Post

Thorin

@tmtabor.io

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

Thorin

@tmtabor.io

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

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

Thorin

@tmtabor.io

So what does that mean in practice? #SystemDesign

Thorin

@tmtabor.io

Clean execution environments matter more than people think. Agents need isolated, deterministic contexts to behave reliably. Leftover state, dirty environments, unexpected side effects: these silently corrupt agent behavior in ways that are hard to trace. #Backend

Thorin

@tmtabor.io

Tool design shapes model behavior. Tools aren't neutral scaffolding. The schema, the naming, the error responses: all of it actively steers what the model does. A poorly designed tool will degrade even a strong model. #PromptEngineering

Thorin

@tmtabor.io

Don't underestimate state management. Most agent failures aren't model failures. They're state coherence failures. The harness controls what the model sees and when, and that decision matters. #SoftwareArchitecture