CAMEL Role-Playing
Instantiate two agents as AI-User and AI-Assistant with inception prompts — they converse autonomously until the task is solved or the turn budget runs out.
Intent & Description
🎯 Intent
Have two agents role-play a user-assistant interaction to autonomously complete a task neither could solve alone.
📋 Context
You want an autonomous system to carry out a task that would naturally unfold as collaboration between a goal-setter and an executor — a product owner working with a developer, an instructor working with a learner. There’s no real user in the loop; both sides need to be played by agents, and the work has to converge through their interaction.
💡 Solution
Use inception prompts to instantiate two agents (AI-User and AI-Assistant) with their roles fixed and the task specified. They converse until the task is completed or the turn budget is exhausted. The output is the final assistant message; the conversation log is the debugging artifact.
Real-world Use Case
- The task benefits from explicit user-assistant turn-taking that a single agent loop misses.
- Inception prompts can fix the two roles and the task tightly enough to keep the conversation on-track.
- A turn budget caps conversation length so unproductive loops terminate.
Source
📌 TL;DR
Two agents, inception prompts, no human needed — AI-User sets goals, AI-Assistant executes, they converse until the task is done or the budget runs out.
Advantages
- Fully synthetic task-solving without any human-in-the-loop overhead.
- Useful for generating training data from autonomous agent interactions.
Disadvantages
- 2× inference cost per task — both sides burn tokens.
- Role drift over long conversations; agents can lose track of their fixed personas.