Relevance AI

Build teams of AI agents that deliver human-quality work

Operations & Processes

Compliance CertificationsSOC2GDPR

Server LocationUnited StatesEuropeAustralia

About Relevance AI

A data science platform for building AI-powered search and recommendation experiences. It provides capabilities to create embeddings, index data, run vector similarity searches and manage experiments. Teams use it to build apps that return relevant results and tailor content to users.

What Cakewalk Does With Relevance AI

Control who and which agents can access Relevance AI across the workflows it runs. Through Cakewalk, AI agents can act inside Relevance AI and Relevance AI's own agents can access every other connected app. Each call runs as the person who asked, checked against policy with an audit record.

Integration Capabilities

Agent Platform

Relevance AI connects to Cakewalk through a single gateway address. From there it accesses the company's connected apps, with each request scoped to the person using it and checked against policy.

Agent Connection

A Connection lets an AI agent act in Relevance AI through Cakewalk instead of with its own API key. The agent operates with the permissions of the person who made the request, only for the duration of that task. Every call is checked against policy and written to the audit log.

Use Cases

Use Case	Description
One Security Layer for Every AgentAgent Platform	Connect Relevance AI once and it joins the same governance layer as every agent platform your team runs, under one audit log and policies you tune by person, app and action.
Each Person Gets Their Own AccessAgent Platform	When several people use Relevance AI, each one's agent acts with that person's own permissions, never a shared account. The same agent gives each person only the access they already have.
Let an Agent Handle Relevance AI TasksAgent Connection	A person asks their agent to do something in Relevance AI, like find a record, update a field or pull a report. The agent does it through Cakewalk with that person's own access, not a shared key.
Every Action Checked and LoggedAgent Connection	Every agent action in Relevance AI is checked against your access rules and written to the audit log. Safe actions go through, risky ones wait for approval or are blocked.