Relevance AI

What it does

Relevance AI is a low/no-code platform for building AI agents and multi-agent teams that complete business tasks on their own. You describe a task, clone a pre-built agent from the Marketplace, or build from scratch. Agents can be given tools (sending email, updating a CRM, searching the web, calling an API) and knowledge sources such as uploaded files, Google Drive, SharePoint, Notion or websites. The output is a running agent or linked workforce, plus monitoring data on cost, evaluations and traces.

Teams use it mostly for sales and customer-facing work: prospect research, pre-meeting briefs, follow-up logging, meeting scheduling, deal review, support triage and content drafting. Its distinguishing features are Invent, an assistant that generates agents from a description, and a visual canvas that connects several agents into a workforce. Each agent can be run with human approvals, escalations, evaluation pass rates and per-task cost visibility, and the company frames adoption as moving from assisted copilots to autonomous agents.

It suits operations, sales, support and marketing teams, especially enterprises that need SSO, role-based access, audit logs and data residency. Sign-up is through the web app, and the docs mention a built-in chat for trying agents. Published pricing in the reviewed pricing information is limited to an Enterprise tier sold through sales, so smaller teams should confirm plan costs before committing. Agents run on third-party models, so output quality and cost vary by model chosen.

What it can do

• Build agents from a description with Invent, from Marketplace templates, or from scratch
• No-code tool builder for actions like sending email, updating a CRM, web search and API calls
• Knowledge (RAG) connected to files, Google Drive, SharePoint, Notion and websites
• Multi-agent workforces linked on a visual canvas
• Human-in-the-loop approvals, escalations and triggers
• Monitoring with agent tracing, evaluation pass rates and cost visibility

Works with

• Google Drive
• SharePoint
• Notion

Example workflows

Pre-meeting brief for sales reps

Input: CRM account records and live web or news sources. Steps: a research agent enriches the account, a prepper agent compiles context before each meeting. Output: a brief for the rep, with call notes logged afterwards.

Escalating at-risk renewals

Input: customer signals and renewal data. Steps: an agent reviews accounts against criteria, flags risk, and routes cases for human approval. Output: an escalation list and follow-up actions.

Before you choose

• Only an Enterprise plan via sales is shown; self-serve prices and free tier are unconfirmed
• Agents depend on third-party AI models, and per-task costs vary by model
• Case-study results are vendor-reported and not independently verified

Listed under

• Sales
• AI agents
• Automation
• Customer success
• Enterprise
• No-code
• Operations

Get started

Enterprise plan requires talking to sales

1. Create an account via the web sign-up
2. Create a first agent with Invent, a Marketplace template, or from scratch
3. Add tools and knowledge sources, then set approvals and triggers before deploying

Enterprise pricing is custom via sales. Self-serve plan prices, credit allowances and free-tier terms were not confirmed.

Source: relevanceai.com/pricing, checked 29 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Specialist AI Agents for Every Task | Relevance AI ↗relevanceai.com
• Pricing - Relevance AI ↗relevanceai.com
• Introduction - Relevance AI Documentation ↗relevanceai.com

Company website

relevanceai.com: product, pricing and policy pages

YC directory mirror

Batch and company name

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.