How to train an AI support agent on your own catalogue

An AI agent is only as good as what you feed it. A practical guide to importing products, writing policies the model can follow, and fixing the answers that come out wrong.

How to · 11 July 2026 · 8 min read · By The OctaDezx team, Builders of the OctaDezx AI customer care platform

Key takeaways

The single biggest predictor of whether an AI support agent works is not the model behind it. It is the quality of the information it was given. A brilliant model with a thin knowledge base will produce confident, useless answers. A modest model with an accurate catalogue and clear policies will quietly resolve most of your inbox.

Here is the order of work that actually gets an agent to a state where you would let it talk to customers.

Step one: import the catalogue, do not describe it

Start with structured product data rather than prose. Names, variants, prices, stock, images, categories and descriptions, imported directly from your storefront. Pasting a storefront URL and importing the catalogue takes seconds and gives the agent something it can be precise about.

The temptation is to summarise your range in a paragraph. Resist it. A summary produces answers like most of our jackets are water resistant, which is exactly the kind of sentence that generates a return.

Step two: write policies as decisions, not vibes

Policies are where most knowledge bases fall apart. Businesses write what they wish were true, in language soft enough to leave room for judgement. An AI has no judgement, so ambiguity becomes invention.

Write each policy as a decision with conditions attached.

Step three: feed it the questions you already answer

Open your inbox and read the last two hundred messages. You will find the same handful of questions repeated with different wording. That list is your highest value training material, because it is empirical rather than imagined.

For each recurring question, add the exact answer you want given, in the voice you want it given in. Upload the files you already have: FAQ documents, spreadsheets of product specs, PDFs of care instructions, a text export of your policies. Anything already written down is faster to import than to rewrite.

If a question comes up ten times a week and nobody has written down the answer, that is not an AI problem. That is a decision your business has not made yet.

Step four: set the tone deliberately

Tone is not decoration. It determines whether customers trust the answer. Decide whether you are warm and chatty or brisk and factual, whether you use the customer's first name, how you handle bad news, and whether you apologise or simply fix.

Give the agent two or three example exchanges written the way you would write them. Examples move tone far more reliably than adjectives do.

Step five: read the first hundred conversations

This is the step everyone skips and the one that matters most. Go through the first hundred real conversations line by line. You are looking for three things: answers that were wrong, answers that were right but sounded wrong, and questions that should have been escalated and were not.

Every one of those is a gap in the knowledge base, and each fix compounds. After a hundred conversations you will typically have added twenty entries and corrected five policies, and the resolution rate will have moved more than any model change would have moved it.

Keeping it accurate as the business changes

Frequently asked questions

How do I train an AI agent on my own products?
Import structured product data directly from your storefront rather than describing it: names, variants, prices, stock, images and categories. Then add your policies as explicit decisions and the exact answers to your most common questions.
What data does an AI support agent need?
Your product catalogue, your written policies for returns, delivery, payment and hours, the answers to your most repeated questions, and two or three example exchanges that demonstrate your tone.
How do I keep an AI agent accurate as my business changes?
Re-sync the catalogue whenever prices or stock change, add a knowledge base entry the second time a new question is asked, review escalated conversations weekly, and retire expired promotions explicitly.

Where this fits in OctaDezx

Keep reading

About the author

The OctaDezx team, Builders of the OctaDezx AI customer care platform. We build OctaDezx, an AI customer care platform used by online stores, restaurants, agencies and clinics to answer customers and take orders around the clock. Everything here comes from running that product and reading real support conversations across those businesses, not from a keyword brief.

Start your free trial · More guides