Seer is the AI debugger that uses Sentry context – like errors, traces, logs, replays, and commit history– to flag breaking changes, automatically root cause issues in production, and fix what you missed.
Sentry’s MCP brings Seer debugging into your local environment.
As issues pop up in development, you can instantly debug them with Seer, before they have a chance to reach production.
In GitHub, Seer automatically checks your PR for mistakes that would likely cause significant issues in production – think security issues, errors, and major performance problems.
Seer’s AI code review checks potential bugs in your PR against real issues that have happened in production to make sure its reviews are all signal, no noise.
Tracking down the root cause is the worst part of debugging. Seer analyzes all the issue context for you, using everything Sentry knows about the issue (stack traces, event history, logs, replays, traces, profiles) to pinpoint the cause.
Seer can also suggest a fix, and you choose whether to apply the patch yourself, let Seer open a PR, or send it to your coding agent.
Seer works with pretty much all programming languages and frameworks, from Assembly to Zig, passing through all stacks supported by Sentry: including web, mobile, and desktop.
Seer leverages distributed tracing data to understand your solution even when it spans across multiple, distributed systems. It can propose fixes that impact more than one repository at a time.
Seer doesn’t just live in Sentry’s UI. It gives you automated, low-noise PR reviews in GitHub, and connects to your AI-enabled IDE to work alongside you as you build.
Seer is the only AI debugging agent that has access to all the context available to Sentry, including the details of the error, stack traces, environment information, logs, breadcrumbs, traces and spans, and your source code–the whole codebase even across multiple repositories. By sorting through all this data, Seer provides more accurate and complete solutions.
Your data belongs to you.
Seer does not use your data, including your application's error information and source code, to train generative AI models, and AI-generated output from your data is shown only to you, not other customers.
Seer gives us exactly what we need — straight to the point, fast, and accurate. It’s saved us hours per feature, and that translates to the bottom line.
Read MoreSentry [Seer] is actually… good? One-shot fixed this error that I've spent the last 2 hours debugging
Read MoreSeer provided insights that led us to a fix within 30 minutes, for a bug that would have taken an engineer at least a day otherwise.
Amazing. @getsentry Seer did better than I would have. I wouldn't have thought to have a special ogType for articles. https://t.co/Y44lHdMitM
Read MoreSeer is available to all Sentry users on a paid plan (Team, Business, or Enterprise) at $40 per active contributor, per month. An active contributor is anyone who commits two or more PRs in a connected repo.
More details are available in the Seer pricing docs.
All Sentry users on a paid plan or trial can use Seer. You will be prompted to enable Seer and generative AI features within the Sentry interface upon attempting to use them for the first time.
Seer can fix most bugs and performance issues in your application. Seer includes issue scan, which intelligently tries to determine the likelihood that an issue can be fixed with a code change, and enables you to run Seer on those issues. Alternatively, you can configure Seer to run issue fix automatically on issues that it believes it can help you fix.
Seer supports all programming languages and frameworks supported by Sentry, including web (frontend and backend), mobile, and desktop. Virtually all modern programming and configuration languages are supported, and then some more.
Seer respects your privacy and your data, and it comes with robust guarantees:
AI-generated output from your data is shown only to you, not other customers
Your data is not used to train generative AI models without your express consent (off by default)
We process your data only via trusted subprocessors that are not allowed to use your data to train their own models
You can read more in our docs.
Teams that want to turn off Seer and generative AI features can go to Settings → Organization → General Settings → Enable Generative AI Features and disable the feature toggle.
Sign up for our newsletter.
And yes, it really is monthly. Ok, maybe the occasional twice a month, but for sure not like one of those daily ones that you just tune out after a while.
Get started with the only application monitoring platform that empowers developers to fix application problems without compromising on velocity.
