Name: Detecting malicious pull requests at scale with LLMs
Start: 2026-05-27T11:15:00+0200
End: 2026-05-27T11:45:00+0200

Detecting malicious pull requests at scale with LLMs

FULL

Wednesday May 27, 2026 11:15 - 11:45 CEST

👾 DEV/TECH ARENA

Limited Capacity full
Adding this to your schedule will put you on the waitlist.

As AI coding assistants accelerate software development, the volume of pull requests at Datadog has grown to nearly 10,000 per week, increasing the risk that malicious changes slip through due to review fatigue. To address this, Datadog built BewAIre, an LLM-powered code review system designed to identify malicious source code changes introduced by threat actors. By reducing approval fatigue for developers while increasing friction for attackers, BewAIre guides human reviewers to the areas where judgment matters most, without slowing developer velocity.

In this presentation, I will share why BewAIre was built, how it evolved from a hackathon experiment into a production-grade internal system, and the key architectural decisions and trade-offs involved along the way. I will discuss what worked, what didn’t, and the limitations we encountered when applying LLMs to security-critical workflows.

Speakers

Julien Doutre

DATADOG

Software engineer at Datadog, focusing on securing the Software Development Lifecycle thanks to container images signing and supply chain attacks detection with AI.

Wednesday May 27, 2026 11:15 - 11:45 CEST
👾 DEV/TECH ARENA 135 Rue Sadi Carnot, Ronchin, France

Dev / Tech, Talk

Audience Intermediate

Attendees (60)

View All →

Success you have shared X tickets.

Dev Summit 2026

Julien Doutre

Attendees (60)

Waitlist (21)

Get help with the event

Success you have shared X tickets.

Dev Summit 2026

Julien Doutre

Attendees (60)

Waitlist (21)

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Get help with the event