LLM & Agents · Enghouse Interactive · 2024 — Present

Agentic Knowledge Assistant

Agentic assistants and RAG pipelines that give customer service agents accurate, context-aware answers from large knowledge bases.

01 The problem

Support agents lost time digging through sprawling knowledge bases, and generic chatbots produced confident but wrong answers.

02 What I did

Upgraded LLM services with RAG architectures built for large-scale knowledge retrieval.
Built agentic assistants that ground every answer in the knowledge base and draft context-aware replies.
Added code-interpreter tooling so the assistant can analyse CSV / XLSX data on demand.
Shipped behind unit and end-to-end tests, Jenkins CI/CD and an automated quality-evaluation framework.

03 Impact

Faster, more accurate responses for customer service teams
Answer quality measured automatically — not by spot checks
Production-grade LLM services with real test coverage

Client work — details generalised to respect confidentiality. Happy to discuss specifics in an interview.