Everything you need to get started

What Videlic does

Videlic reads the full log of an AI coding session — every file the agent read, every edit it made, every command it ran — and turns it into a report you can act on at a glance. Instead of trusting the agent’s summary, you see what actually changed, how risky those changes are, which tests were deleted or can never fail, and exactly how the session unfolded.

It runs automatically on the work your agent pushes, so you get a report without changing how you code.

Quickstart

Three steps to your first report.

1. 1

   Install the GitHub App

   Connect Videlic to GitHub and choose the repositories the App can read.

2. 2

   Connect your agent

   Open Setup in your dashboard and run the one-line command once — it works the same on macOS, Windows, and Linux. It installs a small hook in your coding agent that sends the session to Videlic each time the agent stops, and detects the agent automatically. No SDK, no code changes.

   $ npx @videlic/connect <your-token>
3. 3

   Open a pull request

   Code as usual. When you open a PR, the verdict posts as a comment in about a minute. Open the full report from the comment or your dashboard.

What’s in a report

Every session runs three independent engines, plus a full timeline. Each looks at the work from a different angle, and any one of them can surface a problem the others miss. Every plan gets all of them — Free included.

Reading your report

Each report opens with a clear verdict, a one-line headline, and a short reason — so you know where things stand before you read another word.

• Clear — no issues found in the review.
• Review — worth a look before you merge. The report points to exactly what, and where.
• Blocked — a serious problem. Don’t merge until it’s resolved.

Every finding is backed by concrete evidence — the agent’s own words, the file and line it points to, and the change it relates to — so you can click straight to the source instead of taking the result on faith. Nothing is a black box.

Test visibility

Coding agents often shorten test output to keep their context small, so a report can see that tests passed without seeing which ones ran. Test visibility asks your project’s test tool for the list of test files each run used, so your report shows exactly what was tested.

Turn it on

Go to Settings → General → Analysis and switch on Test visibility. It applies to your whole workspace. Owners and admins can change it, and it stays off until someone turns it on.

What it runs

• Only test commands your coding agent already ran in the session, in list mode — no tests run again.
• Only while the pull request is open, on its latest commit, with no uncommitted changes.
• On the developer's computer, with that developer's permissions. Your test tool loads your project's configuration, as it does when the agent runs it.
• Works with Jest and Vitest on macOS and Linux.

Supported agents

Claude Code is supported today — auto-detected from the session format, with nothing to configure. Cursor, Cline, and Codex are on the way.

Integrations

Videlic posts the verdict where your team already reviews code — on the pull request and in your inbox today, with GitLab and Slack on the way.

Plans & Teams

You’re billed per review — one per pull request, no matter how many agent sessions go into it. Re-pushes and re-reviews on the same PR are free, so you’re never charged for iterating. Every plan runs all three engines plus the timeline; you pay for scale, not features.

Free is free forever — no credit card. Pro raises your monthly reviews. Team adds a shared review pool, a team dashboard, an audit log, and member roles — Owner, Admin, and Member. See the pricing page for current limits.

FAQ

Privacy & Data

The hook sends every session your coding agent runs on that computer, and we use what it sends to produce your reports and to improve how we review sessions. You choose which repositories the GitHub App can read, and you can stop uploads at any time by removing Videlic’s Stop entry from ~/.claude/settings.json on that computer, or by deleting the token the hook was set up with in Settings → CLI token. For the full details on what we collect and how it is handled, read our Privacy Policy.