Skip to content

Autopoetic Documentation

Autopoetic is a multiperspective subjective AI conversation system. Every message you send is simultaneously evaluated by multiple internal perspectives — a cynic, an empiricist, a speculator, an empath — and their collective influence shapes a steering signal injected into the model while it writes. The result is an assistant with a persistent, evolving point of view instead of neutral, generic output.

What you can do

  • Chat with an agent that has a point of view. Watch each perspective's take stream live before the synthesized response arrives, explore how the perspectives weighted the answer, and see the "subjective shape" of every message rendered in 3D. Start with what Autopoetic is.
  • Build a knowledge repository automatically. Every conversation teaches Autopoetic about the people, places, and things you discuss — entities, relationships, and a hash-chained event log you can explore as an interactive graph, complete with a time slider. See the knowledge repository.
  • Orchestrate your own agents and reviews. Workflow templates compose steps that call out to your systems via webhooks, wait (indefinitely, for free) for your agents to respond, and gate work behind peer review whose confidence is computed by Autopoetic's decision engine. See workflows.
  • Use it programmatically. The Responses API generates agent responses for your code; the platform REST API manages conversations, knowledge, projects, and workflows as data; the MCP server drives the same from LLM clients. See the API overview.

Where to go next