0PricingLogin▼
AI Agents · Lesson

Data Collection: Trajectories and Trace Replay

Replay successful agent traces to build a training set of (state, action) pairs.

Data Is the Product

Fine-tuning is 10% modelling, 90% data. The biggest quality improvements come from better datasets, not bigger models.

What an Agent Trajectory Looks Like

A trajectory captures one complete agent run:

trajectory = {
    'task': 'Refactor the auth module',
    'messages': [
        {'role': 'system', 'content': '...'},
        {'role': 'user', 'content': 'Task...'},
        {'role': 'assistant', 'content': 'Plan...', 'tool_calls': [...]},
        {'role': 'tool', 'content': '...'},
        ...
    ],
    'outcome': 'success'
}

All lessons in this course

  1. When Fine-Tuning Beats Prompting
  2. Data Collection: Trajectories and Trace Replay
  3. LoRA and QLoRA for Cost-Efficient Tuning
  4. Evaluating Tuned Models vs Base
← Back to AI Agents