Rasa

Flows call tools from MCP servers directly with a call step and input and output mappings, ReAct sub agents pick MCP tools at runtime, and a custom actions server built on the Rasa SDK reaches any backend API. No prebuilt connector catalog is published beyond channel connectors.

Sourcerasa.com/docs/pro/build/mcp-integration.mdread 2026-09-27

Flows define business processes as steps with conditions, links and calls to other flows, and Rasa acts as the orchestrator for sub agents inside them: built in ReAct sub agents with MCP tools and external agents over A2A, with shared context, state checks, resume after interruption and up to three retries with backoff.

Sourcerasa.com/docs/reference/config/agents/overview-agents.mdread 2026-09-27

Enterprise search indexes the customer's documents in FAISS, Milvus or Qdrant, or a custom retriever, and the enterprise search policy retrieves relevant passages when it detects a knowledge question and has the model answer from them.

Sourcerasa.com/docs/pro/build/configuring-enterprise-search.mdread 2026-09-27

A human handoff conversation pattern passes the conversation to a person, and CALM limits the model to developer defined flows so it cannot invent steps, but no surface where a reviewer approves or rejects an agent action before it runs is documented; the live agent side of a handoff sits in the customer's contact center.

Sourcerasa.com/docs/learn/concepts/conversation-patterns.mdread 2026-09-27

Studio ships SSO and role based access, set up through Keycloak, the Rasa Pro API takes token or JWT auth with role based access, and Pro adds PII management and Vault secrets. No attestation is published: the security page says controls are aligned with ISO 27002 and names no SOC 2 or ISO certificate, and a SOC 2 claim appears only in third party writeups, not on rasa.com.

Sourcerasa.com/pricingread 2026-09-27

Tracing records the assistant's own processing, LLM calls with prompts, inputs, outputs and token usage, generated commands, flow transitions and custom actions, exported to Jaeger, an OTEL collector or Langfuse; an analytics pipeline streams conversation events through Kafka to a warehouse, and Studio adds a conversation view.

Sourcerasa.com/docs/pro/improve/tracing.mdread 2026-09-27

Slots are the documented memory, key value state the assistant collects within a conversation. Tracker stores keep every conversation, and user scoped conversations let the API list all trackers for one user, but that is the conversation record, not a memory layer with a stated scope and lifetime that the assistant reads across sessions.

Sourcerasa.com/docs/pro/build/assistant-memory.mdread 2026-09-27

The paid platform deploys self managed on premises or in a private cloud, or as a managed service, with Kubernetes deployment through Helm and deployment playbooks for AWS, Azure and GCP, and the finance page adds hybrid setups; the free Developer Edition runs locally or in production.

Sourcerasa.com/pricingread 2026-09-27

Project templates such as tutorial and calm scaffold a starter assistant through rasa init, and default conversation patterns come built in, but no catalog of ready to use agents is published.

Sourcerasa.com/docs/pro/tutorial.mdread 2026-09-27

An HTTP endpoint lets an outside system inject an intent into a conversation in place of a user message, after which the assistant runs its response and sends it to a named output channel, and a ReminderScheduled event lets the assistant schedule itself to act later; these are the autonomous seams. Most work arrives from people on the documented messaging and voice channels (web, Slack, Telegram, Messenger, Twilio, Genesys Cloud, AudioCodes, Jambonz, Vonage and others).

Sourcerasa.com/docs/reference/api/pro/http-api/tracker/inject-an-intent-into-a-conversation.mdread 2026-09-27

The customer configures model deployments in endpoints.yml, including Azure and self hosted endpoints such as vLLM, Llama.cpp and Ollama, and a multi LLM router spreads requests by shuffle, least busy, latency, cost or usage with failover to the next deployment.

Sourcerasa.com/docs/pro/deploy/llm-routing.mdread 2026-09-27

The Rasa Pro REST API covers status, models, conversation trackers and message injection with token or JWT auth, the Rasa SDK builds custom actions, and an A2A server exposes the assistant to outside orchestrators with an agent card at /.well-known/agent-card.json and bearer JWT auth.

Sourcerasa.com/docs/reference/api/pro/rasa-pro-rest-api.mdread 2026-09-27

End to end tests assert each step of scripted conversations with coverage reports and are meant for CI, and evals drive simulated users through YAML scenarios scored by an LLM judge plus deterministic assertions; the docs say evals are not yet suited to blocking CI.

Sourcerasa.com/docs/reference/testing/evals/overview.mdread 2026-09-27

The product covers channels, flows, sub agents, MCP tools and APIs, with no browser or computer use capability documented; any browser work would come from an outside MCP server or A2A agent.

Sourcerasa.com/docs/llms.txtread 2026-09-27