| How do you eval your agents?
Agent traces are a good place to start.
In this 1-hour workshop with @DataTalksClub, you… |
@dltHub |
Company |
Original |
2026-07-07 |
338 |
3 |
0 |
0 |
0 |
6 |
| AI writing pipelines is cool.
AI remembering the entire workflow is better.
dltHub Pro carries context from ingestion… |
@dltHub |
Company |
Original |
2026-07-06 |
136 |
2 |
0 |
0 |
0 |
1 |
| Text-to-SQL doesn't break because models can't write SQL, it breaks because they don't know what your data means.
An a… |
@dltHub |
Company |
Original |
2026-06-25 |
115 |
3 |
0 |
2 |
0 |
0 |
| Human in the loop shouldn't mean copy-pasting context into an agent every 5 minutes.
It should mean judgment, not erra… |
@dltHub |
Company |
Original |
2026-06-24 |
135 |
3 |
0 |
0 |
0 |
0 |
| 91% of the 81,000 new dlt pipelines shipped in January 2026 were built by agents.
The bottleneck in data engineering i… |
@dltHub |
Company |
Original |
2026-06-18 |
101 |
3 |
0 |
1 |
0 |
0 |
| How much data can $1 of compute move?
We benchmarked dltHub on a small worker (2 vCPU / 4 GB) loading into BigQuery:
… |
@dltHub |
Company |
Original |
2026-06-09 |
132 |
6 |
0 |
0 |
0 |
1 |
| Data quality usually starts too late.
By the time bad data hits a dashboard, the original business assumptions are gon… |
@dltHub |
Company |
Original |
2026-06-05 |
152 |
6 |
0 |
1 |
0 |
1 |
| Agentic Analytics Demo Night lands in San Francisco this Wednesday 🚀
We're joining @inngest, @lightdash_devs, and @str… |
@dltHub |
Company |
Original |
2026-06-01 |
394 |
6 |
1 |
1 |
0 |
0 |
| What does it take to build a product people actually keep using?
On Wednesday, we're hosting @sameer_alsakran, Founder… |
@dltHub |
Company |
Original |
2026-06-01 |
288 |
6 |
1 |
1 |
0 |
0 |
| Berlin’s Applied AI Week is looking pretty special.
Tomorrow, dltHub and @modal are hosting an evening in Berlin for f… |
@dltHub |
Company |
Original |
2026-05-26 |
149 |
5 |
0 |
1 |
0 |
0 |
| The AI stack is evolving fast, but reliable data movement is still the foundation.
Join dltHub, @LanceDB and @DataHubC… |
@dltHub |
Company |
Original |
2026-05-18 |
111 |
3 |
1 |
0 |
0 |
0 |
| How fast can you go from zero to a production-ready data pipeline when AI is your copilot?
Next Wednesday, @elviskahor… |
@dltHub |
Company |
Original |
2026-05-15 |
107 |
4 |
0 |
1 |
0 |
0 |
| Building pipelines with AI usually means losing context between tools.
dltHub AI Workbench runs the full 12-step workf… |
@dltHub |
Company |
Original |
2026-05-14 |
437 |
5 |
0 |
0 |
0 |
3 |
| Explainer on ontology engineering and what we're building around it: why just clean schemas and prompts aren’t enough, … |
@dltHub |
Company |
Original |
2026-05-12 |
112 |
2 |
0 |
0 |
0 |
0 |
| Big milestone for dlt ❄️
dlt is now a Snowflake Native App.
Run pipelines entirely inside @Snowflake, no external inf… |
@dltHub |
Company |
Quote |
2026-04-23 |
379 |
4 |
0 |
0 |
0 |
0 |
| Every layer of software automation was called overkill before it became the baseline.
Fortran → Make → CI/CD → Docker … |
@dltHub |
Company |
Original |
2026-04-15 |
147 |
2 |
0 |
1 |
0 |
0 |
| AI agents don’t just use your APIs, they optimize around them.
Ask an agent to “build a pipeline” and it will find cre… |
@dltHub |
Company |
Original |
2026-04-14 |
108 |
2 |
0 |
1 |
0 |
0 |
| Not everything that can be modeled should be.
With LLMs, more context doesn’t mean a better prompt.
The key is Minimu… |
@dltHub |
Company |
Original |
2026-04-09 |
107 |
2 |
0 |
0 |
0 |
0 |
| AI can generate a data pipeline in 10 minutes.
But can you trust what it produces?
That’s the real problem, and it’s … |
@dltHub |
Company |
Original |
2026-04-03 |
170 |
4 |
0 |
1 |
0 |
1 |
| Most AI coding tools stop at “here’s your code.”
But getting pipelines into production, and trusting them there, is th… |
@dltHub |
Company |
Original |
2026-04-02 |
140 |
4 |
0 |
1 |
0 |
3 |
| Most teams still build connectors one by one.
Each with its own patterns.
Each with its own tech debt.
What if you b… |
@dltHub |
Company |
Original |
2026-03-31 |
172 |
5 |
0 |
1 |
0 |
3 |
| This is the part that makes agent workflows actually work.
Not just generating pipelines, but understanding and trusti… |
@dltHub |
Company |
Quote |
2026-03-30 |
99 |
2 |
0 |
0 |
0 |
0 |
| Agents don’t break on code generation, they break when they hit real data infra: schema changes, rate limits, hidden pl… |
@dltHub |
Company |
Quote |
2026-03-30 |
113 |
3 |
0 |
0 |
0 |
0 |
| LLMs fail at data transformation because they see isolated tables, not your business.
We built the dltHub AI Workbench… |
@dltHub |
Company |
Original |
2026-03-30 |
100 |
3 |
0 |
1 |
0 |
1 |
| Agents can generate pipelines, but how do you know the data is actually correct?
With the dltHub AI Workbench, validat… |
@dltHub |
Company |
Original |
2026-03-26 |
121 |
6 |
0 |
0 |
0 |
1 |
| New course: Agentic Data Engineering with dltHub 🤖
Agents can now write entire data pipelines, but writing code was ne… |
@dltHub |
Company |
Original |
2026-03-26 |
123 |
3 |
0 |
1 |
0 |
3 |
| Writing API connectors from scratch is becoming obsolete.
With the new dltHub AI Workbench, open your terminal and pro… |
@dltHub |
Company |
Original |
2026-03-24 |
197 |
3 |
0 |
1 |
0 |
2 |
| Turning data from DBs, APIs, and cloud into training datasets is still harder than it should be.
Great to see @hugging… |
@dltHub |
Company |
Quote |
2026-03-23 |
145 |
4 |
0 |
0 |
0 |
0 |
| Agents can generate pipelines but can you trust them?
Today we’re launching the dltHub AI Workbench:
→ Generate
→ Va… |
@dltHub |
Company |
Quote |
2026-03-23 |
175 |
4 |
0 |
1 |
0 |
1 |
| WAP (Write → Audit → Publish) has a blind spot.
It assumes your data can safely land in staging.
But in real pipeline… |
@dltHub |
Company |
Original |
2026-03-22 |
137 |
2 |
0 |
1 |
0 |
0 |
| Curious what people here are actually using for AI coding 👀
Copilot? Cursor? Claude Code?
We put together a super sho… |
@dltHub |
Company |
Original |
2026-03-19 |
215 |
3 |
0 |
0 |
0 |
0 |
| Microsoft Fabric is great at compute & storage but data quality enforcement is on you.
Use WAP to validate data be… |
@dltHub |
Company |
Original |
2026-03-17 |
170 |
3 |
0 |
0 |
0 |
1 |
| LLMs follow the gravity of your vocabulary, not your business logic.
That's why your AI-generated stack looks great in… |
@dltHub |
Company |
Original |
2026-03-16 |
144 |
2 |
0 |
1 |
0 |
0 |
| ❄️ Module 2 is live in our course dlt + @Snowflake
Learn how to run dlt pipelines inside Snowflake using Snowpark Con… |
@dltHub |
Company |
Original |
2026-03-15 |
205 |
4 |
1 |
1 |
0 |
0 |
| Small data teams deserve better tools.
We’re opening early design partnerships for solo and small data teams to try dl… |
@dltHub |
Company |
Original |
2026-03-13 |
107 |
2 |
0 |
0 |
0 |
1 |
| Build a data pipeline locally with @DuckDB → ship it to @ClickHouseDB
Join @elviskahoro & Joshua Lee from @Altinit… |
@dltHub |
Company |
Quote |
2026-03-13 |
268 |
2 |
1 |
0 |
0 |
0 |
| Your production traces are gold, but they aren’t training data yet.
We turned raw agent traces into a specialist model… |
@dltHub |
Company |
Original |
2026-03-11 |
369 |
9 |
1 |
2 |
0 |
4 |
| The “pipeline-d hug” 🤗 is here.
We just launched our @huggingface integration in dlt, bridging two worlds that have be… |
@dltHub |
Company |
Original |
2026-03-09 |
2,475 |
8 |
1 |
2 |
1 |
2 |
| Spring brings good things and more than just flowers. 🌸 ❄️
Catch up on Module 1 of our dlt + @Snowflake course before … |
@dltHub |
Company |
Original |
2026-03-08 |
204 |
4 |
0 |
1 |
0 |
0 |
| Team at @TasmanAnalytics runs data engineering projects for mid-market and enterprise clients.
Their biggest challenge… |
@dltHub |
Company |
Original |
2026-03-05 |
561 |
5 |
0 |
1 |
1 |
2 |
| Thanks for the shoutout @lhoestq, this hug means a lot! 🤗
We’re excited to see @huggingface datasets hub live as a des… |
@dltHub |
Company |
Quote |
2026-03-03 |
514 |
6 |
1 |
0 |
0 |
1 |
| Data models describe the data, ontologies describe the world. With ontologies, an agent can reason over data as opposed… |
@dltHub |
Company |
Original |
2026-02-26 |
167 |
4 |
1 |
0 |
0 |
2 |
| Who is the @ufc GOAT? 🥊📊
We turned that curiosity into a full-stack pipeline analyzing 30+ years of UFC fights.
Every… |
@dltHub |
Company |
Original |
2026-02-22 |
141 |
3 |
0 |
1 |
0 |
0 |
| Part 2 of our RAG debug series is out.
We froze retrieval, prompts & dataset, and tested newer models only.
Resul… |
@dltHub |
Company |
Original |
2026-02-20 |
97 |
2 |
0 |
0 |
0 |
0 |
| AI agents fail without memory & context. @cognee_ turns data into self-improving, structured memory at scale.
If y… |
@dltHub |
Company |
Original |
2026-02-19 |
191 |
3 |
1 |
1 |
0 |
2 |
| Legacy ingestion can become a maintenance trap.
At the dltHub Paris meetup, @lavrobs shared how @yespark_fr migrated f… |
@dltHub |
Company |
Original |
2026-02-16 |
620 |
2 |
1 |
2 |
0 |
0 |
| From APIs to Warehouses 📦
On Feb 17 (16:30 CET), together with @DataTalksClub, Aashish Nair will walk through building… |
@dltHub |
Company |
Original |
2026-02-12 |
84 |
2 |
0 |
1 |
0 |
0 |
| What if dimensional modeling didn’t mean hours of boilerplate SQL?
We built an AI-driven workflow that turns raw data … |
@dltHub |
Company |
Original |
2026-02-12 |
117 |
2 |
0 |
0 |
0 |
2 |
| Berlin, it’s meetup time!
Join us for the dltHub Community Meetup, an evening of real-world demos, lessons learned, an… |
@dltHub |
Company |
Original |
2026-02-11 |
79 |
2 |
0 |
1 |
0 |
0 |
| January’s Rising Stars in the dlt ecosystem 👇
Builders are vibe coding pipelines around real-time markets, AI dev plat… |
@dltHub |
Company |
Original |
2026-02-10 |
362 |
3 |
0 |
2 |
1 |
0 |
| 💘 Data Valentine Challenge started today.
5 days. 5 live data therapy sessions with @DataRecce, https://t.co/W31W689b5… |
@dltHub |
Company |
Original |
2026-02-09 |
109 |
2 |
1 |
0 |
0 |
0 |
| An AI coding agent ignored a code freeze, wiped a prod DB, then hallucinated data to cover it up.
Data quality in the … |
@dltHub |
Company |
Original |
2026-01-21 |
109 |
3 |
0 |
0 |
0 |
0 |
| 🇫🇷 Paris data folks 💛
We’re hosting a dlt Community Meetup in Paris on Feb 4th (6–9 PM) together with @Polycea.
A comm… |
@dltHub |
Company |
Original |
2026-01-15 |
110 |
2 |
0 |
1 |
0 |
0 |
| Semantic layers are the most important "boring" part of data.
Building them manually is a bottleneck for Chat-BI. dlt… |
@dltHub |
Company |
Original |
2026-01-07 |
139 |
2 |
1 |
1 |
0 |
1 |
| To overcome complex cloud cost analysis, @sspaeti showed how dlt can ingest and normalize AWS, GCP, and Stripe data int… |
@dltHub |
Company |
Original |
2025-11-25 |
180 |
3 |
0 |
1 |
0 |
1 |
| European data teams can enjoy lightning-fast analytics & production-ready pipelines with @motherduck EU region full… |
@dltHub |
Company |
Original |
2025-11-13 |
268 |
3 |
0 |
0 |
0 |
1 |
| Ever launched a data pipeline and wondered what’s happening under the hood? The dlt Workspace Dashboard gives real-time… |
@dltHub |
Company |
Original |
2025-11-12 |
709 |
5 |
2 |
0 |
0 |
1 |
| At @SmallDataSF we’re going hands-on with one idea: keep data simple & scalable → for builders who want less toolin… |
@dltHub |
Company |
Original |
2025-10-29 |
268 |
3 |
0 |
1 |
1 |
0 |
| From “plausible but wrong” to production-ready.
Our LLM scaffolds start with deterministic parsing + AI semantics to b… |
@dltHub |
Company |
Original |
2025-10-23 |
128 |
1 |
0 |
0 |
0 |
0 |
| Perfect Friday reading: Erfan Hesami's guide to dlt makes data pipelines actually simple.
Our co-founder spent 10 year… |
@dltHub |
Company |
Original |
2025-10-10 |
176 |
3 |
0 |
1 |
0 |
0 |
| We’re an official launch partner for @motherduck EU expansion!
Blazing-fast, serverless DuckDB warehousing now fully i… |
@dltHub |
Company |
Original |
2025-09-24 |
305 |
4 |
0 |
0 |
0 |
0 |
| LLMs tried to write code for you but saw the docs and went "nah"
We explore a benchmark on pipeline creation
🔹 Split t… |
@dltHub |
Company |
Original |
2025-04-01 |
145 |
2 |
0 |
0 |
0 |
1 |
| Managed cloud databases markup compute by 35-70x. It was fine when humans ran queries. AI doesn’t need coddling.
Iceber… |
@dltHub |
Company |
Original |
2025-03-19 |
256 |
3 |
2 |
0 |
0 |
1 |
| Data teams using dlt often build declarative pipeline interfaces to enable low-code collaboration.
So we created dlt+ … |
@dltHub |
Company |
Original |
2025-03-05 |
290 |
5 |
1 |
0 |
0 |
0 |
| Hope is not a testing strategy.
CI/CD isn’t just a tool, It’s a way to work without fear.
Fewer Fires, More Trust,
L… |
@dltHub |
Company |
Original |
2025-03-04 |
203 |
3 |
1 |
0 |
0 |
1 |
| Stop waiting on your warehouse.
dlt+ Cache lets you run dbt models, test data, and debug transformations instantly—wit… |
@dltHub |
Company |
Original |
2025-02-25 |
525 |
5 |
2 |
1 |
0 |
4 |
| Writing Iceberg or Delta on filesystem/buckets? dlt supports both:
https://t.co/Ge76tPZ2ZV
And if you wanna Bring Y… |
@dltHub |
Company |
Original |
2025-02-04 |
126 |
5 |
0 |
0 |
0 |
1 |
| 1/2 Data engineering learners, exciting news!
𝑂𝑢𝑟 2024 𝑑𝑎𝑡𝑎 𝑖𝑛𝑔𝑒𝑠𝑡𝑖𝑜𝑛 𝑤𝑜𝑟𝑘𝑠ℎ𝑜𝑝 on 𝐷𝑎𝑡𝑎𝑇𝑎𝑙𝑘𝑠.𝐶𝑙𝑢𝑏 was the most watched… |
@dltHub |
Company |
Original |
2025-01-20 |
249 |
3 |
2 |
1 |
0 |
1 |
| Building your first data warehouse? Avoid the pitfalls: complex configs, broken schemas, & duplicate data.
With dlt… |
@dltHub |
Company |
Original |
2025-01-16 |
227 |
3 |
1 |
0 |
0 |
0 |
| Working with spatial data in PostgreSQL? 🌍
DLT + PostGIS makes it simple:
✅ Load WKT or WKB formats
✅ Handle SRIDs (de… |
@dltHub |
Company |
Original |
2025-01-09 |
221 |
0 |
1 |
1 |
0 |
0 |
