---
id: "contrarian-disable-model-skills"
type: "contrarian-insight"
source_timestamps: ["00:17:04", "00:20:02"]
tags: ["prompt-engineering", "control"]
related: ["concept-procedural-vs-ability-skills", "claim-procedural-over-abilities", "action-blank-slate-agents"]
speakers: ["Matt Pocock"]
---
# Disable Model Autonomy for Better Results

## Prevailing narrative

Give the AI agent maximum autonomy. Let it decide when to invoke tools, what skills to use, and how to orchestrate its own workflow.

## Pocock's challenge

**Explicitly disable model invocation** for certain skills, forcing human-triggered, procedural workflows. See [[concept-procedural-vs-ability-skills]], [[claim-procedural-over-abilities]], and the operational directive [[action-blank-slate-agents]].

## Where autonomy still wins

High-volume, low-risk environments (internal tools, batch pipelines, exploratory prototyping). Frameworks like AutoGen, LangGraph, and ReAct-style planners show autonomous tool-use can be productive when properly constrained.