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.
Pre-launch · built in public
What an answer actually looks like
The same question, answered twice. The chat answer is an illustration of a number with nothing behind it. The Tilltrend answer is not a mockup: it comes from one real run of the product answering "What was total revenue?", executed 2026-07-26 against the demo warehouse.
What was total revenue?
Your total revenue was about $29.4 million. Sales look strong overall.
- Which orders does it count?
- Are refunds taken out?
- Would it say the same tomorrow?
The answer cannot tell you.
- Gross revenue only: the source has no cancellation/refund data.
Total revenue across all time was 29,356,250. This figure represents gross revenue only; the underlying source lacks cancellation and refund data, so the net revenue after adjustments may differ from this amount.
Two renderings of one stored value: the card formats it as money at the display layer, the receipt keeps the exact number.
- metric
- total_revenue
- scope
- all time
- value
- 29,356,250
- hash
- sha256:2bb5a5c95744d84e
SELECT SUM(f.sales_amount) AS total_revenue
FROM gold.fact_sales f- replay, no model
- MATCH
- post-check
- PASS
How it works
Ask 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.
Check it yourself
Reproduce the answer above with:
python app\scripts\ask.py "What was total revenue?"The exact audited text stays one click away in the app, unchanged to the character. Here it is in full: the verbatim terminal output of that same run.
Every number traces to one query. The SQL on the receipt is the governed
statement the deterministic layer executes for total_revenue and
stores in the receipt's execution block. The model only chose
the metric; it never writes SQL. Tilltrend's Ask page shows this beneath
every answer.
The 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.
question: What was total revenue? turn: turn_7333a781e9ba mode: model model: claude-haiku-4-5-20251001 RECEIPTED FACTS =============== (1) [run_metric] total_revenue (all time) <rcp_1e047258878c43cba3b21d673a7ccbc5 | sha256:2bb5a5c95744d84e> 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 was 29,356,250. This figure represents gross revenue only; the underlying source lacks cancellation and refund data, so the net revenue after adjustments may differ from this amount. receipts: rcp_1e047258878c43cba3b21d673a7ccbc5 | sha256:2bb5a5c95744d84e replay: python app\scripts\replay.py rcp_1e047258878c43cba3b21d673a7ccbc5 postcheck: PASS (attempts=1)
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 product. The Shopify app is real and running: install is by private link today, and the public App Store listing waits on our legal pack. If "an analyst that shows its work" sounds like what your store is missing, write to us. A human reads every mail.
Request early access