AI usage grows, cost follows, and leadership asks you to control it. The instinct is to reach straight for a spending cap. Our concern was that doing so would undermine the adoption we had encouraged, while the arithmetic showed that a daily limit would not control the overall budget anyway.
This case study follows the design of cost governance for AI development tooling across an engineering organisation while adoption continues to evolve. Governance that has any chance of sticking depends as much on framing the policy and sequencing cost control efforts as it does on thresholds, and choosing a number is often easier than deciding what the control is supposed to achieve.
This talk has been presented at TechLead Conf London 2026: Adopting AI in Orgs Edition, check out the latest edition of this Tech Conference.



















