Compare · checked 5 May 2026
AgentWorks vs Relevance AI
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 hosting for the platform and every model, approvals and budgets, EU AI Act tooling, and euro pricing with costs shown before anything runs.
Side by side
| AgentWorks | Relevance AI | |
|---|---|---|
| EU AI Act compliance | Approvals on every plan; risk classification per workflow, AI-system register and audit log on Business | Not advertised as a Relevance AI feature |
| GDPR + EU data residency | Platform on our own servers in Germany; all 22 models EU-hosted; no self-host | Hosted in US/AU; EU data residency not advertised |
| PII masking before LLM | Optional PII detection and anonymisation before the model | Not advertised |
| LLM choice in one workspace | OpenAI, Anthropic, Google, Mistral; switch per turn | OpenAI primary; Anthropic and others available per node |
| Free tier | Free: €0 for up to 2 people, €5 starter balance once | Free tier with limited credits |
| Entry paid pricing | Free for 2 people; Business €29 / seat / month incl. €10 usage | Team ~$199 / month (USD) |
| Pricing currency | EUR; price of each model and paid action shown before it runs | USD; credit-pack model |
| Pricing transparency | Workspace balance; spend per person and per workflow visible | Credit packs that map opaquely to model usage |
| AI agent templates | 66 agent templates across 11 categories | Strong template library; sales/marketing focused |
| Tool builder | Workflows + 40 apps; build agents yourself on every plan | Visual tool builder is a core strength |
| Workflows with several agents | Visual chain of agents; daily/weekly schedules on Business | Multi-agent flows via Tools/Agents combinations |
| Knowledge base + RAG | Native; ground any agent on documents and URLs | Native knowledge bases, vector indexing |
| Human-in-the-loop | Approval before any change by an agent; approval step in workflows | Approval steps configurable per workflow |
| Audit log | Approval decisions, runs with cost, audit log (Business) | Run logs per workflow; export availability not documented |
| Self-hosted / on-prem | No self-host: managed in the EU (own servers in Germany) | SaaS only |
A tick marks the stronger side for that row. Relevance AI facts from their public pages, checked 5 May 2026.
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.
- 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 the platform and every model to be hosted in the EU.
- You need optional PII detection before a model sees data.
- You want prices in euros shown before anything runs, not USD credit packs.
- You serve regulated industries (finance, healthcare, public sector, legal) where US-only hosting is a blocker.
Switching from Relevance AI
- 01Export your Relevance "agents" and "tools" definitions to JSON; document each one's data sources and triggers.
- 02Map each Relevance agent to the closest AgentWorks template (66 in the app); build the rest with the agent builder.
- 03Re-index Relevance knowledge bases as AgentWorks knowledge bases (one-to-one is the cleanest starting point).
- 04Re-implement triggers: Relevance scheduled runs become AgentWorks scheduled runs (Pro+); webhooks map directly.
- 05Apply EU AI Act risk classification per workflow and turn on human-in-the-loop on customer-impacting steps.
- 06Run both systems in parallel for one to two weeks, comparing outputs and audit logs before redirecting traffic.
Questions
AgentWorks or Relevance AI?
Sources
- https://relevanceai.com
- https://relevanceai.com/pricing
Yes. AgentWorks is purpose-built for EU teams: EU AI Act compliance, GDPR, EU data residency, optional PII detection before the model, and euro pricing with costs shown before anything runs. Relevance AI is hosted in the US/AU and bills in USD with credit packs.