Fine-Tune a Model on Your Own Coding Agent Traces

Melvin Vivas · X post · 2026-08-30 · Open on X

Topics: Fine-tuning & Model Customization, AI Agents, Tool Use & MCP · Level: advanced

Summary

The creator recommends a Hugging Face live tutorial by Ben Burtenshaw on fine-tuning a coding agent with its own agent traces, so it keeps learning over time. The idea is to turn the logs your coding agent already produces into training data.

Key points

• Coding agent traces (logs of agent sessions) can be used as training data.
• Fine-tuning on those traces is a path to continual learning for a coding agent.
• The tutorial is a free live session on Hugging Face's YouTube channel.
• There is an accompanying article (not linked in the post).

Resources mentioned

• Training Agents series (Hugging Face) · video · youtube.com · free
  Hugging Face live tutorial on fine-tuning a coding agent with its own traces for continual learning.
  Also in: Hugging Face Training Agents series: post-training coding agents (Melvin Vivas on X · notes)
• Ben Burtenshaw · person · x.com · free
  Hugging Face engineer who presents the agent fine-tuning tutorial.

Try this

• Watch the Hugging Face live tutorial on fine-tuning a coding agent.
• Find and read the accompanying article.
• Collect your own coding agent traces and fine-tune a small model on them.