Agentic-Ai
Guardrails
A layered guardrail system around every agent run, from deterministic checks to policy agents, with violations your process or case can handle.
Open LLM provider support
Run agents on any model, configured centrally and switchable at runtime, from hosted Anthropic and OpenAI to self-hosted and private models.
MCP in both directions
Consume tools from remote MCP servers, and expose Flowable itself as an MCP server.
Document agents
Document agents gain fallback models, structured inputs and in-Design testing.
AI-assisted modeling
Draft prompts, services, scripts and whole apps with AI help inside Design.
Agent evaluators
Automatically score the quality of what your agents produce, on every run, so you can measure and track agent quality over time.
Agent observability
See exactly what every agent did, with instance views, timelines and operations dashboards.