Skip to main content
Your agent reads each tool’s own description when it connects, which says exactly what the tool takes and returns. This page is the overview. For what a context, a project, a round and a synthesis are, see How Semilattice works.

Your context and user models

  • get_context: read the context your simulations are planned against.
  • list_contexts: list the contexts you can use, yours and your organisation’s.
  • create_context: write a new context with you, from what you tell it.
  • list_user_models: list the user models you can use, with their accuracy, and which are your organisation’s own.

Projects and rounds

  • create_project: start a project, optionally with a name and a context.
  • list_projects: list your projects, newest first, to find one to add to.
  • get_project: read a project: its rounds, what each one tests, its simulations and its synthesis.
  • rename_project: rename a project.
  • start_round: start a new round in a project.
  • rename_round: rename a round.
  • attach_artefact: attach the document, page or file a round tests.
  • read_artefact: read the text of a document attached to a round, for example one uploaded in the app.
  • regenerate_synthesis: write a round’s synthesis again from every simulation in it. This replaces any edits made to it.

Simulations

  • list_simulation_schema: list the two kinds of simulation, their goals, and what each goal needs.
  • create_simulation: draft a simulation. Semilattice writes its questions or task in the background.
  • get_simulation: read a simulation’s status, plan and results.
  • update_simulation_plan: change a planned simulation: edit, add or delete questions, or change a journey’s task.
  • run_simulation: run a planned simulation, after you have confirmed it.
  • list_simulations: list past simulations, to build on what you already know.
  • delete_simulation: delete a simulation, after you have confirmed it.
  • share_simulation: make a simulation’s results viewable by anyone with the link.

Reading results in depth

  • read_respondent_answers: read how individual simulated users answered.
  • read_journey_session: read one simulated user’s journey in full, step by step.
  • read_planner_conversation: read what you discussed with the agent in the app on a project, so your agent knows what was decided there.
read_artefact, read_respondent_answers, read_journey_session and read_planner_conversation work over MCP only. They are not part of the API.