Harness Engineering: Code and Data That Agents Can Trust

Agents don't fail because they're dumb. They fail because the codebase or data they operate on wasn't built for them.

This meetup features two talks on the emerging discipline of harness engineering: what it takes to structure your code and your data so that agents can act reliably and autonomously.

Dru Knox opens with harness engineering as a core skill for agentic developers, the loop, the common codebase modifications, and how to scale the work. Will Martin follows with the data side: what a well-engineered data harness looks like, how the semantic layer functions as the data equivalent of a well-instrumented codebase, and why query acceleration and open lakehouse architecture matter for agents that need fast, trustworthy results.

Agenda

18:00 Venue opens

18:30 Talk 1: Harness Engineering: The New Core Skill for Agentic Developers by Dru Knox

19:00 Talk 2: Belay On: Building Data That Harness Engineers Can Trust by Will Martin

19:30 Networking

20:30 THE END

Harness Engineering: The New Core Skill for Agentic Developers

Harness engineering is emerging as a new core competency for agentic engineers. Your job isn't writing good code, it's upgrading your codebase so that agents reliably succeed.

This talk covers the core loop of harness engineering, the most common codebase modifications you'll make, and how to 10x your harness engineering efforts with Tessl's harness engineering agent.

Dru Knox, Head of Product & Design at Tessl

Dru Knox is Head of Product & Design at Tessl, where he leads the development of AI-native tools purpose-built for developers. A seasoned product manager, Dru has spent his career working on deeply technical and developer-facing products at companies like Google and Airtable. Over the past several years, he’s focused on machine learning and generative AI at scale, driving product innovation at Grammarly, his own startup, and the AI-native social network Cantina. Dru is passionate about making LLM-powered products that are fast, useful, and intuitive, especially in the codegen space. He brings a thoughtful, pragmatic approach to building tools that serve real developer needs, grounded in experience across both big tech and startups. Outside of work, Dru’s interests include improv comedy, Dungeons & Dragons, and philosophy. His favorite podcasts are Cortex, The Adventure Zone, and Sharp Tech. Originally from Virginia, he’s currently based in London and still counts winter (and snow) as his favorite season.

Belay On: Building Data That Harness Engineers Can Trust

Harness engineering aims to build the context, structure, and tooling that lets agents succeed autonomously. Just as acritical to your agents success is your data foundation. Agents that query your data will fail in the same predictable ways that agents fail on undocumented codebases: ambiguous schemas, inconsistent metric definitions, no clear entry points, and nothing to tell the agent what's trustworthy and what isn't.

This talk covers what a well-engineered data