Compare products across retailers
Ask for a product, pack size or category and return comparable shelf prices, effective prices and unit prices across the four major retailers.
Commercial add-on · Private MCP-compatible access
BasketWatch Agent Access exposes the live grocery dataset through a managed private layer for analyst copilots, internal chat tools and automated reporting workflows. It is designed for commercial teams that want answers with prices, promotions, unit prices and evidence attached.
What it can do
The agent layer is not a general chatbot. It is a focused interface over structured Irish grocery data across Aldi, Tesco, SuperValu and Dunnes Stores.
Ask for a product, pack size or category and return comparable shelf prices, effective prices and unit prices across the four major retailers.
Surface current Clubcard, Real Rewards, multibuy, was-price and member-only offers with the underlying offer text preserved.
Turn week-over-week changes into readable summaries: what rose, what fell, by how much, and where the evidence came from.
Identify newly listed products, removed products and range churn by retailer, category or search term.
Build weekly category notes, promotion roundups, competitor snapshots and customer-ready summaries from the latest snapshot.
Responses can include scrape dates, retailer names, product URLs, IDs and row-level context so an analyst can verify the conclusion.
Example prompts
These are the kinds of workflows the private agent layer is designed around. Exact connector details, endpoints and setup instructions are only shared with approved commercial users.
Private tool layer
The agent uses controlled BasketWatch data tools, then writes the answer from returned rows. That keeps the LLM away from guessing prices or inventing promotional context.
How access works
The public website explains what the layer can do. The implementation details stay private so access can be controlled, metered and supported properly.
We agree the use case: analyst chat, weekly brief, watchlist, product comparison or internal copilot.
Usage limits, data access, cadence and support level are matched to the team and subscription.
Approved customers receive private setup details and keys. Connector internals are not published publicly.
Answers are checked against row-level evidence so teams can trust the data behind the summary.
Pricing model
Agent access is separate from the public API marketplace listings. It is best suited to teams that already know they want BasketWatch data inside an AI workflow and need controlled access, support and usage boundaries.