AI Native Dev Boston: Inside the Dark Factory

AI is reshaping how software gets built, and the fastest way to keep up is a room full of people working it out in practice. For this Boston edition, the AI Native Dev community has teamed up with the AISecEng Community to bring together the people building with coding agents and the people making sure that's done safely. Expect an evening of talks on both sides of that coin, from architecting a self-optimizing development pipeline to putting agents to work fixing security bugs. Whether you're already shipping with coding agents or just starting to fold them into your workflow, you'll leave with ideas you can put to work and new people to compare notes with.

Huge thanks to Snyk for hosting us!

Agenda

• 6:00pm Venue opens

• 6:30pm Talk 1: Building Your Dark Factory: Engineering the Future of AI-Powered Development by Sahil Deshmukh

• 7:00pm Talk 2: Remediation Agents Demystified: Your AI Teammate for Fixing Security Bugs by Brendan Hann & Ryan McMorrow

• 7:30pm Talk 3: The Verification Layer for the Dark Factory: How Coding Agents Earn Trust by Max Binshtok

• 8:00pm Networking

• 8:30pm THE END

Building Your Dark Factory: Engineering the Future of AI-Powered Development

Harness engineering is emerging as a new core competency for agentic engineers. Discover how Tessl is architecting a self-optimizing development pipeline, and what it means for engineering teams everywhere.

Sahil Deshmukh, Member of Technical Staff at Tessl

Hi My name is Sahil. I'm currently baby sitting coding agents at Tessl.I was previously building things to move a bunch of data around at MongoDB.I love solving meaningful problems, especially through software. It’s what keeps me busy and curious. I take every opportunity I can get to learn from all the wonderfully smart and talented people around me. I’m also doing my best to share all the cool things I’m learning, although I definitely need to get better at this!

Remediation Agents Demystified: Your AI Teammate for Fixing Security Bugs

Mythos made it clear - finding vulnerabilities is easy. Fixing them? That's where the real work begins.
Enter agentic remediation—the next evolution of AI in software development. But what exactly is it? Is it just another coding assistant, or can it actually understand security findings, generate trustworthy fixes, and help developers stay ahead of attackers?
Join us for a fun talk where we'll unpack everything you need to know about remediating with agents. We'll explore why throwing the latest model at a backlog fails and talk about a different approach; how it works under the hood, why it’s quickly becoming an essential part of the secure development workflow, where agentic remediation shines, where it still struggles, and what the future of fully autonomous remediation looks like.
Of course, theory is better with a demo, so we'll also take a look at Snyk Remediation Agent as a real-world example. You'll see how it tackles security findings, generates merge-ready fixes, and fits into a developer's day-to-day workflow

Brendan Hann - Senior Product Marketing Manager, Snyk
Brendan Hann is a Senior Product Marketing Manager at Snyk, focused on the developer experience and core analysis engines. He's also the lead for our newest community chapter opening in Boston

Ryan McMorrow - Staff Product Manager, Snyk
Ryan is a Staff Product Manager at Snyk, driving the product vision and strategy for remediation. He focuses on empowering customers to strengthen application security through both proactive and reactive fixes across Snyk's product offerings

The Verification Layer for the Dark Factory: How Coding Agents Earn Trust

Agentic development pipelines can plan, generate, test, and open pull requests faster than human teams can inspect every line. The dangerous shortcut is allowing the same system that produced a change to certify it. In this session, we'll break down a practical verification layer for agentic development: codebase context before execution, independent code review, and inspectable evidence at the pull-request boundary. Using a concrete agent-to-PR workflow, we'll see what can be automated, what should be challenged independently, and where human judgment still needs to re-enter the system.

Max Binshtok, Forward-Deployed Engineer at Qodo.

Max Binshtok is a Forward-Deployed Engineer at Qodo. He works alongside engineering teams bringing AI-assisted development into real codebases and delivery workflows, with a focus on code quality, review, and trustworthy adoption of coding agents!

This event is brought to you as part of the AI Native Dev Community. Consider subscribing to the Mailing List, Podcast, and joining our Discord Community