The anatomy of AI: what we learned building it in the real world

At our recent event, the QED team hosted The Anatomy of AI. Not a product demo. Not a panel of predictions. An evening with the engineers who build these systems every day, talking about what actually happens when AI meets a real organisation.

The question we started with: when you are building AI, where do you land on cost, accuracy, and privacy? Not as abstract values. As real constraints that shape every decision in the build.

You cannot maximise all three. That is not a limitation of the technology. That is the nature of the problem. The job at the start of any project is to understand which one matters most, and design from there.

The evening was built around three case studies. Three industries. Three very different places to land on that triangle.

Education: safeguarding 450+ UK schools

Before this project, safeguarding worked on keyword alerts. Every match triggered a manual review. Auditors were processing a backlog of 45 minutes per incident. At that speed, a real problem could escalate before anyone reached the school.

The AI layer we built analyses full context, not keywords. Text, images, behaviour patterns. It removes the noise before anything reaches a human reviewer, so auditors spend their time on the cases that actually matter.

• Alert processing time: 45 minutes to 8 minutes
• False positive rate reduced by 42%
• Detection rate maintained at 100%
• Same human effort. 70% more pupils covered.

Privacy was not a feature. It was a design constraint. Student data never leaves UK servers. Images are processed locally. Identifiers are anonymised before anything is sent externally.

Read the full case study here.

Energy: coordinating an entire building, not just a floor

Large commercial buildings are optimised floor by floor, manually. The problem is that optimising one system creates an imbalance somewhere else. Heating a floor affects the one above. Reducing AC for a quiet afternoon creates a problem the next morning.

The system we built coordinates everything at once. Heating, ventilation, air conditioning, occupancy, energy costs. No more local fixes that create global problems.

• 20% reduction in energy consumption
• 35% improvement in HVAC efficiency
• 26% reduction in carbon footprint
• Return on investment within 14 months

Read the full case study here.

Defence: institutional knowledge that stays secure

Cost estimation in defence depends on expertise that lives in people. When those people leave, the knowledge goes with them. Proposals took three to six weeks and required five people to get right.

The constraint here was privacy, not accuracy. No sensitive data could leave the client's environment. We built the system entirely on self-hosted language models. The institutional knowledge now lives in the system, not only in people.

• Proposal time: 3 to 6 weeks down to under one week
• Team required per estimate: 5 people to 1
• Estimator productivity up 80%

Read the full case study here.

What the evening was really about

Three industries. Three completely different constraints. The same underlying question every time: what does this organisation actually need, and what are we building within?

The conversations after the presentations went further than we expected. People were not asking what AI can do. They were asking whether they can trust it, afford it, and control it. Those are the right questions.

That is the conversation we want to keep having.

If you want to understand where AI could move the needle for your organisation, start with a diagnostic.

Talk to us We will tell you if it makes sense.