Any name of the medicine. Only facts from the leaflet.
Customers search by brand, by active ingredient, by symptom — often misspelled. AACSearch links names to ingredients, matches dosages exactly, and answers only from the official leaflet text you index.
Queries plain keyword search gets wrong
нурофенbrandибупрофен 400ingredient + doseибупрафенtypoот головной болиsymptomаналог но-шпыsubstituteWhere search loses customers today
Brand vs active ingredient
The customer knows the brand; the cheaper generic with the same ingredient stays invisible.
Dosages are numbers
200 and 400 mg are different products; fuzzy matching must not merge them.
Medical claims
A search assistant must not invent indications or dosages.
How AACSearch solves it, layer by layer
Each card names the capability behind it. Items marked “in development” are designed and scheduled, not live yet.
Finds the right item from the first letters — typos, synonyms, filters, meaning.
Widens the basket: similar, frequently together, personal.
Answers questions a filter can't, citing your own catalogue and docs.
Leaflet-only answers
Answers strictly from the indexed leaflet text with citations; refuses otherwise.
Learns how items, queries and topics connect — and leads the visitor to the goal.
Ingredient graph
Will link brands, ingredients and forms so substitutes are found by composition, not by name.
One visitor, from first query to goal
What the visitor does on the left, what AACSearch does on the right.
- 1
Search
Types “ибупрафен 400”.
Finds ibuprofen 400 mg products despite the typo.
Instant search - 2
Compare
Opens a brand product.
Shows generics with the same ingredient and dose.
Recommendations - 3
Ask
Asks about contraindications.
Quotes the leaflet with a citation.
AI answers with citations
Your first two weeks
A typical rollout for this industry. Most teams are live on day one and spend the rest of the time measuring and tuning.
Day 1
Import products with active ingredient and dosage fields.
Day 2
Link brand and generic names with synonym sets.
Week 1
Index leaflet texts; check the assistant only quotes them.
Week 2
Track generic share and zero-result rate.
What to measure
The numbers to judge a rollout by. Compare them with an A/B split or a before/after window on the same traffic.
- Zero-result rate
- Misspelled drug names are the main source.
- Generic share
- Orders where a generic alternative was chosen.
- Leaflet citation rate
- Every assistant answer should quote the leaflet it is based on; the target is 100 %.
Connects to
- 1C-Bitrix
- YML / CSV feed
- REST API
Capabilities used
Coming next
Questions
Search for Pharmacy & health, live this week
Connect a feed or a site, embed one script, and measure the difference on your own traffic.