Relevance AI

What is Relevance AI?

Relevance AI is a no-code platform for building and deploying "an AI workforce", specialist agents, and teams of agents, that run business workflows across sales, marketing, operations and support. You compose agents from tools, connect them to your stack over 2,000+ integrations and MCP, and orchestrate several into a coordinated "workforce." It ships the surrounding infrastructure too: an LLM router that picks a cheap model that still passes quality bars, an evals framework, human-in-the-loop approvals, tracing and access controls. Its flagship sales agent, Bosh, is a custom-onboarded BDR. Founded in 2020 in Sydney, Australia by Daniel Vassilev, Jacky Koh and Daniel Palmer, the company has raised $37M total, most recently a $24M Series B led by Bessemer Venture Partners in May 2025, with Insight Partners, King River Capital and Peak XV also participating, and opened a San Francisco office as part of that expansion.

What does Relevance AI do?

You build an agent in a visual builder by giving it a role, a set of tools (native integrations, custom API actions, or MCP servers) and instructions, then trigger it on a schedule, a webhook, or another agent’s output. Multiple agents combine into a "workforce" that hands work between specialists, a researcher enriches a lead, a writer drafts the outreach, a scheduler books the meeting. Underneath, Relevance routes each step to the cheapest LLM (across Claude, GPT and Gemini) that still passes your evals, so you’re not locked to one model or paying frontier prices for simple steps. It provides job queues, tracing, human approval gates, RBAC and SSO for running agents in production. Pricing uses a dual meter: "Actions" measure platform usage while "Vendor Credits" pay for the underlying AI compute, and paid tiers let you bring your own OpenAI, Anthropic or Google keys to bypass credit consumption. A free self-serve tier lets you build and test before upgrading. At the top end, Bosh is a fully-managed BDR agent that prospects, researches, writes personalised cold email, handles two-way replies, logs to your CRM and books meetings, onboarded to your company over several weeks rather than switched on self-serve.

Key features

• No-code agent + tool builder: Compose agents from tools and instructions in a visual builder, or extend with custom API actions and MCP.
• Multi-agent "workforces": Orchestrate several specialist agents that hand work between each other on one workflow.
• Cost-optimising LLM router: Routes each step to the cheapest model (Claude, GPT, Gemini) that still passes your quality evals.
• Production infrastructure: Built-in evals, tracing, human-in-the-loop approvals, RBAC and SSO for running agents live.

What are Relevance AI's use cases?

• Autonomous prospecting: The Bosh BDR agent finds ICP-matched contacts, researches them, sends personalised cold email and books meetings.
• Ops automation: A workforce enriches inbound leads, updates the CRM and drafts follow-ups without a human touching each record.

What does Relevance AI integrate with?

• Salesforce & HubSpot (CRM)
• Slack & Gmail
• LinkedIn & Apollo
• 2,000+ apps + MCP servers
• Model providers — Anthropic, OpenAI, Google

Why use Relevance AI?

• Build coordinated multi-agent teams, not just single bots, without code.
• The LLM router cuts cost by matching each step to the cheapest capable model.
• Enterprise-grade controls, evals, tracing, approvals, RBAC/SSO, for running agents in production.

Pros & cons

Relevance AI pricing

• FreeFree
• ProFrom $19 / /month
• TeamFrom $234 / /month
• EnterpriseCustom

See current pricing on relevanceai.com ↗Compare Relevance AI alternatives →

Relevance AI review

Relevance AI is one of the more serious "agent platform" plays: it’s built from the ground up for multi-agent workforces, with the unglamorous production plumbing, an LLM router, evals, tracing, approvals and RBAC/SSO, that separates a demo from something you’d trust with live pipeline. The cost-optimising router and bring-your-own-keys option are genuinely useful for keeping AI spend sane. The tradeoffs are real: the dual meter of Actions plus Vendor Credits is easy to misjudge on AI-heavy agents, the flagship Bosh BDR is a custom enterprise onboarding rather than a self-serve click, and the public pricing page now leads with "talk to sales." Pick Relevance AI if you want to build coordinated agent teams with enterprise-grade control and will invest in learning it; skip it if you need a single quick bot, open-source self-hosting, or perfectly predictable flat pricing.

A production-grade multi-agent platform, strong orchestration and cost control, but priced by a dual meter that rewards careful budgeting.

Frequently asked questions