Model Mix, Top Sessions and behavior pattern analysis that drive up consumption, based on guidance from OpenAI, Anthropic, and GitHub.

---

More options

whatidid --14D # last 14 days
whatidid --30D # last 30 days
whatidid --date 2026-03-19 # specific date
whatidid --from 2026-03-01 --to 2026-03-31 # date range
whatidid --7D --email # send via Outlook
whatidid --7D --email you@company.com # send to a specific address
whatidid --refresh # force re-analysis

🏗️ How It Works

~/.copilot/session-state//events.jsonl (Copilot CLI sessions)
/Code/User/globalStorage/ (VS Code Copilot Chat
emptyWindowChatSessions/.jsonl sessions — same pipeline)
│
▼
harvest.py → scan sessions, extract messages, tools, files, intents
│
▼
analyze.py → AI categorization via GitHub Models API (gpt-4o-mini)
│ → calibrated effort estimation with quantitative signals
▼
report.py → HTML report: story arc, donut charts, heatmaps, ROI
│
▼
whatidid.py → opens report in browser; --email sends via Outlook COM

See [docs/architecture.md](docs/architecture.md)...