Building AI systems that don't reach for AI first

What a field-service inspection project taught us about reliable AI, predictable checks and human review.

Calab.ai engineers working together on a laptop

The best AI system is not always the one that uses AI at every step.

When Calab.ai built a system to inspect photographs of utility meter installations, testing revealed an uncomfortable problem: the same photograph could produce different answers, even when the model sounded certain.

Muhammad Abdullah, Forward Deployed Engineer at Calab.ai, explores how that finding shaped the design: choosing predictable checks where possible, using AI where judgement is needed, and bringing in a person when the evidence is unclear.

Choose whether optional tools can run. You can change your choices at any time using Cookie settings in the footer.