AI triage on 42,000 client queries a year — freeing 9,000 partner-hours.
A UK Top-50 accountancy firm was losing partner time to recurring client queries. We built a RAG agent that auto-drafts responses with citations, routes exceptions to partners, and cleared the drag on advisory capacity.
Advisory work was being crowded out by routine.
Partners were spending hours a week on queries the firm had answered hundreds of times. Client satisfaction was solid; partner capacity for higher-value advisory was not. The firm wanted to fix that without adding headcount.
We scoped the problem, built a production-grade RAG system integrated with their practice-management platform, and landed it inside 11 weeks.
Production, not a prototype.
Week 1: scoping + evals
Collected 800 ground-truth queries, built offline eval harness before prompt v1.
Weeks 2–3: retrieval
Ingested firm knowledge base (VAT, payroll, R&D, corporate tax), hybrid retrieval with re-ranking.
Weeks 4–8: agent & UI
Tool-using agent, structured outputs, human-review workflow, partner dashboard.
Weeks 9–10: red-team & rollout
Safety testing, partner training, phased rollout across three offices.
Ongoing: operate
Quality monitoring, retrieval refresh, cost optimisation.