Recommendations you can defend.
Compose AI agents and workflows into reusable decision engines, then converse with them to decide faster. Every answer shows exactly how it was reached — which agents ran, what context they used, and why. See how it works, or read the research.
Talk to Rico. No account, no setup.
Rico is the conversational front door to your engines. Tell it what you need to decide and it will design the engine with you — which agent does the reasoning, what its goals and constraints are, how the workflow runs, and what the traceable recommendation contains.
- The real Rico, running the real platform — read-only for the demo.
- Nothing is collected about you. No email, no connections, no data.
- When you're ready, what you designed here carries into your account.
-
Hi — I'm Rico. Ask me anything about building a decision engine, or tap one of these to start.
Agents, workflows, engines — and the policy-gated component library they're built from.
Explore the platform →The case for traceable AI decisioning, and how we measure whether a recommendation holds up.
Read the research →Drive engines from the terminal, stream activity in, and connect any MCP tool.
Build on Recommengine →
Ready to build your decision engine?
Compose agents, converse with Rico, and decide with confidence — traceable and ownership-safe. Start in minutes.