Shoppers ask your AI Chat Bot about products, stock, and orders. The bot doesn’t make up answers. It uses a snapshot of your store data called AI Memory, plus a few live lookups. This guide shows which store content the bot indexes, which details it checks live, and how to force a sync after you update a product.
Prerequisites
- StoreAgent AI for WooCommerce installed, activated, and connected to your StoreAgent.ai account.
- The AI Chat Bot enabled in StoreAgent → Settings → AI Chat → General.
Which content the chat can access
The chat reads from three post types by default, and you can enable others. To configure what’s indexed, go to StoreAgent → Settings → AI Chat → Post Types:
- Products: names, descriptions, prices, categories, tags, attributes, and any custom meta fields you’ve added via the Metadata Keys to Include field on the Products panel.
- Pages: your static pages (about, FAQ, shipping, returns). On by default if you kept the recommended choices in onboarding. Turn the toggle off to stop indexing them.
- Posts: blog posts. On by default if you kept the recommended choices in onboarding. Turn the toggle off to stop indexing them.
For each post type you can also exclude specific items via the Exclude [Post Type] search field on its panel, useful for hiding archived, internal-only, or restricted-content posts from the chat.
Checking what’s indexed
The Post Types tab shows an indexing summary next to each enabled post type: a fraction (for example 19/19) that tells you how many items of that post type are in the index against the total available. When the two numbers match, every published item is indexed; when they don’t, some are still being processed or have failed.
You also get a per-item view: the Products list has an AI Memory column showing each product’s current sync status. The Posts and Pages lists show the same column when those post types are enabled. Hover over the icon to see the details: added, pending upload, needs re-upload, pending deletion, or a message that starts “The last upload to the AI memory failed”. Instead of an icon, some products show “Not publicly viewable” or “Hidden from catalog”. The Post Types tab also shows a failed count for each post type. See How StoreAgent AI Memory works for the full breakdown of statuses and what to do about each.
Triggering a manual sync
StoreAgent re-uploads a product to AI Memory automatically 3 to 5 minutes after you save it. If you can’t wait, for example you’ve just fixed a typo a customer flagged in chat, use Sync Now.
Sync a post type now
- Go to StoreAgent → Settings → AI Chat → Post Types.
- Click the Sync Now icon (a circular arrow) next to the post type’s enable toggle.
Sync Now retries failed items and uploads changed items straight away. Items that haven’t changed since their last upload are skipped. To send every item again, use Clear Post Data Hashes on the Tools tab. See StoreAgent Admin Tools page reference.
Manual sync also helps when the index is partially out of date after a long period of bulk imports, for example after migrating a catalog or importing a product CSV.
What the chat can and can’t reference
The chat answers from indexed content only. That means:
- Yes: any product, page, or post you’ve enabled in Post Types settings, including custom meta fields you’ve explicitly added to Metadata Keys to Include.
- Yes (with the Wholesale Suite integration on): wholesale-role-specific pricing per the customer’s role. See How to integrate StoreAgent with WooCommerce Wholesale Suite.
- No: draft, pending, password-protected, or trashed posts. The index only stores published items.
- No: products with Catalog visibility set to Hidden in WooCommerce. If you hide a product that’s already indexed, StoreAgent removes it from AI Memory. The AI Memory column shows “Hidden from catalog” for these products.
- No: custom-field data unless you’ve added the meta key to the per-post-type Metadata Keys to Include field.
- No: external websites or third-party services. The chat does not browse the web or pull answers from outside sources.
How the chat gets exact prices, stock, and order details
Most answers come from the indexed content described above. For a few details that change often, the AI Chat Bot also does a live lookup in your store at the moment a shopper asks.
- Variable product prices and variation details. A general answer may quote a starting price or a price range from the index, while the exact price and SKU of a specific variation are fetched live when the shopper asks about that variation.
- Stock. The bot checks stock live at the moment the shopper asks. It can say if a product or variation is in stock, out of stock, or on backorder, and if backorders are allowed. If your store shows stock counts, it can also say how many are left. A stock change shows in chat straight away, with no re-index. Your WooCommerce Stock display format setting (under WooCommerce → Settings → Products → Inventory) is respected, so if your store hides quantities, the bot doesn’t get the number. It never gives a count for a product that’s out of stock or on backorder.
- The shopper’s own order. When a logged-in shopper asks about their order, the chat looks it up live. It only ever returns that shopper’s own order. If a guest asks about an order, the chat can’t look it up. Instead it can ask them to sign in and give them a link to your store’s login page. That link is your WooCommerce My Account page, or the WordPress login screen if there’s no usable My Account page.
These live lookups are read-only and stay within your own store. The chat still never calls external websites or third-party services.
Troubleshooting
The chat returns outdated product details
If a stale answer lasts more than 10 minutes, go to StoreAgent → Settings → AI Chat → Post Types and click the Sync Now icon next to the post type. If it’s still stale, hover over the product’s icon in the AI Memory column. If the message says “The last upload to the AI memory failed”, StoreAgent retries automatically on the date shown after “Scheduled:”. After several failed attempts, it waits about a day before the next try.
To retry now, go to StoreAgent → Settings → AI Chat → General and click Resume indexing in the Indexing needs attention notice. The small delay you see after a normal save is expected: StoreAgent waits 3-5 minutes before it re-uploads a changed product.
The chat answers from a page I don’t want it to reference
Go to StoreAgent → Settings → AI Chat → Post Types, find the post type’s panel, and add that specific page to the Exclude [Post Type] search field. The chat will stop referencing it on the next sync. Alternatively, disable the whole post type’s toggle if you don’t want any of its items in the index.
Custom field values aren’t appearing in chat answers
List each meta key, comma-separated, in the Metadata Keys to Include text area on the post type’s panel. Save, then update each affected product so it is uploaded again with the new fields. Changing this setting does not mark existing products as changed, so Sync Now skips them until they are updated. To send every item again at once, go to StoreAgent → Settings → Tools and, under Clear Post Data Hashes, click Clear Post Hashes. See StoreAgent Admin Tools page reference. By default, only standard WooCommerce product fields (name, description, price, and so on) are indexed.
Custom fields are read from the product or post itself, not from individual variations. Content is also indexed as written, so text that only appears after a shortcode or page builder renders on the front end is not part of the index.
Frequently asked questions
Does the chat see customer personal data?
Customer accounts and personal data are never added to the index. The chat can look up a logged-in shopper’s own order when they ask about it, but only their own order, and only coarse location details (city, state, postcode, and country). It never returns a customer’s name, email, phone number, full street address, payment details, or anyone else’s orders. It does see the logged-in user’s role, so it can apply wholesale pricing.
What data does the AI Chat Bot actually use?
Two things: the store content you choose to index (your products, and any pages or posts you enable), and the messages in the current conversation. That is separate from your website’s general privacy policy, which covers site-wide topics like cookies, IP addresses, and analytics. Those tracking topics are not what the AI Chat Bot works from. It answers from your published store content and the conversation itself.
How big is the index?
It depends on your plan’s vector item allowance. The free StoreAgent Lite plan includes 1,000 memory items; paid plans include larger allowances. See How StoreAgent calculates your usage for the math, and your StoreAgent.ai dashboard for current usage.
What if I exceed my vector item allowance?
New items aren’t indexed once you’re over the limit, and chat answers may reference older versions of products that have changed. When the limit stops an upload, StoreAgent pauses syncing and shows a StoreAgent: AI Memory Syncing Paused notice with a View account button.
The fix is to either remove items from AI Memory (Bulk actions → Remove from AI Memory) or upgrade your plan. After you upgrade or renew, syncing resumes automatically.
Need help?
If you have a question or run into any issues, we’re here to help.
- Premium users: Open a support ticket
- Free users: Visit our community forum
