LogicStar AI

Most engineering teams don't have an observability problem. They have a triage problem. Logicstar is building the filter layer.

@HarukiKuroda_ Yes. Engineers shouldn't be triaging noise. Logicstar ranks bugs by production and business impact, so the time goes where it counts.

@logic_star_ai これは、エンジニアの時間を最適に使うためのツールだね

LogicStar connects production signals, code, and business impact to prioritize what deserves engineering attention.

Did we just blow our entire marketing budget on this sign at AI Council? 🤔 Come find our CTO @mnmueller in SF this week to hear what we're building at LogicStar. And to confirm whether we have any runway left.

8/8📄 Paper: arxiv.org/pdf/2602.11988 💻 Code: github.com/eth-sri/agentb… Would love to hear how this lines up with what you're seeing in your own agent setups.

7/8 Joint work with @ThibaudGloaguen, @nielsmuendler, @VeselinRaychev, and @mvechev at the @the_sri_lab @ETH_en and @LogicStarAI.

1/8 Our paper "Evaluating AGENTS.md" just won Runner-Up Best Paper at the ICLR MemAgents workshop 🏅 We asked a simple question: do context files actually help coding agents? Two findings. Both unflattering. 🧵

Everyone's measuring AI coding ROI wrong. The pitch: AI assistants make engineers 10x faster. The reality at every Series A/B team I've talked to: PR volume up 3-5x Review quality down Bug backlog quietly compounding On-call rotations getting heavier, not lighter Senior engineers spending 30%+ of their week on triage and root-cause work that used to take 5% The bottleneck moved. Writing code stopped being the hard part. Owning code after it ships became the hard part. The "second half" of software engineering (reproduce, root-cause, fix, verify) is still 100% human. That's the gap. It's also what we're building Logicstar for: an autonomous agent that takes a bug report and ships a verified PR. No human in the loop until review. self serve is open now.

@DavidKandler Same pattern in eng tooling. Teams don't lack fix velocity, they lack a ranked list of what to fix. Upstream triage is the whole game.

The most valuable AI skill in 2026 isn't prompting. It's knowing which problems are actually worth solving. The bottleneck moved upstream. Most people haven't noticed.

@DavidKandler Collection is a solved problem. Triage isn't.

Something I’ve heard consistently from 60+ eng leads at 40–100-person companies: even with mature observability stacks, the volume of actionable alerts hasn’t dropped. On-call still breaks at ~50 engineers not because of raw count, but because nothing filters what actually matters.

Exciting research in collaboration with SRI of ETH Zurich

Stop fixing bugs. Let AI Agents fix them for you. Join us for a session on Autonomous Software Systems and learn how AI agents are using telemetry data to detect, diagnose, and fix production bugs without human intervention. meetup.com/localstack-com…

Great dinner with @lovable, @localstack, and @logic_star_ai AI (three “Lo*”s) in Zurich - discussing the future of agentic coding 🤖, cloud DevX 💻, and building delightful apps ✨. Can't wait for more collaborations and partnerships among the three “Lo*”s and beyond! 🚀

🚨 AI agents wrote 7% of all GitHub PRs in June. But can we trust their code? We built Agents in the Wild – a live dashboard tracking autonomous AI agents across GitHub to answer that question: insights.logicstar.ai Here’s what we learned from analyzing 10M+ PRs 👇 1/n 🧵

We are excited to see the community use our SWT-Bench and work on the crucial topic of test generation!

SOTA code agent OpenHands (top-1 for SWE-full) achieves only 22% accuracy in unit test generation on SWT-lite (half its SWE performance), only slightly outperforming SWE-agent. What is going on? We dug through the data to find a simple trick and achieve almost 30%! 👇🧵 1/9