What AI efforts failed or were rolled back?

“We built an automated AI code review GitHub Action in a single day, and we reverted it before the day was over. The idea was simple: someone comments a trigger phrase on a pull request, and a workflow runs our deepest review and posts the result. It took seven small pull requests to get that far, and one revert pull request to undo them.”

TradersPostPublished by the organization itself (post), no named author

“Nobody wrote a postmortem. We did not collect a table of review comments the bot produced, measure their precision, or compare cost against the existing session-based review. So we cannot tell you the bot failed because of noise, or cost, or authentication friction, or a change of mind about where review should live.”

TradersPostPublished by the organization itself (post), no named author

“Our first approach used a high-level orchestrator agent for this role. It worked, but it was expensive, slow, and sometimes unreliable. … We learned that although an LLM can orchestrate a workflow, predictable coordination is better implemented in code.”

StripePublished by the organization itself (post), no named author

“An agent that has silently lost its tools does not report that it lost its tools. It answers anyway, with the same fluency as before.”

Arthur VinbergHead of DevOps & IT · Leader, Ionix

“But the real problem with all of this is I built this and I hit a little bit of AI psychosis. And I started shipping 10 design docs a day. And soon, the team was fighting my slop. … This last rule was … ship a design doc, you require people to actually go read it. And with this last standard, we suddenly had design docs … incredibly high quality.”

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

“And every morning, we walk into the office to a small incremental PR that's low risk. And when we first did this, it was actually really frustrating, and we turned the loop off … because we had to constantly update the skill, we had to constantly check out the branch, change the skill, change the code, commit and push, and our loop was actually really high friction, right?”

Kyle MisteleCo-founder, HumanLayer · Executive, HumanLayer

“Locking also caused too much contention. 20 agents would slow to the throughput of 1-3 with most time spent waiting on locks.”

Wilson LinResearcher, Cursor (author of the Towards self-driving codebases post) · Practitioner, Cursor (Anysphere)

“I think we found that the state-of-the-art in December was you can probably, run this for about two weeks. By the end of those two weeks, you’d find that, hey, you want to, change the color of a button. Well, it turns out this button is implemented in, 10 different places, and they, have All these different variations, and oh, you forgot one of them, and actually it’s a slightly different color in one spot.”

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

“We need to rethink this and make customer service a human experience. Everyone who wants a human connection should get it.”

Sebastian SiemiatkowskiChief Executive Officer and co-founder · Executive, Klarna

“The time went into three plumbing problems: what the action accepts as inputs, which permissions the job needs, and how the job authenticates to the model provider.”

TradersPostPublished by the organization itself (post), no named author