# Relevance AI — Platform for building and running specialist business agents and multi-agent workforces. > Source: The Agents Index — https://theagentsindex.com/relevance-ai (structured, researched, re-verified) > Facts last verified: 2026-09-22 Relevance AI is a hosted platform for building specialist AI agents and multi-agent "workforces" that run business tasks across sales, customer success, marketing, HR and support. Work is metered in Actions and Vendor Credits. | Fact | Value | | --- | --- | | Website | https://relevanceai.com | | Price | from $29/month billed monthly, $19/month billed annually | | Free tier | No | The Free plan is retired and cannot be selected at signup; existing Free organisations keep access. Entry is the paid Pro plan at $29/month month-to-month ($19/month billed annually), which carries 2,500 Actions and $20 Vendor Credits per month. ## What it does **Writes code** · Partly — Not a coding agent, but the built-in Website Builder agent in Chat generates a complete website from a text description; there is no general source-authoring product. > Website Builder is a built-in Agent in Chat that generates complete websites from a text prompt or description. > — https://relevanceai.com/docs/get-started/chat/chat-agents/website-builder · Website Builder page, opening paragraph **Done-for-you service** · Partly — You buy software, but the vendor also puts an embedded deployment team on the first build and then hands the work back to your own team. > An embedded deployment team gets you live, then trains your team to build without us. > — https://relevanceai.com/ · Section "Drive ROI in six weeks or less: with your first team of agents", subheading ## How much it does unattended **Runs autonomously** · Yes — Agent-to-tool and agent-to-agent connections can be set to Auto Run so actions execute with no human in the loop, with an optional cap on automatic executions. > In this mode, the agent will execute actions automatically without requiring approval. > — https://relevanceai.com/docs/build/workforces/workforce-features/approvals-and-escalations · Setting Up Approval Modes, "Auto Run" subsection **Multi-agent** · Yes — Workforce is a visual canvas for wiring several specialist agents together, and Workforces are unlimited on every published plan tier. > Workforce transforms how your agents collaborate by providing a visual canvas where you can design, connect, and monitor teams of specialised agents. > — https://relevanceai.com/docs/llms.txt · Documentation index, Workforces entry description **Agent permissions** · Yes — Each connection carries one of three approval behaviours - Auto Run, Approval Required, or Let Agent Decide - so the autonomy boundary is set per tool, not per product. > This mode forces the agent to seek explicit approval before executing an action. > — https://relevanceai.com/docs/build/workforces/workforce-features/approvals-and-escalations · Setting Up Approval Modes, "Approval Required" subsection ## Which models it runs on **Claude** · Yes — Anthropic Claude models run through Anthropic's API with no data logging, and agent settings expose Claude-specific thinking type and effort controls. > Anthropic models are offered through their API, and once again, no data is stored or trained on during this process. > — https://relevanceai.com/docs/admin/security · LLM models section, paragraph on Anthropic models **GPT** · Yes — The vendor's own model/vendor table lists GPT supplied by OpenAI with no logging and no training, available when you supply no API key of your own. > | GPT | OpenAI | No | No | Yes | > — https://relevanceai.com/docs/admin/security · LLM models section, model/vendor table, GPT row **Open models** · Yes — Open-weight models are reachable through the OpenRouter integration, and the vendor says it also hosts open-source models such as LLaMA in its own cloud accounts. > OpenRouter models are a unified access point to a wide variety of open models like Meta's LLaMA family, Google Gemini models, and others. > — https://relevanceai.com/docs/integrations/llm-integrations/openrouter · OpenRouter LLM models page, opening line **Model choice** · Yes — You pick the model per agent, set a fallback model from another provider, and the feature table marks "Bring your own LLM" available on every published tier. > | **Bring your own LLM** | ✓ | ✓ | ✓ | > — https://relevanceai.com/docs/get-started/pricing · Complete feature comparison, AI management table, "Bring your own LLM" row ## Where you use it **In your editor** · Partly — There is no in-editor coding assistant; instead the MCP server can be added to Cursor, VS Code, Windsurf or Zed to build and run your Relevance agents from the editor. > The Relevance AI MCP server gives any MCP-compatible AI client direct access to your agents, tools, and knowledge. > — https://relevanceai.com/docs/integrations/mcp/mcp-server · MCP server page, opening paragraph above the supported-clients list **On the command line** · Partly — No first-party CLI of its own, but a published Claude Code plugin bundles the MCP server and skills so agents can be built and managed from a terminal. > Use the Relevance AI Claude Code plugin to build and manage your agents directly from your terminal. > — https://relevanceai.com/docs/integrations/mcp/claude-code · Claude Code plugin page, page subtitle **In a browser** · Yes — The product is a hosted web application, with a separate Chat interface documented for desktop, mobile and browser use. > Use AI Agents and Workforces in a chat interface on desktop, mobile, and browser > — https://relevanceai.com/docs/llms.txt · Documentation index, Chat entry description _Not established: In your pipeline_ ## Whose machine it runs on **Self-hosted** · No — Hosted multi-tenant service only; customer data is logically separated within the vendor's cloud and a single-tenant option is described as still unbuilt. > Relevance operates on a multi-tenanted architecture where customer data is logically separated ... Single-tenant options are currently in the works > — https://relevanceai.com/docs/admin/security · Data residency & storage, "Tenant isolation" bullet list _Not established: Open source_ ## What it costs to run **How it meters** · Yes — Two meters plus seats: an Action is one tool run, Vendor Credits are the pass-through model and tool cost, and each plan caps how many build users it carries. > An Action is a single run of a Tool. Each time a tool runs, it counts as an action — whether it's a simple task like sending one email or running a complex workflow with many steps. > — https://relevanceai.com/docs/admin/subscriptions/plans · Understanding Actions, first paragraph **Free tier** · No — The standing $0 plan has been withdrawn: existing Free organisations keep access but no new signup can choose it, so the cheapest way in is the paid Pro tier. > The Free plan is retired and closed to new signups. Organizations already on Free keep their existing access and can upgrade at any time. > — https://relevanceai.com/docs/get-started/pricing · Note directly beneath the Pro/Team/Enterprise plan cards **API access** · Yes — A documented SDK with sk- project API keys for server code plus scoped embed keys for browsers, and agents can additionally be triggered by direct HTTP requests. > API keys are available in the project settings on the dashboard. They follow the `sk-...` format and grant unrestricted access to every resource in the project. > — https://relevanceai.com/docs/sdk/authentication · API key authentication section, first paragraph **MCP server** · Yes — A hosted MCP server at mcp.relevanceai.com lets another agent list and run your agents, with OAuth access bounded server-side by the caller's project role. > The Relevance AI MCP server gives any MCP-compatible AI client direct access to your agents, tools, and knowledge. > — https://relevanceai.com/docs/integrations/mcp/mcp-server · MCP server page, opening paragraph **Bring your own key** · Yes — Bringing your own model keys is optional on every plan and bypasses Vendor Credit metering entirely, with the vendor's credits left as a fallback. > To bypass Vendor Credits entirely, you can bring your own API keys. BYOK is optional on every plan — it lets you skip Vendor Credits while still having them available as a fallback. > — https://relevanceai.com/docs/admin/subscriptions/plans · Understanding Vendor Credits, closing paragraph ## Buying it for a team **A company can buy it** · Yes — Paid subscriptions attach to the Organization rather than a person, and Enterprise buyers can request further organisations under one contract. > Yes, for Pro and Team plans. Subscriptions are applied at the Organization level, not to individual users or projects. > — https://relevanceai.com/docs/get-started/pricing · FAQs, "Is my subscription applied at an organization level?" answer **Seat model** · Yes — Seats are split into build users and end users with hard ceilings per tier - two builders on Pro, five builders plus 45 end users on Team, unlimited only on Enterprise. > | **[Build Users](/docs/admin/project-management/add-members)** | 2 | 5 | Unlimited | > — https://relevanceai.com/docs/get-started/pricing · Complete feature comparison, Platform table, Build Users row **Pooled budget** · Yes — One balance for the whole organisation: everybody shares the plan's Actions and Vendor Credits rather than holding a personal allowance. > Everyone in the Organization shares the plan's Actions, Vendor Credits, and feature access. > — https://relevanceai.com/docs/get-started/pricing · FAQs, "Is my subscription applied at an organization level?" answer **Admin controls** · Partly — Per-connection approval gates and spend/usage limits are available broadly, but role-based and fine-grained access control are gated to Enterprise on the vendor's own tier table. > | **[RBAC](/docs/enterprise/rbac)** | ✗ | ✗ | ✓ | > — https://relevanceai.com/docs/get-started/pricing · Complete feature comparison, Security & compliance table, RBAC row **Audit log** · Partly — Audit logging exists but only on Enterprise, where events and execution traces are streamed out over OpenTelemetry; Pro and Team are marked as not having it. > | **[Audit Logs](/docs/enterprise/streaming-events)** | ✗ | ✗ | ✓ | > — https://relevanceai.com/docs/get-started/pricing · Complete feature comparison, Security & compliance table, Audit Logs row **Single sign-on** · Partly — SAML 2.0 and OIDC single sign-on is documented but reserved for Enterprise; the two self-serve tiers are marked without it on the vendor's comparison table. > | **[SSO (SAML)](/docs/enterprise/sso-setup)** | ✗ | ✗ | ✓ | > — https://relevanceai.com/docs/get-started/pricing · Complete feature comparison, Security & compliance table, SSO (SAML) row ## What happens to your code **Opt out of training** · Yes — Nothing to opt out of by default: the vendor states it does not train on customer data absent a specific partnership agreement, and metadata is excluded from training. > We do not use your data to train our models or improve our services unless you have a specific partnership agreement with us > — https://relevanceai.com/docs/admin/security · Data ownership and privacy, "You own your data" bullet list **Data residency** · Yes — Three regions are offered and chosen at signup - N. Virginia, London or Sydney - but the vendor warns the choice is fixed once the organisation exists. > Data is stored in Australia, the US, or the EU/UK, based on your selection at signup. > — https://relevanceai.com/docs/admin/security · Data residency & storage, "Choose your region" subsection **Getting out** · Yes — Data exports in CSV, Excel or JSON are available at any time, and unused Vendor Credits roll over indefinitely while the subscription stays active rather than expiring. > You can export your data at any time in standard formats (CSV, Excel, JSON) > — https://relevanceai.com/docs/admin/security · Data ownership and privacy, "Data export and deletion" bullet list **Certifications** · Yes — SOC 2 Type II and GDPR are claimed on every tier with third-party assessment reports offered to Enterprise under NDA; no ISO 27001 certification is claimed anywhere read. > Relevance AI is SOC2 Type II compliant, and we operate in a multi-region environment. > — https://relevanceai.com/docs/admin/security · Security certifications and compliance, "SOC2 Type II compliant" subsection ## Provenance Every fact above comes from the vendor. Nothing here is independently corroborated yet. ## Coverage elsewhere Pages about this product that the vendor does not control. The label states how independent each one is. | Source | Kind | Read | | --- | --- | --- | | techcrunch.com | Independent source | 2026-08-23 | ## What changed - 2026-09-22 — Capabilities · Commercial terms · Free tier - 2026-09-02 — Capabilities · Commercial terms · Free tier - 2026-08-31 — Capabilities · Commercial terms · Free tier · Price - 2026-08-23 — Alternatives · One-liner · Summary - 2026-08-16 — One-liner · Summary ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Relevance AI, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth. Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.