Use cases / Teams running coding agents
Agents that check their own work first
Let the agent call visualdiff before it opens the pull request, and fix what it finds.
The problem
Feedback that arrives after the pull request opens costs a human round trip. The cheapest review is the one the agent runs on itself.
What visualdiff does
- The same analysis runs from a CLI with no dependencies, from any CI, or from the API.
- An agent can run it on its working tree and read the findings as JSON.
- An MCP server, so agents can call it as a tool, is on the roadmap.
npx-free: curl the CLI, run it with Node, exit non-zero on hold.
Related
- Reviewing pull requests written by agentsAgents open pull requests faster than anyone can read them. Read the 10% that decides whether it is safe.
- Large refactors that hide a behaviour changeA refactor is supposed to change nothing. Find the one line that does.
- Stopping hallucinated dependenciesSlopsquatting: attackers register the package names models invent. Catch them at review.
- Seeing which running systems a change reachesThe diff says rds.tf. The map says orders-db, the API in front of it, and the queue behind it.