AI pull request review for Azure DevOps, GitHub, GitLab, and Forgejo, with repository context and memory of your team's review decisions.
What ProPR does with a change, from the moment it opens to the comment your team reads.
Connect Azure DevOps, GitHub, GitLab or Forgejo, in the cloud or self-hosted. ProPR picks up new pull requests on its own, with no pipeline to write or maintain.
Supported platformsA review draws on semantic search across your code, linked work items, wikis and past reviews, so ProPR judges a change against what it is meant to do.
How ProPR worksWhen your team rejects a finding, ProPR records the decision. On the next push it leaves that discussion closed and reviews only the files that changed.
Reviews and thread memoryProPR checks each finding against your code before it posts it. The comment arrives as a thread on the exact line, with its severity, where your team already reviews.
ProPR tracks which of its findings your team acts on, so precision and recall are numbers you can read instead of a claim you have to trust.
One review standard across every repository, on the AI account your organisation already pays for.
Use the AI provider your organisation already has a contract and a budget for: Azure OpenAI, OpenAI, Anthropic, AWS Bedrock, Google Vertex, or a model you host yourself. One team can run on one provider while another runs on a different one.
Model choice is one setting, referred to by a name you pick. Moving a team to another vendor, because the pricing changed or a better model shipped, means repointing that name. Nothing else about how your reviews are configured has to change.
ProPR already knows what the common models cost and how much context they take, so spend reporting works the day you install it. Pick a model from the list and its details come with it, with no spreadsheet of token prices to maintain.
Azure DevOps, GitHub, GitLab, and Forgejo, cloud or self-hosted. Code quality stops depending on which platform a team happened to pick, and a platform administrator decides which hosts are available at all.
Decide what review should cost per month, per pull request, or per run, then see and control it.
Give a team a monthly figure, a ceiling for any single pull request, and a ceiling for any single run. A soft limit pauses new reviews until budget frees up. A hard limit stops work in progress and publishes what it already found. Leave a field blank for no limit.
Spend so far, both limits, and a projection for the rest of the period on one chart. You get to plan around an overrun in week two, while there is still budget left to reallocate.
Cost and volume per team over any date range, broken down by which model did the work. Enter your negotiated rates and the figures match the invoice instead of the vendor's list price.
Total spend for every team in one view, against each of their budgets, with a twelve-month trend. Enough to answer what AI review costs the organisation without collecting numbers from each team.
Deeper scrutiny where a change is risky, silence where it is not, and a record behind every comment.
Risky files can be reviewed more than once, from a different angle, with a security specialist's brief and checks derived from CodeQL. You choose which model does it, and you can trial a new model on live pull requests without a word of it reaching your team.
When your team resolves or dismisses a point, ProPR remembers the decision. The next push will not reopen it in slightly different words. Reviewers that do get muted within a fortnight.
"Why did it say that?" has an answer. Each review keeps a full record of what it examined, what it found, what it chose not to post, and why, including what a re-review reused instead of paying to check again.
Set how assertive it is and what severity is worth posting, replace its instructions where your standards differ, or commit your conventions to a file beside the code so they apply only where they are relevant.
Bound where your code may be sent, and keep the evidence that the boundary held.
State which AI services and which hostnames your organisation permits, and ProPR refuses anything else. The check runs when someone saves a configuration and again every time it is about to send code, so tightening the policy covers what is already set up.
Each team gets isolated configuration, credentials, and budget, managed from one place. Agencies and platform groups can onboard a new client without a new deployment.
See what every review cost and which model produced it, stop one that is going wrong, restart one that was paused for budget, or exclude a pull request from review entirely.
New models appear constantly, and an air-gapped install should not be stuck on last year's list. Update ProPR's knowledge of models by uploading a file, which keeps the refresh entirely inside your network and preserves your own pricing.
ProPR watches your repositories, and when a pull request opens or updates it reviews the change and posts its findings as threaded comments where your team already works. There is no pipeline to write. You connect a repository once from the admin console and reviews start on their own.
Behind that, it reads each changed file with the surrounding context it needs, checks its own findings against your code, and applies a consistent rule about what is worth interrupting a developer for. Uncertain or broad observations go into a summary, and only what it can support lands as an inline comment.
Info
No CI pipeline configuration required. Connect a repository, choose an AI account, set a budget, and ProPR handles discovery and review orchestration in the background.
Read about the review process, supported source-control platforms, and AI providers in the documentation. Deployment and edition details are on the self-hosted page; hosted beta access is on the hosted offering page.