Relevance AI
Platform for building and deploying a workforce of AI agents with a no-code tool builder.
Relevance AI is a no-code platform for building what it calls an AI workforce: teams of AI agents that carry out multi-step business tasks on their own rather than just answering questions. It is aimed primarily at the people closest to the work, ops, sales, and support teams and subject-matter experts, who can design and deploy capable agents without relying on developers. Where a chatbot responds, a Relevance agent researches, decides, takes actions in other systems, and remembers what it has done.
Building starts in a few ways: you can describe what you want in plain language and have the platform generate a first-draft agent, clone a pre-built one from a marketplace of templates for roles like business development or research, or assemble one from scratch. Agents are then equipped through a no-code tool builder with concrete actions, sending email, updating a CRM, searching the web, or calling any API, and grounded with knowledge by uploading files or syncing from sources like Google Drive, SharePoint, and Notion so their answers stay accurate.
The platform's signature capability is coordinating several agents into a Workforce. On a visual canvas, you link specialized agents so each owns a step and hands context to the next, turning a proven manual playbook into a digital assembly line: one agent researches a prospect, a second drafts personalized outreach, a third checks it for quality and tone, all triggered by events in your pipeline. Agents keep persistent memory across sessions, can run in bulk against large lists rather than one conversation at a time, and are held to a standard through built-in evaluations that let domain experts define what good output looks like.
Relevance AI is model-agnostic, so agents can use whichever language model best balances quality and cost, and you can bring your own keys. For organizations it adds enterprise controls like role-based access, audit logs, and single sign-on, along with SOC 2 Type II and GDPR compliance and a promise that customer data is not used to train models. Its center of gravity is go-to-market work, automating research, qualification, outreach, and support so a lean team can operate at a scale that once required many more people.
Vendor details
Canonical URL
https://relevanceai.com
Category
Multi-agent platform
Company status
independent
Use cases & customers
Target customers
Deployment options
In practice
Your prospecting is a manual assembly line: research a lead, write outreach, check it, update the CRM. Relevance AI lets you build a Workforce of specialized agents that each own a step and hand off context automatically.
Your ops team wants to automate work but has no developers. Relevance AI's no-code builder lets subject-matter experts describe an agent in plain language, equip it with actions like CRM updates, and deploy it without code.
You need agents to run against a whole list, not one chat at a time, and stay accurate. Relevance AI runs agents in bulk, grounds them in your synced documents, and holds output to standards through built-in evals.
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
Agent Features research report + JSON Feature Rubric |
|
| Workflow Orchestration | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Knowledge Grounding & RAG | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Human Oversight & Guardrails | Partial |
|
Agent Features research report + JSON Feature Rubric |
|
| Security, Identity & Governance | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Observability & Auditability | Partial |
|
Agent Features research report + JSON Feature Rubric |
|
| Memory & State Persistence | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Deployment & Data Residency | Partial |
|
Agent Features research report + JSON Feature Rubric |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Triggers & Channel Coverage | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Model Flexibility & Routing | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Agent Features research report + JSON Feature Rubric |
|
| Testing, Debugging & Optimization | Partial |
|
Agent Features research report + JSON Feature Rubric |
|
| Browser & Computer Use | Unable to verify |
|
Agent Features research report + JSON Feature Rubric |
|
The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
Relevance AI rolled out a multi-feature update introducing the Invent interface for agent creation and adding Google's Gemini 3.5 Flash as a selectable language model across all workflows. The release also updated the platform's MCP server integration to enforce user-level authentication for agent access.
Bears on: Agent capability
View sourceRelevance AI added Confluence Knowledge Sync, project-level public-agent controls, and an Android app, improving enterprise knowledge connectivity, governance, and mobile workforce access.
Bears on: Integrations
View sourceRelevance AI split pricing into Actions and Vendor Credits, enabled BYO API keys, removed markup on vendor costs, and sunset the Business plan.
Bears on: Pricing / packaging
View sourcePricing
Free (200 Actions/mo) · Pro $19/mo annual ($29 monthly)
actions + vendor credits
Included quota
Free: 200 actions/mo + $2 bonus vendor credits
What is public
Relevance AI publishes four public commercial tiers: Free, Pro, Team, and Enterprise. In the captured annual view, Pro is $19/month with 30,000 actions/year and $240 vendor credits/year; Team is $234/month with 84,000 actions/year and $840 vendor credits/year; Enterprise is custom. The feature matrix on the same pricing page shows the same plans as 200 / 2,500 / 7,000 actions per month and 1,000 one-time / 10,000 / 35,000 vendor credits per month. [41]
Billing mechanics
Relevance explicitly split pricing into Actions and Vendor Credits. Docs define an Action as a single run of a tool, even if it fails, and Vendor Credits as pass-through model/tool cost with no markup. On paid plans, customers can BYOK to bypass vendor-credit charges, and paid users can buy top-ups in fixed increments: 1,000 actions or 10,000 vendor credits per purchase. Docs also state that action top-ups roll over to the next cycle and vendor-credit top-ups roll over indefinitely while a subscription remains active. [42]
Cost watchouts
September 2025 restructure split billing into Actions (each tool run) and Vendor Credits (model costs passed through at provider rates); always on agents burn both meters, so costs track activity rather than seats. Bring your own OpenAI or Anthropic keys on paid plans to bypass Vendor Credits entirely, the single biggest cost lever. Unused Vendor Credits roll over while subscribed.
Variable cost rationale
Actions, vendor credits, BYOK, and paid top-ups create a meaningful variable-cost layer beyond the base plan.
Overage / add-ons
Paid top-ups; BYOK on paid plans; rollover behavior published
Sales call required
No, self serve available
Free / trial
Free
Lowest paid plan
Pro $19/mo billed annually ($29 monthly): 2,500 Actions/mo equivalent + $20 Vendor Credits/mo
Commercial notes
Team adds priority support, a larger user footprint, calling/meeting agents, analytics, and coupon-like rollover treatment, while Enterprise adds enterprise triggers, agent evaluations, work-hour controls, multi-org management, enterprise security, a dedicated account manager, and custom implementation. The main caveat is that the pricing page mixes annual, monthly, and vendor-credit units in a way that can confuse buyers, so any website card should separate base plan, actions, and vendor credits into different fields. [10]
Key ambiguities
Price page mixes annual/monthly and vendor-credit unit systems
Cancellation / refund
Rollover rules are public; cancellation/refund not clearly public
Support SLA / resale
Team includes priority support; Enterprise has dedicated account manager and custom implementation
Related vendors
- CrewAI — Open-source multi-agent orchestration framework for building…
- Agent Zero — Open-source multi-agent framework with its own Linux-VM agent,…
- Akka — Enterprise agentic AI platform that builds and runs multi agent…
- Artian — Enterprise multi agent AI platform for financial services: a Planner…
- Databricks Mosaic AI — Databricks Mosaic AI platform for building, deploying, and…
- Dataiku — Enterprise AI and machine learning platform with an agentic layer…
Alternatives to Relevance AI
The closest documented capability profiles to Relevance AI among multi-agent platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Mindra12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
- Distyl AI11.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & AuditabilityRelevance AI vs Distyl AI →
- Rasa12.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
- SimplAI12.5 / 14Adds documented Browser & Computer Use
- Akka12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
- CrewAI13.0 / 14Adds documented Browser & Computer UseRelevance AI vs CrewAI →
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded