The AI analyst for your store.
Every answer shows its work.
Ask questions about your store in plain language. Every number in the answer carries a receipt — the governed metric definition, the exact SQL, and a hash you can replay without the AI in the loop.
Request early accessAsk in plain language
"What was total revenue?" "Compare June and July." "Which countries drive revenue?" The model picks the right governed metric and writes the prose — it never writes the SQL and never touches your data directly.
Every answer carries a receipt
Answers come in two visible sections: receipted facts (numbers produced by governed SQL, each with a receipt id and hash) and interpretation (model prose, clearly labeled as not receipted). Any receipt can be replayed model-free; a doctored one fails.
Your warehouse is yours
Tilltrend builds a real bronze/silver/gold warehouse from your store data — on PostgreSQL you control, exportable, inspectable. Built so that leaving is easy, which is exactly why you won't have to.
What an answer actually looks like
This is not a mockup. It is the verbatim terminal output of the product answering "What was total revenue?" — run on 2026-06-13 against the demo warehouse. Reproduce it yourself with:
python app\scripts\ask.py "What was total revenue?"question: What was total revenue? turn: turn_aba83b83e19d mode: model model: claude-haiku-4-5-20251001 RECEIPTED FACTS =============== (1) [run_metric] total_revenue (all time) <rcp_c60c017f43c346328383448a66088735 | sha256:371834e1a0a6100a> total_revenue = 29,356,250 caveat: Gross revenue only — the source has no cancellation/refund data. INTERPRETATION (model, not receipted) ===================================== | Total revenue across all time is 29,356,250. This figure represents gross revenue; the underlying data does not include information on cancellations or refunds, so the actual net revenue may differ. receipts: rcp_c60c017f43c346328383448a66088735 | sha256:371834e1a0a6100a replay: python app\scripts\replay.py rcp_c60c017f43c346328383448a66088735 postcheck: PASS (attempts=1)
Every number traces to one query. Here is the governed SQL Tilltrend runs
for total_revenue — the exact statement the deterministic
layer executes for that metric and stores in the receipt's execution
block. The model only chose the metric; it never writes SQL. Tilltrend's Ask page now
shows this beneath every answer:
SELECT SUM(f.sales_amount) AS total_revenue
FROM gold.fact_sales fThe 29,356,250 is a property of the demo dataset, not a revenue claim about this product or anyone's business. Replaying that receipt re-executes the same governed SQL with no model involved and grades the result — observed verdict: MATCH. Doctor the receipt file and it fails. See every claim with its reproduction command →
Where this is honest by construction
Tilltrend is pre-launch. No merchant counts, no testimonials, no revenue-lift percentages — we have none, so none appear on this site. What we do have is a working product whose every claim is reproducible: the evidence page lists each one with the exact command and the observed result, and the changelog records only shipped, verified work.
Early access
We're looking for a small number of merchants to shape the first connectors (Shopify planned first). If "an analyst that shows its work" sounds like what your store is missing, write to us — a human reads every mail.