Advanced Analytica Advanced Analytica: IBOM
BACK
Deterministic code is the secret to smaller models — Smaller models become far more capable when code handles the parts of the workflow that should never be guessed.

Deterministic code is the secret to smaller models

Jonny Bowker
Share

Smaller models become far more capable when code handles the parts of the workflow that should never be guessed.

Deterministic Code Is the Secret to Smaller Models

Smaller models should not be asked to do work that code can do better.

That sounds obvious, but it is one of the most common mistakes in AI system design. Teams ask a model to route, validate, format, calculate, retrieve, score, approve, remember, and explain, all inside the same prompt. Then they blame the model when the result is inconsistent.

A better architecture separates judgement from machinery.

The model handles the language problem. Deterministic code handles the operational contract.

What code should own

In a governed agentic workflow, many steps should be predictable by design:

  • input validation
  • permission checks
  • data retrieval
  • formatting
  • routing
  • thresholds
  • audit logging
  • version control
  • escalation triggers
  • repeatable calculations

None of these should rely on a model’s mood, context window, or interpretation of a vague instruction. They should be built into the system.

That makes the model’s job smaller and clearer.

Why this helps smaller models

A smaller model has less general capacity than a frontier model. That is exactly why it needs a well-built operating environment.

If the surrounding code supplies the right context, constrains the available actions, validates the output, and routes exceptions to a human or larger model, the smaller model can concentrate on a narrower reasoning task.

This is how smaller systems become useful in production. They are not winning by being broadly smarter. They are winning because the architecture stops asking them to solve everything at once.

The adapter plus code pattern

Jonny’s model upskilling idea is not just “train a small model.” It is closer to:

  1. Use a capable model to teach the reasoning pattern.
  2. Capture the pattern in specifications, examples, and tests.
  3. Train or tune adapters for the repeatable judgement task.
  4. Wrap the smaller model in deterministic code.
  5. Route uncertainty, exceptions, and high-risk decisions appropriately.

The smaller model then becomes part of a system rather than the whole system.

That is the key distinction. Production AI is not a model. Production AI is an operating design.

The governance point

Deterministic code also makes governance easier. It creates clear places to enforce policy, log decisions, test conformance, and prove that the system did what it was supposed to do.

For regulated, client-facing, or high-volume work, that matters as much as output quality.

Smaller models do not punch above their weight alone. They do it when the system around them carries the weight they should never have been asked to carry.

Further context

This post supports Jonny Bowker’s work on upskilling AI and the wider spec-driven AI methodology.

Start The Conversation

Turn this perspective into a practical agentic AI plan.

This opinion sets out a practical issue for organisations putting AI into real workflows. The useful next step is to locate where that issue appears in your business, define the rules and judgement agents need to apply, and decide what should be tested before the work moves into production.

We turn that into a clear path from strategic intent to governed agentic AI that can operate reliably.

“Smaller models become far more capable when code handles the parts of the workflow that should never be guessed.”
Jonny Bowker
Teaching Smaller Models

Related Posts

View All
Advanced Analytica

Most businesses are sitting on knowledge they can't use at speed. The people who hold it are busy, the documents that contain it are static, and the processes built around it weren't designed for AI.

Advanced Analytica turns that knowledge into governed agentic systems that work in production. We bring the strategy, the specification, and the AI skills, so the business can move fast and stay safe.

MOVE FAST. STAY SAFE.