Hi,i'm viv:)

ai research & engineering

Hey there, I'm Viv! I'm having fun working on autonomous agents, harnesses, and evals.

I'm currently at LangChain where I get to lead our work on open source agents & harnesses with our amazing team. Previously, I worked on my own startup on building agents for visual understanding and before that was a scientist at AWS while I did my PhD in CS at Temple University.

More about me or get in touch below.

Recent Posts

• The Anatomy of an Agent Harness

  10 Mar, 2026

  Agent = Model + Harness. We define what a harness is and derive the core components today's and tomorrow's agents need by working backwards from desired agent behavior.

• Improving Deep Agents with Harness Engineering

  17 Feb, 2026

  Our coding agent went from Top 30 to Top 5 on Terminal Bench 2.0. We only changed the harness. Here's our approach to harness engineering.

• Agents Should Be More Opinionated

  25 Nov, 2025

  The best agent products aren't the most flexible, they're the most opinionated. Learn why agents need fewer knobs, not more, and how to design around model intelligence spikes.

• The Modern Planning Agent is Really a Dynamic, Adaptive Workflow Generator

  24 Oct, 2025

  Understanding how modern planning agents work as just-in-time, adaptive workflow generators and their role as universal bridge nodes in workflow builders.

• The Claude Code SDK and the Birth of HaaS (Harness as a Service)

  23 Sep, 2025

  As tasks require more autonomous behavior, we're seeing a shift from LLM APIs to Harness APIs. Explore how Claude Code's SDK enables rapid agent development through HaaS (Harness as a Service).

• Welcome to My Blog

  6 Aug, 2025

  Quick intro to what I'll be sharing here.