Open source · MIT

Your sprint review, written from git.

sprint-review reads what your team shipped and writes the deck the business understands. Every line traced to a real commit, real screenshots of what changed, ready before the meeting.

Open the demo deck →

CLI · GitHub Action · Claude Code plugin · MCP server · Claude, GPT, Gemini, Bedrock or a local model

Real decks: VS Code · Next.js · Supabase · Excalidraw

sprint-reviews/2026-11-16/deck.htmlLive deck
PlayingFull screen ↗

How it works

The model writes. The code checks.

A model alone gets the words right and the facts wrong. So the words come from the model, and everything that has to be true is done in code.

Read the sprint

Commits, changed files and pull request descriptions from your git history, by date or by tag.

Write for the room

Themes in the language of your audience: what changed for them, not which files moved.

Check every line

Each point must name real commits. Plumbing moves under the hood. A second reader flags what's unclear, and it gets rewritten.

Ship the deck

One self-contained HTML deck with speaker notes and a presenter view. Also PowerPoint and Markdown.

Features

Built to run every sprint, unattended.

Traced to commits

A line that can't name the commits behind it doesn't make the deck. Every correction is logged in checks.md.

Before and after

Screenshots diffed pixel by pixel: from your visual tests, a folder, or taken by the tool from your app's URLs.

A second reader

A separate call reads only the slides, like your audience will. Lines it stumbles on are rewritten once and checked again.

In CI, on a schedule

A GitHub Action and a GitLab template: the deck is ready on review day, posted to Slack if you like.

Edit in your browser

sprint-review edit opens the content beside the live deck. Change a word, see the slide, save.

Your brand, your agent

Colors, fonts and logo from your own PowerPoint. Runs from Claude Code, Cursor and other MCP clients.

Get started

One command. No config needed.

Run it in any git repository with an API key set. Add a config later to name your product, set the audience and point it at your screenshots.

# a preview of what it reads, no AI call
npx @guuskeunen/sprint-review --dry-run

# write the deck for the last sprint
export ANTHROPIC_API_KEY=...
npx @guuskeunen/sprint-review

# change anything, with the deck beside it
npx @guuskeunen/sprint-review edit sprint-reviews/2026-11-16/review.json
“I finally understand what the developers did.”
Project manager, on the first generated review

Questions

Good to know

Why not just ask an AI for a sprint review?

You can, once. sprint-review does it every sprint with no one in the loop: it reads the exact range, refuses lines it can't trace to commits, diffs real screenshots, and keeps a log of every correction. The result is something you can present without checking it line by line.

What does it send to the model?

Commit subjects, bodies, changed file names and, if you allow it, pull request descriptions. Never your code. It runs on your machine or in your CI with your own key: there's no sprint-review server. Run --dry-run to see exactly what would be sent, and read the security and privacy page.

What does a run cost?

Two or three model calls per sprint, typically a few cents to a few dimes depending on the size of the sprint and the model.

Which models does it work with?

Claude by default, with a fallback model on errors. Also Amazon Bedrock, Azure OpenAI, OpenAI, OpenRouter, Gemini, Mistral, and local models with Ollama or LM Studio, where nothing leaves your network.

Can it match our company style?

Set a color and logo, or point it at an existing PowerPoint: it takes the accent color, fonts and logo from the theme. There's a light and a dark deck.

Does it work without screenshots?

Yes. Screenshots make the deck better, but themes, speaker notes, milestones and usage numbers all work without them.

Ready on review day

Spend the hour on the demo, not the slides.