dltHub

382 posts

dltHub banner
dltHub

dltHub

@dltHub

dltHub is the creator of data load tool (dlt)

Berlin Katılım Kasım 2022
20 Takip Edilen562 Takipçiler
Sabitlenmiş Tweet
dltHub
dltHub@dltHub·
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-d…
dltHub tweet media
English
0
0
2
39
dltHub
dltHub@dltHub·
How fast can you go from zero to a production-ready data pipeline when AI is your copilot? Next Wednesday, @elviskahoro joins @temporalio alongside @nyghtowl and @cecilphillip for a live Vibe Check building a GitHub-powered pipeline with AI + dlt.
English
1
0
2
28
dltHub
dltHub@dltHub·
Explainer on ontology engineering and what we're building around it: why just clean schemas and prompts aren’t enough, and how adding a canonical model + taxonomy + ontology changes what agents can correctly compute (ARPU being the clearest example). dlthub.com/blog/ontology-…
English
0
0
2
71
dltHub
dltHub@dltHub·
@probabl_ai We’ll show how agents can power data pipelines as code, turning traces into fresh, reliable datasets. Stack: dlt, LanceDB, Pydantic, Ibis, HuggingFace + more → behind our agent evaluation platform. 📅 May 5 | 🕒 12:20–12:40 📍 Station F, Paris paris2026.gosim.org/schedule/from-…
English
0
0
2
79
dltHub
dltHub@dltHub·
We’re excited to share that Violetta Mishechkina will be speaking at GOSIM Paris 🇫🇷 Invited by @probabl_ai to join the “Own Your Data Science and AI” workshop. 🎤 From Agent Traces to Analytics Agents generate code, text, telemetry, yet most teams still rely on stale datasets.
dltHub tweet media
English
1
0
2
89
dltHub retweetledi
Kliment Minchev
Kliment Minchev@minchev·
Hosting this true GTM engineering gem on the 28th at @posthog space in SF w/ @modal @p0 @dltHub GTM demo time!!!
Parallel Web Systems@p0

GTM teams are some of the earliest adopters of agents in their pipelines. We're co-hosting an event with @modal_labs, @daboraHQ, and @PostHog to get into the details: orchestrating agent-driven GTM workflows, preparing data for downstream agents, and structuring event data as usable context. Speakers from @modal, @dltHub, @posthog, and Parallel will share real architectures and implementation details, followed by Q&A and pizza. Sign up here: luma.com/nc5v76gs

English
0
3
5
499
dltHub
dltHub@dltHub·
We built the dlt AI Workbench so you don't have to maintain the "how to use dlt" layer yourself. Full argument: dlthub.com/blog/llm-codin…
English
0
0
1
62
dltHub
dltHub@dltHub·
Skills that wrap a library are software. They have dependencies, need maintenance, and degrade when the product changes and no one updates them. The vendor owns the product surface. You own your integration. Same rule, new layer.
English
1
0
1
86
dltHub
dltHub@dltHub·
Big milestone for dlt ❄️ dlt is now a Snowflake Native App. Run pipelines entirely inside @Snowflake, no external infra, no data leaving your account. → Try it free: app.snowflake.com/marketplace/li…
Matthäus Krzykowski@matthausk

1/ Today we @dltHub have released our initial @Snowflake Native App. Replicate MSSQL, MySQL & PostgreSQL → Snowflake, without leaving Snowflake. Create, schedule, and monitor pipelines from the Snowflake UI. No external orchestrator. app.snowflake.com/marketplace/li…

English
0
0
4
355
dltHub
dltHub@dltHub·
Eval: base Claude vs our Workbench. Base: leaks creds 100%, skips docs, no sampling, 1-shot code. Workbench: 0 leaks, always docs/samples/iterates. 58% higher cost ($2.21 vs $1.40) isn’t overhead, it’s the gap between AI slop and production. full read dlthub.com/blog/agent-new…
English
0
0
2
142
dltHub
dltHub@dltHub·
Every layer of software automation was called overkill before it became the baseline. Fortran → Make → CI/CD → Docker → now agents. Code that runs is only the 10%. The other 90% is engineering judgment, boundaries, and iteration.
English
1
0
2
128
dltHub
dltHub@dltHub·
If you don’t define the path, the agent will improvise. With our Agentic REST toolkit, we make the right way the easiest way: - structured access - limited operations - no hidden side effects Full breakdown: dlthub.com/blog/agentic-r…
English
0
0
3
80
dltHub
dltHub@dltHub·
AI agents don’t just use your APIs, they optimize around them. Ask an agent to “build a pipeline” and it will find credentials, escalate privileges, and take the shortest path to completion. Not against your interests, just goal-driven.
English
1
0
2
91
dltHub
dltHub@dltHub·
Not everything that can be modeled should be. With LLMs, more context doesn’t mean a better prompt. The key is Minimum Viable Context for high-precision data models. Here’s what we learned building ontology-driven modeling. Blog by Hiba Jamal ↓ dlthub.com/blog/minimum-v…
English
0
0
2
93
dltHub
dltHub@dltHub·
Outcome → fixed-price, high-margin projects are now viable. This isn’t a productivity hack. It’s a business model shift. Case study 👇 dlthub.com/case-studies/t…
English
0
0
2
81
dltHub
dltHub@dltHub·
For agencies and teams of 5+, standardization is everything.  Tasman encodes their standards, naming, rate limits, and workflows so mid-level engineers ship production-quality work. Knowledge scales across the team instead of being locked in a few individuals.
English
1
0
2
80
dltHub
dltHub@dltHub·
AI can generate a data pipeline in 10 minutes. But can you trust what it produces? That’s the real problem, and it’s not technical. It’s business. If you can’t trust the output, it never reaches production. 🧵
English
1
0
4
156

Keşfet

@elviskahoro @temporalio @nyghtowl @cecilphillip @probabl_ai @posthog @modal @p0