For Agents
Configure Algolia personalization strategies and read or delete per-user affinity profiles so search results adapt to each user.
Get started with Personalization API in minutes using your preferred integration method.
# Add to your MCP client config (Claude Desktop, Cursor, Windsurf)
{
"jentic": {
"url": "https://api.jentic.com/mcp",
"auth": "oauth"
}
}
# Then ask your agent:
"set up Algolia personalization strategy"
# → Jentic returns the GET /events tool with parameter schema, agent executes.What an agent can do with Personalization API API.
Define a personalization strategy that weights facets and events for affinity scoring via POST /1/strategies/personalization
Read the current personalization strategy for an application via GET /1/strategies/personalization
Retrieve a user's affinity profile keyed by user token via GET /1/profiles/personalization/{userToken}
Delete a user's profile to reset affinities or comply with erasure requests via DELETE /1/profiles/{userToken}
GET STARTED
Use for: I need to set up a personalization strategy for an Algolia app, Retrieve the affinity profile for a specific user token, Delete a user's personalization profile after a privacy request, Update the facet weights in our current personalization strategy
Not supported: Does not handle search execution, event ingestion, or product recommendations - use the Algolia Search, Insights, and Recommend APIs for those. Use this API for personalization strategy and user profile management only.
Jentic publishes the only available OpenAPI document for Personalization API, keeping it validated and agent-ready.
Jentic publishes the only available OpenAPI specification for the Algolia Personalization API, keeping it validated and agent-ready. The Personalization API manages personalization strategies and user profile data for Algolia search experiences. You define which facets and events count toward each user's affinity score, then read or delete the resulting per-user profile. Personalization is rate-limited to 40 calls per second per application.
Issue a temporary client API key scoped to the user's session via /setClientApiKey
Patterns agents use Personalization API API for, with concrete tasks.
★ Stand up personalized search for an e-commerce site
Define a strategy that scores brand and category facets, plus click and conversion events, for each user. Once events flow in via the Insights API, the Personalization service builds an affinity profile per userToken and Algolia automatically reorders search results to favor items matching that profile. Setup is a single POST to /1/strategies/personalization.
POST /1/strategies/personalization with eventScoring weighting clicks at 1 and conversions at 5, and facetScoring weighting brand at 3 and category at 2
GDPR profile reset on account deletion
When a user deletes their account or exercises the right to erasure, call DELETE /1/profiles/{userToken} to remove their affinity data from Algolia. Pair with DELETE /1/usertokens/{userToken} on the Insights API to wipe the underlying events.
Call DELETE /1/profiles/user_42 to remove the user's affinity profile, then DELETE /1/usertokens/user_42 on the Insights API to wipe the events
Inspect personalization quality in production
Pull a sample of user profiles via GET /1/profiles/personalization/{userToken} to verify that affinities reflect real user behavior. If profiles look thin, increase event sampling on the Insights API or adjust facet weights in the strategy.
GET /1/profiles/personalization/user_42 and report which facets and values have the highest affinity scores
Agent-managed personalization tuning
An AI agent supporting a merchandising team can read the current strategy, propose facet weight adjustments based on conversion data, and apply the new strategy through Jentic - all from a chat interface. Credentials stay in the Jentic vault.
Search Jentic for 'update Algolia personalization strategy', load setPersonalizationStrategy, and execute with the new facet and event weights
9 endpoints — jentic publishes the only available openapi specification for the algolia personalization api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/1/strategies/personalization
Get current personalization strategy
/1/strategies/personalization
Create or update the personalization strategy
/1/profiles/personalization/{userToken}
Get a user's affinity profile
/1/profiles/{userToken}
Delete a user's personalization profile
/1/strategies/personalization
Get current personalization strategy
/1/strategies/personalization
Create or update the personalization strategy
/1/profiles/personalization/{userToken}
Get a user's affinity profile
/1/profiles/{userToken}
Delete a user's personalization profile
Three things that make agents converge on Jentic-routed access.
Credential isolation
x-algolia-application-id and x-algolia-api-key are stored encrypted in the Jentic vault. Agents receive a scoped token at request time; the raw Algolia keys never enter agent context or logs.
Intent-based discovery
Agents search Jentic by intent (e.g. 'set up Algolia personalization' or 'delete a user's affinity profile') and Jentic returns the matching Personalization operation with its input schema.
Time to first call
Direct integration: 1 day to wire strategy management, profile inspection, and rate-limit handling. Through Jentic: under 30 minutes - search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Algolia Recommend API
Different relevance lever - product recommendations rather than personalized search ranking
Choose Recommend when you need 'related products' or 'frequently bought together' rather than personalized result ordering.
Algolia Insights API
Sends the events that build personalization profiles
Always pair with Insights - Personalization is empty without click and conversion events from Insights.
Algolia Search API
Personalization rerankings apply to Search API queries
Use Search to run queries with the userToken parameter so personalization affinities are applied.
Specific to using Personalization API API through Jentic.
Why is there no official OpenAPI spec for the Personalization API?
Algolia does not publish a standalone OpenAPI specification for the Personalization API. Jentic generates and maintains this spec so that AI agents and developers can call the Personalization API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Algolia Personalization API use?
Two API key headers: x-algolia-application-id and x-algolia-api-key with the personalization or admin ACL. Through Jentic, both are stored in the vault and injected at request time, so agents never handle the raw key.
Can I read a single user's affinity data?
Yes. GET /1/profiles/personalization/{userToken} returns the user's facet and event affinity scores. Use it to debug personalization quality or to surface a 'why this result' explanation in the UI.
What are the rate limits for the Algolia Personalization API?
40 API calls per second per application. The response includes x-ratelimit-limit, x-ratelimit-remaining, and x-ratelimit-reset headers so clients can pace themselves. Plan for backoff on /1/profiles reads during bulk audits.
How do I update the personalization strategy through Jentic?
Search Jentic for 'update Algolia personalization strategy', load setPersonalizationStrategy, and execute with the desired eventScoring and facetScoring arrays. Jentic handles the credential injection.
Does Personalization work without sending Insights events?
No. Personalization profiles are built from click, conversion, and view events captured by the Insights API. Without those events the affinity profile remains empty and search results are not personalized.