Head-to-head

AgentWorks vs Relevance AI

EU AI Act compliance, multi-LLM choice, and transparent € pricing — compared on the points that actually move a buying decision.

Last verified: 2026-05-05

TL;DR

AgentWorks and Relevance AI both ship AI agents and tools that automate sales, marketing, and operations work. Relevance AI is the more mature US/AU self-serve product with a polished tool builder. AgentWorks differentiates on EU AI Act compliance, EU data residency, transparent per-token € pricing, and self-hosted deployment on Azure, AWS, GCP, or IBM Cloud.

Feature-by-feature comparison

FeatureAgentWorksRelevance AIEdge
EU AI Act complianceBuilt in: per-agent risk classification, audit log, human-in-the-loopNot advertised as a Relevance AI feature
GDPR + EU data residencyEU regions on managed cloud or self-hosted on Azure/AWS/GCP/IBMHosted in US/AU; EU data residency not advertised
PII masking before LLMGateway-layer redaction across all modelsNot advertised
LLM choice in one workspaceOpenAI, Anthropic, Google, Mistral; switch per turnOpenAI primary; Anthropic and others available per node
Free tierStarter: free with €5 token creditFree tier with limited credits
Entry paid pricingPro €49 / month · pay-as-you-go walletTeam ~$199 / month (USD)
Pricing currencyEUR; transparent per-token pass-throughUSD; credit-pack model
Pricing transparencyLive € wallet; per-token spend visible per turnCredit packs that map opaquely to model usage
AI agent templates200+ templates across marketing, sales, support, HR, finance, opsStrong template library; sales/marketing focused
Tool builderPipelines + integrations; custom agents on EnterpriseVisual tool builder is a core strength
Multi-agent pipelinesVisual chain of agents; daily/weekly schedules on Pro+Multi-agent flows via Tools/Agents combinations
Knowledge base + RAGNative; ground any agent on documents and URLsNative knowledge bases, vector indexing
Human-in-the-loopPer-agent and per-pipeline; required on EU AI Act high-risk stepsApproval steps configurable per workflow
Audit logEvery chat turn, agent run, tool call — exportable JSON/CSVRun logs per workflow; export availability not documented
Self-hosted / on-premSelf-host on Azure, AWS, GCP, or IBM Cloud (Enterprise)SaaS only

When Relevance AI is the better choice

Relevance AI has a more mature self-serve product if you are a US- or AU-based team optimizing for time-to-first-agent.

  • You operate primarily in the US or APAC and do not need EU AI Act or EU residency.
  • You want to evaluate today via instant self-serve sign-up, rather than a contact-sales onboarding.
  • Your team has invested in the Relevance "tools" abstraction and wants to keep that workflow.
  • You are comfortable with USD pricing and credit-pack billing instead of per-token € transparency.
  • You don't need self-hosted deployment.

When AgentWorks is the better choice

AgentWorks fits European teams that need governance and currency native to their procurement reality.

  • You must comply with the EU AI Act and need built-in risk classification, audit log, and human-in-the-loop.
  • You require EU data residency on managed cloud or want self-hosted on Azure / AWS / GCP / IBM.
  • You need PII redaction at the gateway layer before any LLM sees data.
  • You want transparent per-token € pricing with a live wallet — not USD credit packs.
  • You serve regulated industries (finance, healthcare, public sector, legal) where US-only hosting is a blocker.

Migrating from Relevance AI to AgentWorks

A practical six-step path. Run both systems in parallel for one week before cutting over.

  1. 1Export your Relevance "agents" and "tools" definitions to JSON; document each one's data sources and triggers.
  2. 2Map each Relevance agent to the closest AgentWorks template (32+); flag the rest for AgentWorks AI-engineer custom builds.
  3. 3Re-index Relevance knowledge bases as AgentWorks knowledge bases (one-to-one is the cleanest starting point).
  4. 4Re-implement triggers: Relevance scheduled runs become AgentWorks scheduled runs (Pro+); webhooks map directly.
  5. 5Apply per-agent EU AI Act risk classification and turn on human-in-the-loop on customer-impacting steps.
  6. 6Run both systems in parallel for one to two weeks, comparing outputs and audit logs before redirecting traffic.
Request test workspaceSee AgentWorks AI agents

Sources for Relevance AI facts: https://relevanceai.com, https://relevanceai.com/pricing. Reviewed 2026-05-05. We update this page when Relevance AI Pty Ltd ships material changes.

FAQ

AgentWorks vs Relevance AI — common questions

Is AgentWorks a Relevance AI alternative for European businesses?
Yes. AgentWorks is purpose-built for EU teams: EU AI Act compliance, GDPR, EU data residency, PII masking before any LLM, and transparent per-token € pricing. Relevance AI is hosted in the US/AU and bills in USD with credit packs.
How does AgentWorks pricing compare to Relevance AI?
Relevance AI uses USD credit packs that map opaquely to model usage; the entry paid tier is around $199/month. AgentWorks Pro is €49/month with a pay-as-you-go token wallet and per-token pass-through pricing on a live € wallet — no model markup, no credit-to-call mapping to decode.
Can I run multi-LLM workflows in AgentWorks like Relevance AI?
Yes. AgentWorks runs OpenAI, Anthropic, Google, and Mistral in one workspace; you can switch model per turn or per agent. Relevance AI supports OpenAI as the primary engine with Anthropic and others available per node.
Can AgentWorks be self-hosted like Relevance AI?
Self-hosted is an Enterprise feature on AgentWorks (Microsoft Azure, AWS, Google Cloud, or IBM Cloud — including EU-only configurations). Relevance AI is SaaS only.
Is Relevance AI EU AI Act compliant?
Relevance AI has not advertised the platform as EU AI Act compliant; the burden is on the deploying organization to design risk classification, audit logging, and human-in-the-loop for high-risk decisions. AgentWorks ships these as core platform features.
Can I migrate my Relevance agents and tools to AgentWorks?
Yes. The migration path is: export Relevance agent and tool definitions, map to AgentWorks templates (200+ pre-built), build custom agents for anything specific, re-index knowledge bases, re-implement triggers as AgentWorks schedules or webhooks, and run both systems in parallel for a week before switching.