Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
AI Chatbots

An AI Chatbot That Actually Answers Questions

Last updated:

Why people hate chatbots

Because most of them are worse than the alternative. They answer a question adjacent to the one asked, cannot escalate, and stand between a customer and a person who could have solved it in thirty seconds.

The technology is no longer the problem. The design is: a bot optimised to deflect tickets rather than to answer questions will always end up frustrating the people it deflects.

Grounding: answering only from what you have

The single most important design decision is that the bot answers from your content, not from the model's general knowledge. Your returns policy, your delivery times, your product specifications — retrieved, then answered from.

Concretely: the question is used to retrieve relevant passages from your own material, and the model is instructed to answer only from those passages and to say so when they do not cover the question. That constraint removes the majority of embarrassing answers.

An ungrounded bot asked about your refund window will produce a number. It will be a plausible number. It will not be your number.

Saying “I do not know” is a feature

A bot that answers 70% of questions well and admits the other 30% is far more valuable than one that answers everything with 85% accuracy. Users forgive not knowing; they do not forgive being told something wrong.

  • Retrieved passages do not cover it — escalate
  • Retrieval confidence is low — escalate
  • The question involves an account, an order or money — check the real system or escalate
  • The user asks twice — escalate without being asked

Escalation in one step

Handover must be one action, always visible, and it must carry the conversation with it. Making a frustrated customer repeat everything to a human is the moment the whole investment turns negative.

We also route on sentiment: a message expressing frustration goes to a person immediately regardless of whether the bot could have answered. The ticket deflection lost is worth less than the relationship saved.

What to measure

MetricWhat it tells youWarning sign
Resolution rateAnswered without a humanHigh with low satisfaction = confident wrongness
Escalation rateHanded to a personVery low is suspicious, not good
“I do not know” rateHonest gapsRising = content is out of date
Repeat questionsSame user asking againThe first answer missed
Post-chat satisfactionWhether it helpedThe only metric that matters alone

Deflection rate on its own is a dangerous target. It rewards a bot for preventing contact rather than for resolving problems, and those are not the same thing.

What it takes to build and keep

A useful bot needs your content in a maintainable form, a retrieval layer, the answering logic with its refusal rules, escalation into your existing helpdesk, and a review process for the conversations it got wrong.

That last item is the one businesses under-plan. A chatbot is not a project that finishes; it is a system that needs someone reading a sample of conversations weekly and fixing the content gaps it exposes. Budget an hour a week forever, or expect quality to decay within two months.

Frequently asked questions

How long does a support chatbot take to build?

Four to eight weeks for a grounded bot with escalation, assuming your content exists in some usable form. Longer if the content has to be written first.

Can it access customer accounts and orders?

Yes, through the same kind of narrow tools we give an agent, with authentication. That is where a bot becomes genuinely useful rather than a search box with manners.

What happens when our policies change?

You update the source content and the bot follows, because it answers from retrieval rather than from anything baked in at build time.

Will it handle other languages?

Usually well, and the failure mode is worth knowing: it may answer in the user's language from English source content, which is normally what you want but should be tested rather than assumed.

Keep reading

Want a chatbot that answers from your own content?

Tell us what your customers ask most and we will tell you how much of it can be handled well — and what should still reach a person.

Book a free 30-minute call Get a project estimate WhatsApp us

Related services

What we build for problems like this one

AI Chatbot DevelopmentAI Integration