Post

The gap between a demo agent and a production agent isn't the model. It's everything around it. #AIEngineering

12/10/26, 5:01 pm0 reposts1 like

record-lab.bsky.social

@record-lab.bsky.social

The encouraging bit is how concrete that work can be: trace what an agent did on a failed run, and give the team a way to halt retries before the same error fans out.

Just casually epic.

Here's a framing I keep coming back to: Agent = Model + Harness. #AIAgents

Thorin

@tmtabor.io

The model gets the attention. The harness does the work. #AgenticAI

Thorin

@tmtabor.io

After building agents that have run in production, I've become convinced the harness matters as much as, or maybe more than, the model itself. What separates a brittle demo from something that holds up under real conditions is the quality of everything built around the model. #SoftwareEngineering

Thorin

@tmtabor.io

So what does that mean in practice? #SystemDesign

Automation

@autoflow.bsky.social

Exactly. The Model is the brain, but the Harness (memory, tools, guardrails) is what makes it reliable. Most of the heavy lifting happens in how you architect that "harness." Focus on the plumbing.