Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
AI Apps

The Cases Where AI Is the Expensive Wrong Answer

Last updated:

The test

Ask the person who does the job to describe how they decide. If they produce a set of conditions, that is a rule engine. If they say “you just know from reading it”, that is a model.

Most business processes are more rule-shaped than people expect, and rules are cheaper on every axis that matters.

What rules do better

PropertyRulesModel
Cost per decisionEffectively nilReal and recurring
SpeedInstantHundreds of milliseconds up
ConsistencyPerfectHigh, not perfect
AuditabilityTrivially explainedRequires effort
TestingExhaustiveStatistical
Changing itEdit a conditionAdjust and re-evaluate

Where models genuinely earn it

  • Free text where meaning matters — emails, notes, reviews
  • Documents with varied layouts, where position cannot be assumed
  • Classification with fuzzy boundaries and many categories
  • Summarising or drafting for a human reader
  • Matching things that are the same but written differently

The hybrid is usually right

Model for the messy part, rules for the decision. Extract the fields with a model; decide what to do with them using logic you can read, test and defend.

That keeps a probabilistic component out of the audit trail while still handling input that rules cannot parse.

An honest example

A client wanted AI to decide which orders needed manual review. Their expert described six conditions in four minutes. We built the six conditions: two days, no running cost, perfectly auditable.

The model then handled the part they could not specify — reading the free-text delivery notes for special instructions. That is the right division of labour.

Frequently asked questions

What if the rules get complicated?

Fifty rules is usually still better than a model, if they are correct and tested. Two hundred conflicting ones suggest the process itself needs simplifying.

Can we start with rules and add AI later?

It is the best sequence. Rules force you to articulate the process, which is exactly what you need before any model can be evaluated.

Do you lose the project by saying this?

Sometimes. We would rather build the two-day rule engine that works than the six-week model that was never needed.

How do we know if our problem is rule-shaped?

Have someone write the decision as if training a new starter. If the document is complete, it is rules.

Keep reading

Been told you need AI?

Describe the decision to us and we will tell you whether a rule would do it better and cheaper.

Book a free 30-minute call Get a project estimate WhatsApp us

Related services

What we build for problems like this one

AI AgentsCustom Software DevelopmentSaaS Development