Turn the agent traces you already collect into a training-ready dataset, then let distil labs fine-tune a cheaper drop-in model.
Put this blueprint to work
Talk it through with the dltHub team and we will help you ship it to production.
Contact usBrowse all blueprintsYour coding agent
Claude Code, Cursor or Codex
the agentic layerdltHub AI harness
Agentic primitives to build, run and fix pipelines
dltHub context catalog
Lineage, schema, data quality, governance, run state
Pydantic Logfire
Arize
Langfuse
LangChain
the managed infra layerIngest and standardize traces into the OpenAI messages format as a training-ready dataset.
distil labs
Fine-tune a specialist model, served as a drop-in replacement via API to distil labs customers.
This Blueprint gives distil labs customers a dltHub workspace that turns the agent traces they already collect into a training-ready dataset, ready to share with distil labs.
Point the workspace at your trace vendor (Pydantic, Arize, Langfuse, or LangChain). It ingests the traces, handles schema drift, and standardizes everything into the OpenAI messages format that distil labs trains on.
From the workspace you hand that dataset to distil labs, who fine-tune a specialist model and give you back a drop-in replacement served via API.
Talk it through with the dltHub team and we will help you ship it to production.
Contact us
OpenAI