Putting an agent into production means deciding what it may do, how its work will be checked and who can stop or recover it when something goes wrong. We build those controls with your engineers, on your infrastructure.
What our own system teaches us
We run our consulting practice with AI agents and can show you a sanitised account of how that system works. Written instructions set expectations. They do not make an agent reliably obey them.
Permissions and checks outside the model can constrain particular actions. Verification tests whether the work meets an agreed requirement. Human review addresses decisions that need judgement. Each control has a scope and can miss failures; an agent’s confidence or claim of completion is not evidence that its work is correct.
Our walkthrough covers the architecture, controls and failures we have encountered, without exposing client data.
What working with your team means
- Embedded: we build alongside your engineers, establishing permissions, validation and review in the working system.
- Advisory: your team builds; we review the architecture, decision boundaries and failure cases.
- Ongoing: a capacity retainer supports your team as the systems evolve.
What you get
An agreed implementation with explicit acceptance criteria: permitted actions, evidence of changes, verification of results, and named human responsibility. We test failure and recovery scenarios as well as successful runs, and hand over the knowledge your team needs to maintain the system.
The checks provide evidence about the cases tested. They do not guarantee that an agent will always behave correctly.
What it costs
Discrete pieces of work are fixed price for a fixed timebox, agreed before work starts. Ongoing support is a capacity retainer, not billed hours. Published rates, expenses at actuals, and if an engagement fails to meet the agreed standard, we refund the fee.
Where to start
If the problem still needs investigation, start with AI Opportunity Discovery. If you know what you need to build, tell us about it, including what the agent would be allowed to change and what failure would cost.