Answering support before it becomes a ticket
- Organisation
- iLyF — Easy, Instant Insurances
- Role
- Led the build, the knowledge base behind it, and the escalation boundary
- Period
- Malaysia
An omnichannel AI assistant across WhatsApp, Telegram and web — built so that most of the effort went into deciding what it was allowed to say.
- of routine tickets handled without a human
- 70–80%of routine tickets handled without a human
- first response on every channel
- 24/7first response on every channel
- support headcount as the user base grew
- Flatsupport headcount as the user base grew
How the system actually worked
Scroll the figure sideways to read it, or turn your phone.
- Retrieval over curated content, not open generation. The assistant answers from validated material or it does not answer — which is what stops it saying something confident and wrong about a policy somebody paid for.
- The boundary is drawn explicitly: which classes of question it may attempt at all, decided in advance rather than discovered in production.
- An escalation carries the full conversation, so the customer never has to restart their story with a human.
- Every escalation is a knowledge-base gap, not a model failure. Closing those gaps moved deflection far more reliably than prompt tuning ever did.
Context
Support volume grows with the user base, and most of it is the same twenty questions. At the rate iLyF was growing, the honest options were to hire linearly or to answer automatically.
What was actually needed
Instant answers on the channels people already used, without the failure mode that makes support bots hated: confidently saying something wrong about a policy somebody paid for.
How I used AI here
Retrieval over a curated knowledge base, not open generation. The assistant answers from validated content or it does not answer. I drew the escalation boundary explicitly — which classes of question it may attempt at all, and which go straight to a human with the full conversation attached so the customer never restarts their story. The larger share of the project was writing and structuring that knowledge base, not building the assistant.
Decisions that mattered
Treating unanswered questions as a content backlog rather than a model failure. Every escalation was a signal that the knowledge base had a gap, and closing those gaps improved deflection far more reliably than prompt tuning ever did.
What changed
Between seventy and eighty percent of routine tickets resolved without a human, around the clock. Support cost stayed roughly flat while the user base grew, and human agents spent their time on the complex cases that actually needed judgement.
The insight I kept
A support assistant’s quality ceiling is set by your documentation, not your model. Most of our gains came from writing better answers.
Stack & practices
- OpenAI
- Retrieval over curated KB
- Telegram
- Web