Managed AI search for your data
Agentic search that learns.
Records in → agentic search out.
Evaluating Relevan for a large team? Talk to sales about dedicated capacity and an SLA.
Fig 00
01 / Drop it in
Your records become a tuned index.
02 / It learns
Agents send feedback about their searches.
03 / It improves
Each search makes the next one smarter.
04 / No ops
Nothing to size, tune, or keep running.
01 / Ingest
Drop your records in.
Send your catalog, your docs, or your profiles. The index designs itself.
02 / Feedback
Your agents stop guessing.
Responses carry feedback agents can use to improve their search.
From a real response
Matched: headphones. Top results share terms you have not used yet: wireless, audio, noise, cancelling.
03 / The loop
It gets better while you sleep.
Agents don't learn from their search mistakes. Relevan does. We use each search to improve the next one.
The ranking belongs to your index. Your results improve from your traffic.
noise-cancelling headphones for travel
Run the search to compare regular search with the Relevan Protocol.
This walkthrough is scripted against a fixed product catalog, so it plays the same way every time. Every query, score, and protocol response is replayed from the real search engine, and a test fails if any of them drifts. Create an index in the console to run it against your own data.
Searches to reach the answer
3 → 2
Results the agent must read
22 → 6
The same shopper, the same catalog, the same opening query. The second run reads what matched and finishes sooner.
04 / Ops
Nothing to operate.
Search engines are easy to start and hard to keep. Relevan carries the indexing, the tuning, the upgrades, and the uptime.
- —No cluster to size, shard, or upgrade
- —No relevance tuning by hand
- —No relevance engineer to hire
- —No reindex window, and no on-call rotation
The whole surface
Two calls.
RELEVAN_URL="https://feat-650-agent-skills.api.dev.relevan.dev"
# Search the index
curl -X POST "$RELEVAN_URL/v1/$ORG_ID/indexes/products/search" \
-H "x-api-key: $RELEVAN_API_KEY" \
-H "content-type: application/json" \
-d '{"query": "travel headphones"}'
# Report the outcome. Send back the queryId
# from the response's searchContext.
curl -X POST "$RELEVAN_URL/v1-beta/$ORG_ID/indexes/products/feedback" \
-H "x-api-key: $RELEVAN_API_KEY" \
-H "content-type: application/json" \
-d '{"actionName": "conversion", "label": "purchase",
"queryId": "<queryId>", "objectId": "sku-12345"}'Search, then send feedback. Relevan does the rest.