/ Service
Agentic prototypes stall on the parts that are left until after the demo: how the agent reaches internal systems, how answers stay grounded, and how anyone can tell when behaviour regresses. I design those in from the start — the shape of the reasoning loop, the retrieval behind it and the evaluation that keeps it honest.
/ What this covers
/ Evidence
Retrieval architecture · ReAct agents
Architected and delivered a scalable enterprise RAG and agent platform: a 500GB+ embedding and ingestion pipeline feeding hybrid search with reranking and vector retrieval, behind a ReAct agent architecture. Retrieval quality was treated as the product — measured chatbot accuracy improved to 95% and response latency was reduced.
Grounded assistant · Procurement
Designed and productionised a grounded enterprise Procurement assistant on Azure AI Foundry, using LangGraph for orchestration, ChatKit for the interface, PGVector for retrieval and integrations with MCP servers. Answers stay grounded in trusted enterprise documents, and the architecture was standardised into a reusable reference implementation.
Read the Enterprise Procurement Knowledge Assistant case study
/ Related services
Paved paths and internal platforms so AI applications start from a supportable, governed baseline.
Evaluation sets and retrieval tuning that make assistant accuracy and grounding measurable over time.
Governed agent access to internal systems through MCP servers and shared integration patterns.
The operating model — identity, approvals, usage and cost controls — that lets AI scale past pilots.
/ Next step
Open to full-time Senior–Staff AI / agent platform roles (remote-friendly), as well as contract and consulting engagements. Response within two business days.