Product recommendation settings
Ecommerce → AI configuration decides how the bot turns a question into a shortlist of products.
Search strategy
| Option | How it works | Suited to |
|---|---|---|
| Product Search Only (default) | Searches product records directly | Titles and descriptions that are rich and specific |
| Product Search with Category Fallback | Tries products first, then falls back to categories | Catalogs where some questions are better answered by a category than by one product |
| Category Search Only | Matches the question to a category, then shows its products | Large catalogs of similar items, or thin product descriptions |
New chatbots start on Product Search Only. Category Search Only returns nothing when your categories are empty, so check Ecommerce → Categories before choosing it.
Product Title Search Finetuning
Describe how your product titles are structured, so the AI knows which part is the product name:
Brand - Product name - VariationIf your titles read GreenCo — Monstera Deliciosa — 60 cm, saying so stops the AI treating the size as part of the product name.
This field is shown for the two product-based strategies.
Category Search Finetuning
Extra instructions for category search. Shown when a strategy that uses categories is selected. Use it for the vocabulary gaps between how you name categories and how customers ask:
Customers say “office plants” for the Houseplants category. Treat “gifts” as a request across all categories rather than as a category.
Enhanced Product Detail Prompt
Extra instructions for how recommendations are written up. This shapes presentation, not selection:
Always mention light and watering needs. Say if a product is on sale. Do not claim a delivery date.
Keep it short. Long instructions here make replies wordy and slow.
Brand awareness
Turn on Brand awareness when you sell branded goods and customers ask by brand. It tunes product search to the brands in your catalog and adds a Brands page to the Ecommerce menu, where you choose which brands stay available.
Do not recommend unavailable products
With this on, the bot skips products your feed marks as out of stock. It depends on the availability field being present in your feed — without it, nothing is filtered. See Product feed field reference.
How to tune without guessing
- Collect ten real questions from Chat conversations that returned poor or no products
- Change one setting
- Ask the same ten questions on the Demo page
- Keep the change only if more of them improved
- Check Chats with Products and Conversion Rate on the Dashboard a week later
When settings are not the problem
If most questions return nothing, look upstream first:
- No products imported for the visitor’s language
- Descriptions that only list specifications
- Missing
product_typevalues, leaving categories empty - Do not recommend unavailable products on, combined with a feed where availability is wrong or missing
Related articles
Connect a product feed
Import your catalog from a Google Shopping feed or a CSV URL.
Categories and brands
Curate which parts of your catalog the bot may suggest, and set follow-up questions.
Product feed field reference
Exact column and element names Mikabot reads from CSV and Google Shopping feeds.
Contact us
Our support team is ready to give you fast, personal help when you need it.