Request an evaluation(opens in a new tab)
Request an evaluation(opens in a new tab)

About us

Meet The LogicStar Team

AI made writing code faster. Agentic engineering is changing how the entire software development process works. Software factories are the next step, with agents doing more of the work and engineers setting the direction.

We already see what's possible. At our customers using advanced AI code review, we find that on 78% to 93% of PRs, human review appears not to change production outcomes. The potential is real, but so are the blind spots.

At LogicStar, we work shoulder to shoulder with engineering teams to find what agents can reliably do today, improve what they miss, and push toward greater autonomy. Every step measured against real engineering outcomes.

Principles

What We Believe

AI in engineering pays off when you can prove it on your own code. That proof shapes how we work.

  1. Reality is the grader

    Ground truth comes from your repositories, engineers and production outcomes, not from opinions or an LLM grading its own work.

  2. Start small

    One workflow on one real repo first. More only when the numbers hold.

  3. Find the failure modes

    Measure what agents catch, what they miss and what your engineers still add. Then fix what fails.

  4. Measure every change

    New model, prompt or tool? Measure it against the same history before it reaches everyone.

  5. Autonomy is earned

    Reduce human review where the evidence says it is safe. Keep people in the loop where they still add value.

Story

Why We Built LogicStar

The LogicStar team

LogicStar was founded in 2024 by engineers and researchers from DeepCode, Snyk, ETH Zurich and INSAIT. We have spent years working on code analysis, AI for software engineering and coding agents.

That work exposed a new problem. Agents can now write and review meaningful amounts of code, but teams still struggle to answer basic questions with data. How good is this agent on our code? What does it miss? What do humans still catch? Did the latest model, prompt or tool actually make it better?

So we work hands-on with engineering teams: we build, monitor and improve their agentic workflows, from code review to a software factory, and measure each one on their repository history, their engineers’ decisions and what happens in production.

Founders

Built by people who have done this before

  • Mark Müller

    Mark Müller on LinkedIn (opens in a new tab)

    Co-Founder and CTO

    PhD from ETH Zurich in code analysis for neural networks. 30+ research papers, 1300+ citations, with industrial work at Porsche, Mercedes, and Airbus.

  • Martin Vechev

    Martin Vechev on LinkedIn (opens in a new tab)

    Co-Founder and Advisor

    Martin is a full professor at ETH Zurich and one of Europe’s leading AI researchers, with 200+ publications in AI, networking, programming paradigms and others. He has co-founded five deep tech startups (including two exits) and launched INSAIT, raising over $280M to drive AI innovation.

Team

Research

Research measured on real software

Our research covers repository-level coding tasks, real bug fixes, testing, security and refactoring. We bring the same discipline to your engineering: measure agents on the software they actually work on, find the gaps, and test every change against the same tasks.

  • The founders of LogicStar
  • The LogicStar team working together
  • The LogicStar team at a holiday gathering at INSAIT headquarters
  • LogicStar engineers working together

We’re not just following the AI revolution.We’ve helped lead it.

Transform your SDLC with agentsFrom copilots to a self-driving SDLC

With the team behind the first AI for code.

Backed by frontier coding agent research with ETH Zurich.

Request an evaluation(opens in a new tab)