Topics / Building software

Can AI fix bugs and handle incidents?

AI that triages and fixes bugs, responds to incidents, or takes on-call work.

13 passages from 10 organizations; 13 checked against the source. The page states no conclusion: these are the organizations' own words.

Testo, in the last 30 days, caught 425 bugs.

Geoff CharlesChief Product Officer (CPO) · Executive, Ramp

Talk: What product looks like when coding is solved | Geoff Charles (Ramp CPO), Lenny's Podcast (YouTube channel); Geoff Charles's talk at the Lenny and Friends Summit, recorded 2026-09-10, September 25, 2026.

  • 425 function agent volume, past 30 days, as of 2026-09-25. Level not stated

Checked against the source [ Grade B ] Said in the last year Ramp: $1.5 billion revenue, annualized revenue (ARR), by early June 2026 Passage page

a growing share of sessions aren’t initiated by humans, but by automated managed agents handling code review, self-healing CI failures, completing E2E PRs with visual validation, triaging on-call alerts, debugging incoming bugs, and handling a variety of code maintenance tasks with human reviews/escalations.

Uday Kiran MedisettyDistinguished Engineer · Practitioner, Uber

Post: Running a Software Factory Efficiently at Uber Scale, Uber engineering blog, August 27, 2026.

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

What we did was we built a system that actually has agents constantly running and creating BAML programs. … We then look at the entire … transcripts, see what tools they use, see what happened, and obviously we as humans can inspect them. But more importantly, we can have agents go inspect them. And agents find what was good, what was bad. … And we can have humans collaborate with these issues to figure out which ones are real, which ones are hallucinations, which ones don't have taste as much as I hate to use that word. And then we can have agents go ahead and create fixes to these problems and go to address them.

Vaibhav GuptaCo-founder and Chief Executive · Executive, Boundary (BoundaryML)

Context. Gupta is describing how the team tests its programming language when it does not rely on reading every line of code.

Talk: Fighting Slop with Slop, AI Engineer (YouTube), July 31, 2026, at 5:05.

Checked against the source [ Grade B ] Said in the last year Sells AI tools Passage page

The SRE use case, internally we think about it as auto triage Because we just want every message that comes in, and that’s an alert, that’s a bug report, to have Devin just start triaging it before anything else. And we’ve leaned into this use case so much though that we’ve basically tried to make it so that you don’t ever have to leave Slack to interact with this.

Walden YanCo-founder and Chief Product Officer · Executive, Cognition

Podcast: The Age of Async Agents: Cognition's Walden Yan and OpenInspect's Cole Murray, Latent Space, May 28, 2026, at 01:03:24. Reported by Swyx.

Checked against the source [ Grade C ] Said in the last year Sells AI tools Passage page

Over roughly six weeks, we’ve run thousands of scans, produced over 300 findings ranging from defense-in-depth improvements to resolved security incidents.

Zack DeveauTitle not stated on Deveau's author page; the post is written from Shopify's Application Security team · Practitioner, Shopify

Post: Building an agentic harness that outlasts the model, Shopify engineering blog, July 29, 2026.

  • 300 function agent volume, about six weeks, as of 2026-07-29. Level not stated

Checked against the source [ Grade B ] Said in the last year Shopify: $11.6 billion revenue, FY2025 Passage page

Early data shows that 70% of all our in house background agents, tasks which is Minions are toil.

Abhishek TibrewalSenior Data Scientist, Platform Engineering · Practitioner, Uber

Social post: Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual, Engineering Enablement podcast by DX (DX sells developer-productivity measurement software); recording of Uber's talk at DX Annual, June 22, 2026.

Checked against the source [ Grade B ] Said in the last year Uber: $52 billion revenue, FY2025 Passage page

We are building an agent that "handholds" a change all the way to production — whether it's a code change or a change behind a feature flag. It observes the relevant monitoring graphs, but can also build its own dashboard to monitor important signals. More of our code changes are going to production with this kind of agent monitoring.

Venkat VenkataramaniVP of Engineering, Applied Infra · Leader, OpenAI

Press report: Inside OpenAI's agentic software factory, The Pragmatic Engineer, September 15, 2026, at 2. Death of the IDE & pull requests. Reported by Gergely Orosz.

Checked against the source [ Grade C ] Said in the last year OpenAI: $20 billion revenue, ARR, 2025 Sells AI tools Passage page

JSON: /api/v1/topics/bugs-and-incidents.json