Kiriti Badam

Kiriti Badam is co-founder and CTO at LevelUp Labs, where he helps companies turn AI into business results through engineering, strategy, and education. He has 12+ years of experience building production systems, from distributed infrastructure to machine learning platforms and AI products. Previously, he worked on the core Codex team at OpenAI across product development, agent behavior and reliability, and production infrastructure. Examples include the Codex Web launch, Slack integration, Code Review, and GPU capacity and fleet management. He co-created ChatGPT Sites and co-led its development and launch. Before OpenAI, he was a founding ML infrastructure engineer at Kumo.AI, where he helped build a multi-tenant platform training hundreds of models each day. Earlier, he built large-scale storage and data-processing infrastructure at Google, Databricks, and Samsung. He also writes and teaches practical courses on production AI systems, agent design, evaluation, and harness engineering.

LevelUp Labs, USAkiriti.dev kiriti-badam sai-kiriti-badam

From Issue to Verified PR: Sizing the Harness for Coding Agents

AI Coding Summit NYC

Upcoming

From Issue to Verified PR: Sizing the Harness for Coding Agents

Getting a coding agent to produce a diff is easy. Deciding when that diff deserves a pull request is the engineering problem.

This talk follows one issue through a real coding-agent workflow. We inspect the trace at the first meaningful divergence, then add only the controls that the observed failure justifies: agent-legible context, a checkable completion contract, independent verification, and action boundaries. The comparison becomes a practical framework for sizing the harness to the task: when instructions and tests are enough, when a separate evaluator or sandbox earns its cost, and when a human checkpoint should remain. Attendees will leave with a repeatable method for turning agent failures into systematic improvements instead of longer prompts and more manual review.

best practices