A knowledge assistant support agents actually trust
Agents spent time hunting through help articles, past tickets and internal notes. We built an assistant that answers from those sources and cites them, with a feedback loop to keep it accurate.
These are representative example engagements, written to show our approach. Companies are anonymised and the measures are the targets we agree up front, not guaranteed results.
The challenge
- Answers lived in wikis, old tickets and individual agents’ heads, so replies varied by who picked up the ticket.
- New agents took weeks to become productive.
- Earlier AI experiments produced confident but unsourced answers the team could not rely on.
Our approach
Index the knowledge
Help centre, past resolved tickets and internal runbooks were cleaned, chunked and indexed, with permissions respected.
Answer with citations
Retrieval-augmented answers that quote and link their sources, and say “not found” rather than guess.
Evaluate before launch
A test set of real tickets with agent-approved answers, scored on every change to prompts and retrieval.
Close the loop
Agent thumbs-up and thumbs-down, and corrections, feed back into the test set and knowledge base.