Yes. The SleekAI Wizard maps product fields, postmeta, and taxonomies into named variables that the system message uses on every request. Setup typically takes a few minutes per data source. Variables resolve at request time, so a price change or a stock decrement shows up in the next answer without re-syncing.

You need an account with at least one supported provider. SleekAI works with OpenAI, Anthropic, Google, and OpenRouter, so you can pick a cheap fast model for product Q&A and a stronger one for refund or returns flows. Usage and billing stay on your provider account, not on SleekAI.

Yes. Multibot mode runs several chatbots on one site, each with its own system message, data sources, and display conditions. A common setup is a product-page bot, a cart abandonment bot, and an admin bot for summarising today's orders, all coexisting under the same SleekAI install.

Sync products into an OpenAI Files vector store of up to one gigabyte per file. SleekAI handles the upload pipeline, and the model retrieves only the rows that match the query, so you do not blow the context window. The retrieval index can be refreshed on a schedule when you publish new products.

Yes. WooCommerce stores variation data and per-variation stock as child posts and postmeta, both of which SleekAI's data sources can read directly. The bot can confirm whether the medium-blue version of a product is in stock without you exposing the entire SKU list to the prompt.

Yes. Conversation logging is per chatbot, with user messages, assistant replies, model name, token usage, and page URL all stored inside WordPress. You can spot repeated objections, tighten the system prompt, and feed the patterns back into product descriptions or FAQs.

Yes. SleekAI reads from the WooCommerce data layer rather than direct SQL, so whether you run legacy post-based orders or High-Performance Order Storage, the bot can pull a logged-in customer's last order, status, and tracking field if you expose it.

Yes. If WPML, Polylang, or TranslatePress translates your products, SleekAI reads whichever language is currently active on the request. You can also run separate chatbots per language with their own system messages, useful when tone of voice differs across markets.