Audit and framing
Define the decisions the agent may take, the tools it may call and the actions that always require a human.
AI agent development and consulting
An agent that works in production is a system with permissions, limits, tools, memory and a supervision path - not a prompt loop.
I design and build tool-using agents, including multi-agent orchestration with sequential fallbacks and full traceability.
The situations this answers
- An assistant that answers well but cannot act on business systems.
- Agents with no permission model, no limits and no recovery path.
- No evaluation of tool calls, hallucinations or silent failures.
- A single model dependency with no fallback when it degrades.
How it fits together
A supervisor with bounded tools
A supervisor agent calls retrieval, business APIs and a code sandbox, surrounded by memory, an evaluation set and human approval.
What you get
- Agents with explicit tools, permissions and bounded actions.
- Multi-agent orchestration where each agent has one responsibility.
- Evaluation sets for tool use, extraction quality and failure cases.
- Observability on every run, with traces and cost per operation.
- A supervision path and a documented recovery procedure.
How an engagement runs
Design and delivery
Build the agent graph, the tools, the memory and the evaluation set, then compare architectures on real cases.
Industrialisation and takeover
Add monitoring, fallbacks and alerts, then hand over the operating runbook to your team.
Proof and related reading
Frequently asked questions
When is an agent the right choice?
When the task requires choosing tools or adapting a sequence to the content. A deterministic pipeline stays cheaper and more predictable for stable, well-specified processing.
Which agent frameworks do you use?
Mainly Pydantic AI for typed agents and tools, alongside LangGraph or Bedrock agents when the surrounding stack calls for it. The choice follows the constraints, not the reverse.
How do you prevent an agent from taking a wrong action?
Actions are explicitly allow-listed, arguments are validated, risky steps require confirmation, and every call is traced. Recovery is part of the design.
Can agents run on our cloud?
Yes. Agents can run serverless or on managed services inside your account, with your model providers and your access controls.