Add LLM agent participants to experiment

LLM agents can join experiments as participants. Each agent participant can have its own individual prompt, but will otherwise run through an experiment in the same way as a human would.

Preparing an Experiment for Agent Participants

You can add agent participants to any experiment, as long as you have an API key configured for your chosen provider. No other experiment-level config is necessary. However, we recommend setting up your experiments with an eye for how agent participants will see each stage.

Experiment info: Agent participants will see any text in the experiment info stage, but they won’t see the contents of a linked Youtube video.

Stage metadata: This is where agent participants will see what each stage is about, so consider how clear your stage names and instructions are. For details on what each stage displays to agents, see the stage display table.

Progress settings: Agent participants may move through your experiment faster than you expect, or get stuck on chat stages where you don’t expect. Consider checking “Wait for all active participants to reach this stage before allowing progression” before discussion stages, to prevent agents from moving on from a chat before humans arrive. Also consider setting a chat time limit, or describing specific goals for each chat stage.

Profile settings: If you select the option to assign random animal profiles to participants, be aware that the chosen animal could influence the agent’s behavior! The agent will be reminded in its profile prompt that it is a human and not actually the given animal, so most models shouldn’t try to respond as though they were the animal, but we can’t rule out subtler effects.

Adding Agent Participants to a Cohort

To add agent participants to a cohort:

  • From the experiment overview screen, hit the icon to add a participant, and select “Add agent participant” from the menu.
  • From the cohort management screen, click the icon at the top of the “Agent participants” section, which should appear between human participants and agent mediators.

You’ll see a window to configure the agent: you’ll need to select a model for the agent to use, and you can optionally add a prompt context to give to the agent. The prompt context may be useful for e.g. giving different personalities or instructions to different agents. These settings will apply for that agent across all experiment stages.

Generating and Enhancing Personas

To help create diverse and high-fidelity personas, the configuration window includes three AI-assisted tools:

  • 🪄 Generate: Creates a full character sketch (~200–250 words) covering demographics, Big Five personality traits, values, cognitive style, and communication style. Uses a dry, factual, dossier-style tone. If you have already started writing a persona (e.g., “Your name is Joe”), Generate will expand it into a complete sketch while preserving what you wrote. Each generation samples a unique combination of age, education level, pronouns, setting, and verbosity to ensure diversity.
  • ✨ Enhance: Appends 1–2 short, concrete episodic memories or personal experiences to the existing sketch (e.g., a past job conflict or a life event). These “memories” give the agent something specific to draw on during conversation, making it feel more like a real person and less like an LLM. Only available when there is existing text.
  • 🔄 Refresh: Erases the current persona and generates a brand new one from scratch. Disabled when the field is empty.

Note: You must have a model selected and a valid API key configured to use these features.

Supported Stages

  • Terms of Service
  • Info
  • Set Profile: If allowed to set their profile, agents will usually choose based on their prompt context.
  • Survey
  • Group Chat
  • Private Chat
  • Survey / Survey Per Participant
  • Ranking
  • Asset Allocation
  • Stock Info

Not currently supported:

  • Role assignment
  • Comprehension check
  • Payout
  • Reveal

For details on how a stage implements agent participants, see Add stage.

Debugging Agent Participants

We recommend always doing test runs with agent participants before launching your experiment. To see the details of an agent participant’s response, click the “LLM Logs” button on the left sidebar. Even if the agent is responding as you expect, we recommend reviewing the prompts sent to the agent at each stage, at least once. This will help you confirm that the agent is seeing exactly the information it should be.