←
dltHub411 posts
dltHub avatar

dltHub

@dltHub

The agentic layer and managed infra layer on top of any warehouse, enabling a team and its agents to generate and manage high-quality, auditable data at scale.

◷ Joined November 2022▧ 108 Photos and videos
dltHub avatar
dltHub@dltHub·May 14

Building pipelines with AI usually means losing context between tools. dltHub AI Workbench runs the full 12-step workflow as a continuous session, schemas, incrementals, traces, transformations, and notebooks share context across the stack. dlthub.com/blog/agentic-data…

Post attachment
dltHub avatar
dltHub@dltHub·Nov 17

New on dltHub: datasets and lineage. See how your data flows, without asking who built it. The Workspace Explorer maps sources → pipelines → datasets, shows which jobs trigger which, and highlights what a failed run affects downstream. dlthub.com/blog/introducing-…

dltHub avatar
dltHub@dltHub·Nov 10

New on dltHub: performance optimization. Slow pipeline? Fix it yourself instead of filing a ticket. Your coding agent finds and fixes the bottleneck, you pick the machine size each job needs, and faster runs cost less. dlthub.com/blog/introducing-…

dltHub avatar
dltHub@dltHub·Jul 6

AI writing pipelines is cool. AI remembering the entire workflow is better. dltHub Pro carries context from ingestion to deployment to maintenance instead of starting over every step. Try it: dlthub.com/products/dlthub

Post attachment
dltHub avatar
dltHub@dltHub·Jun 29

AI agents generate traces, but are you analyzing them?  Join Alena Astrakhantseva to learn how to turn tool calls, token usage, and outcomes into structured, queryable data with dltHub Pro. July 6, live on YouTube with @DataTalksClub Register ↓ luma.com/3sint80a

dltHub avatar
dltHub@dltHub·Jun 26

AI memory just got smarter!

Introducing Cognee v1.0: a major breakthrough in agentic intelligence. It is 145% better than Opus 4.8 and GPT 5.5 at long context memory retrieval. Cognee allows a 100 BILLION token context window 100,000x more than Claude. It's: - 6.9x cheaper than GPT 5.5 and Opus 4.8 - Cold starts in 350ms & searches in 260ms Why this matters: Today agents forget important context, redo tasks, waste tokens, and slow down as workflows get more complex. Cognee solves this. It’s not a place to build agents. It connects to the agents you’ve already built, across any platform, and makes them significantly cheaper, faster, and more accurate. Here's how it works:

3:01
dltHub avatar
dltHub@dltHub·Jun 25

The common fix is a semantic layer added on top. Now you maintain it twice and the two drift. We build from the other end: write the canonical knowledge layer first, use that one spec to generate the model and answer questions over it. dlthub.com/blog/canonical-te…

dltHub avatar
dltHub@dltHub·Jun 25

Text-to-SQL doesn't break because models can't write SQL, it breaks because they don't know what your data means. An agent can return valid SQL and still be wrong, and a clean wrong number looks just as trustworthy as a right one.

0:33
dltHub avatar
dltHub@dltHub·Jun 24

Human in the loop shouldn't mean copy-pasting context into an agent every 5 minutes. It should mean judgment, not errands. If your agent needs a Rube Goldberg machine of prompts, tabs, and slack messages, the problem isn't human. It's missing context. dlthub.com/blog/context

0:25
dltHub avatar
dltHub@dltHub·Jun 20

The clearest case: asked if 55% at-risk seats = churned, the schema-only model said no, but guessed. It didn't know the real threshold was 60%. Ask about 65% and it'd still say no. The ontology model said no because 55% < 60%. That reasoning generalizes. 👀

dltHub avatar
dltHub@dltHub·Jun 20

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.

dltHub avatar
dltHub@dltHub·Jun 18

Agents can generate pipelines, models, and dashboards. They can’t generate what a customer is, when an order counts as revenue, why a definition excludes what it excludes, or where historical breaks in your systems are. Most of this is still undocumented, in people’s heads.