Agent Distillation. Same traces, different outcome. Turn them into training-ready datasets for smaller, task-specific models, built together with distil labs. Browse the Blueprints:
Who's Who of AI
datateam.bsky.social
Why they matter
Founder with public evidence across AI business.
- AI signals
- 0 past 30d
- Sources
- 0 distinct domains
- Discussões
- 0 past 30d
- Latest signal
- —
Data engineer & Cofounder @dlthub. Building out the tooling i wish i had.
What they're sharing
dltHub Blueprints dlthub.com
We are launching two dltHub Blueprints for agent spend: Agent Cost & Usage to understand it, Agent Distillation to optimize it dlthub.com
Ingesting Agent Traces with dlthub - Alena Astrakhantseva youtube.com
Articles & links
A few weeks ago we launched dltHub Pro. What surprised us was what people built with it. Teams didn't ask for primitives, they asked for complete solutions. So we built Blueprints.
How do you eval your agents? Agent traces are a good place to start. In this 1-hour workshop with @DataTalksClub, you'll learn how to ingest agent traces, model nested JSON into a queryable schema, and build dashboards to understand agent behavior.
Their own posts
Recent commentary
Gave an LLM a schema: 3/10. 📉 Gave it a schema + an ontology: 10/10. 🎯 Same model, same data. The difference? It finally understood what the columns actually mean instead of just vibing off the names.
Their network
In datateam.bsky.social's orbit
Center = datateam.bsky.social. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you datateam.bsky.social? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/datateam-bsky-social)