Skip to main content

​
The Thesis

Knowledge + structured execution > model
Agent reliability improves more from giving agents the right knowledge and constraining their execution than from switching to a larger model.

​
What This Means

​
Knowledge

Not “more data” — curated, structured domain knowledge delivered to the agent at the right time:
  • Which testing patterns work for this framework
  • What dependencies are available and how to use them
  • What the project conventions are
  • What common failure modes look like

​
Structured Execution

Not “better prompts” — infrastructure that shapes agent behavior:
  • Deterministic preprocessing before the LLM acts
  • Tool configuration that guides tool selection
  • Execution loops with built-in checkpoints
  • Judge feedback that catches failures early

​
> Model

This doesn’t mean models don’t matter. It means that for a given model, you get more reliability improvement from knowledge and execution infrastructure than from upgrading to the next model tier.

​
Evidence

​
Code Coverage v1

The first experiment showed two independent axes of improvement — knowledge injection and prompt hardening — both of which operate on infrastructure, not model choice. The PetClinic “model floor” (92-94% coverage regardless of variant) demonstrates that the model’s prior knowledge creates a ceiling that only infrastructure can differentiate.

​
SkillsBench (External)

SkillsBench (Feb 2026) found that 2-3 curated skills improve agent performance by +16.2 percentage points on average. Comprehensive skills actually decrease performance by -2.9pp. This validates “curated > comprehensive” — structure matters.

​
Stripe Convergence

Stripe’s Minions paper independently arrived at similar conclusions: “the walls matter more than the model.” Their multi-agent system improves reliability through structured task decomposition, not model upgrades.

​
The Equation

Current industry focus is almost entirely on Model Capability. This lab focuses on the first two terms, where the marginal returns are higher.

​
Naming History

This concept has gone through several names: See journal/2026-03-02-naming-the-thesis.md for the full naming discussion.

​
How to Apply

If you’re building agent systems:
  1. Start with knowledge — What does your agent need to know that it doesn’t?
  2. Structure the delivery — Skills > flat files > nothing
  3. Add execution constraints — Deterministic preprocessing, judge feedback loops
  4. Then consider the model — Upgrade only after infrastructure is solid