Building AI Products at @Sentry
San Francisco, CA
- Tweets 893
- Following 351
- Followers 301
- Likes 3,559
Had a real wow moment with Seer today.
Because we send traces from our MCP server to @sentry , I could ask where users were running into capability gaps and get a quantified breakdown.
This is why you should send traces
1
8
1,465
Dhrumil retweeted
I am here once again to say “put up or shut up”
One million to open source this year, as we continue to give back to the ecosystem via the pledge.
More than half has gone directly to your favorite open source developers.
blog.sentry.io/another-year-…
35
47
426
37,989
Dhrumil retweeted
I’ve moved my personal projects to Origin only (no mirror) as I am a bit of a Cursor maximalist at home.
I annoyed @brungarc to chase this integration. Wanted to “move like Cursor”: be first and iterate. Stoked that we can be there with Origin on app marketplace launch day.
Origin, Cursor’s code hosting platform, now supports over 20 integrations.
Connect your repos to tools for CI, deployments, code review, security, monitoring, and project management.
1
6
208
Agent traces can get too long - they have several turns and tool calls and it's tough to easily pinpoint problems when you get a complaint
With Seer+Agent Tracing @sentry, it's as simple as this OOTB
1
1
8
1,125
Seer Agent doesn't just answer questions about your production app, it finishes the work too 🧠
Ask it in Slack or in Sentry what broke, why, and what changed in the last release. Then tell it to act on the answer.
Watch the walkthrough and give it a try today 👇
2
2
11
1,038
When you launch anything, have your agent install and configure @Sentry.
Sentry reports frontend bugs and backend errors your users hit. You can then keep an agent watching those reports in a loop and fixing them as they come in, including while you sleep.
The free account should get you a long way toward a stable app.
4
262
Dhrumil retweeted
3/ Alert Responder
A @Sentry alert fires a webhook. Droid finds the root cause, comments on the issue, and opens a fix PR.
1
2
19
1,656
Don't ever setup an alert in Sentry yourself - you can just Ask Seer
Also - you really don't need to bother querying telemetry either - It's likely that Seer will do it faster and better
Seer Agent just got a lot more powerful 💡
Now you can have the agent manage more of your Sentry projects and integrate third-party data sources, like Datadog and GCP, to help you better diagnose issues.
Learn more in the full blog post: blog.sentry.io/big-improveme…
1
1
6
772
Dhrumil retweeted
We’re also hiring engineers to help build our eval platform and enable every product team at Sentry to ship AI features with confidence: sentry.io/careers/95d2eeab-2…
We’re investing heavily in evals at @sentry. It’s early but we’re seeing a culture change from shipping vibes to shipping with clear data using our evals platform.
Will share more in a future blog post, but some stats from our devs in the past month:
- ~1800 eval runs triggered directly on PRs
- 1500 eval scenarios ran across 17 AI surfaces in our product
- Cost/token reductions of ~20-50% across a few of our surfaces
- Eval passing improvements of ~10-20% from some core “code mode” changes launching soon (shoutout @grichadev)
All this from essentially 0 back when we started this effort in May.
1
1
8
4,223
.@sentry is a great tool to monitor the health of your products. But I don't remember the last time I've actually opened the website.
I just have sentry cli installed, and every morning an agent reads through the issues and flags P1s and P0s for me.
1
2
10
2,586
💯 You will encounter ppl that consider themselves to be "high agency" and think that's license to be dismissive or a jerk vs actually making things net positive
> get introduced to someone new
> being told that they are high agency
> ask if they mean breaking the rules and soiling the commons or figure out a way to push the pareto and create positive sum
> she doesn't understand: "they're high agency sir"
> meet the person
> they're soiling the commons and externalizing internalities
4
254
Agent Plugin @sentry + Sending traces/logs/errors =
Coding Agents get limitless debuggability
3
1
9
707
I’ve also seen counts and rates sent as Errors. I have screamed a little inside
Send those as application metrics. Every plan includes 5 GB of metrics per month too and we don't charge for cardinality so add that user_id without worries
1
5
1,339
And be picky with captureException().
If a third-party API returns an expected, handled 401, track how often it happens as a metric. Keep it as an Error when it breaks a user flow or needs someone to fix it. Your Issues list will thank you.
1
2
577
Want help cleaning this up?
Use the Agent plugin and ask your coding agent to audit your Sentry calls and move routine signals to logs or metrics + build dashboards, while keeping real bugs as Issues.
docs.sentry.io/ai/agent-plug…
7
534
🚨 Want to send fewer noisy errors to @sentry ?
After talking to hundreds of customers, I keep seeing logs, counters, and expected 401s sent as Errors. Put those signals in the right place and, hey, you might save some $$ too. 🧵
6
5
54
12,583
Spend your time ensuring your agents don’t write crap code
Don’t waste it to query data or debug stuff - agents like Seer are good at it
Everyone keeps asking "how do we actually use Seer?"
Cool. We'll just show you.
Introducing #SeerChats ➡️ real, unfiltered convos between us and our own agent, straight from the Sentry trenches. No cherry-picked demos, no marketing gloss. Just Seer doing what it does (and sometimes what it doesn't) so you can see how it actually solves problems, before you throw your own bugs at it 🫡
In this #SeerChat: docs LCP p95 was spiking, so we asked Seer to find out why.
It compared spike vs. calm traces, found the typical user was hit (not just outliers), and traced it to slow RSC responses stacking with heavy JS work during soft navigations — then handed back a prioritized fix.
4
268