Harness engineering doesn't mean building your own harness

In a recent Agent Factory podcast episode, host and guests discussed "harness engineering" for coding agents, with engineer Ryan Lopopolo, who coined the term "agentic harness," explaining how to sculpt smaller feedback loops into long-horizon agentic workflows. Billy Jacobson walked through a simple harness implementation covering linear and closed-loop styles, while Smitha Kolan demonstrated configuring memory, tools, and guardrails using Gemini 3.8 Flash, Antigravity Boost, and the Google Skills GitHub repo. The episode's central takeaway was that many best practices for scaling software engineering teams also apply to coding agents.

It means giving the agent enough context to do the right thing For this week's Agent Factory podcast, I interviewed Ryan Lopopolo https://www.linkedin.com/in/ryanlopopolo/ , the engineer who coined the term "agentic harness." What's in the video - How to Stop Writing Code Manually: Ryan explains how to sculpt smaller feedback loops into long-horizon agentic workflows via harness engineering - Harness, Deconstructed: Billy Jacobson https://www.linkedin.com/in/billyjacobson/ delivers a code walkthrough of a simple harness, exploring linear and closed-loop styles. - The Three-Layer Stack: Smitha Kolan https://www.linkedin.com/in/smithakolan/ breaks down how to use Gemini 3.8 Flash https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/ , Antigravity Boost https://antigravity.google/docs/boost/ , and the Google Skills GitHub repo https://github.com/google/skills to configure memory, tools, and guardrails. The thing that struck me was how many best practices for scaling software engineering teams also apply to coding agents. How much code are you writing manually these days? Let me know in the comments