Overview
Datalayer brings AI agents into the day-to-day environment of data scientists and analysts, sitting alongside notebooks and compute infrastructure. The platform supports code generation, data analysis, and scalable workflow execution, with collaboration as a first-class feature rather than an afterthought.
The product is positioned in the Jupyter and broader data-science tooling ecosystem, with a Brussels base.
Key people
In the news
- After meeting twice in the US, I had the pleasure of catching up with Travis Oliphant yesterday for the third time—this time in Brussels, Belgium. Thank you, Travis, for an inspiring conversation covering so much ground, including the Intelligence Hub whitepaper and its Frames, Cogs, Ops, Guards, Gates, and Tracks constructs. I truly believe your vision and work can make a positive impact on our fast-moving world.As a concrete next step, I’ve updated Datalayer Agentspecs through two PRs to incorporate ideas from the whitepaper: 👉
- Building at AI speed… connecting with Odoo This morning, we made the Datalayer MCP Server extensible. This afternoon, we added tools for Odoo Accounting. And the integration was surprisingly simple. What makes it different? Most MCP servers expose generic tools such as “get entity.” Datalayer lets us provide purpose-built accounting tools such as “get invoices,” making Odoo’s data much easier for AI agents—and people—to work with. Why Odoo? We’re preparing to migrate our own accounting to the platform, and giving people
- 𝗙𝗿𝗼𝗺 𝘃𝗶𝗯𝗲 𝗰𝗼𝗱𝗶𝗻𝗴 → 𝗱𝗼𝗰𝘂𝗺𝗲𝗻𝘁-𝗳𝗶𝗿𝘀𝘁 → 𝘀𝗽𝗲𝗰-𝗱𝗿𝗶𝘃𝗲𝗻 𝗰𝗼𝗱𝗶𝗻𝗴 I’ve been using AI coding agents extensively for more than a year. For a long time, my workflow was mostly 𝘷𝘪𝘣𝘦 𝘤𝘰𝘥𝘪𝘯𝘨: define a reasonably well-scoped feature, sometimes write a document about it, give the context to the agent, and iterate. And it worked brilliantly. ⚡ For me, the productivity boost has easily been 𝟭𝟬𝘅. But I’m now trying to make that workflow much more structured. 📄 𝗕𝗲𝗳𝗼𝗿𝗲 𝘄𝗿𝗶𝘁𝗶𝗻𝗴
- 𝗦𝘂𝗻, 𝘀𝗮𝗻𝗱, 𝗰𝗼𝗱𝗲, 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆… 𝗮𝗻𝗱 𝘁𝗵𝗲𝗮𝘁𝗿𝗲. 𝗡𝗼𝘁 𝗮 𝗯𝗮𝗱 𝘄𝗲𝗲𝗸𝗲𝗻𝗱. I came back from a few days at the Belgian seaside—enjoying the sun, sand and sea, and wandering through some of the art shops along the coast. Then, somehow, I found myself back in front of the keyboard. 😄 But this time for something particularly enjoyable: implementing feature requests coming from the communities around: 👉 https://lnkd.in/ejpZ7ypv 👉 https://lnkd.in/ea-c7gGU And that was probably the highlight of my
Related profiles
Something wrong or missing? Send an update. Fixed within 24 hours.