Blogsby GlyphdltHub Blog the company blog of dltHub: latest posts and feed
dltHub · Company blog · 6.8 a month · 210 posts since Feb 16, 2023
Nov 9
MCP on raw data is just Excel hell again
Agents replaced the analyst, not the warehouse. Why MCP on raw data repeats the Excel mistake, and the two layers that fix it: semantics in your catalog, rules in code.
Nov 5
Trusted answers on new data from day one, with dltHub on Databricks
Private Preview: dltHub works with Databricks Unity Catalog Pages and Genie Ontology so humans and agents get trusted answers on new data from day one.
Nov 5
dltHub on Databricks: the Unity Catalog Pages walkthrough
Demo walkthrough: one CI waste definition in a Unity Catalog Page drives the dlt pipeline, the model, the metric view and Genie's answer.
Nov 3
Building pipelines has become easy. Knowing if they work correctly is now easy, too
We are releasing our new observability UI, the interface to the dltHub context graph, to General Availability. Find out how this will help you solve missing data when everything looks right at the surface from your pipelines.
Oct 29
The future of data work, as discussed in a panel at Helsinki data week
Summary of the 16:00 Panel discussion: The future of data teams and their tools hosted by MotherDuck
Oct 22
The post-AI data stack vs. the post-data AI stack
A lot of teams wire Claude straight into HubSpot, Stripe and Zendesk, and that’s the data stack. It works for today’s questions but often not for last quarter’s, and this post covers why and what to add.
Oct 14
What’s in the Kool-Aid: field notes from data engineers already drinking it
AI pioneers in data engineering say their job is now ontology: platform rules, source meaning, business intent.
Oct 8
Introducing job-inspector: dltHub's first verified agent for diagnosing failed pipelines
dltHub background agents are in public preview, starting with job-inspector: a verified agent that diagnoses failed pipeline jobs with read-only access and posts the cause, its confidence and the log evidence to Slack.
Sep 15
Towards a Self-Improving Autonomous Data Platform
A data platform should run like a power grid: routine faults cleared automatically inside a bounded scope, anything risky escalated to a person.
Sep 8
Reverse ETL to Attio
In March 2024, we published “dlt adds Reverse ETL”. This piece walks through an example GTM workflow: turning a hiring signal into enriched, sales-ready company and people records, then reverse-ETL them to Attio.
Sep 1
From Raw Tables to Conversational Analytics in One Afternoon
We previously explained in detail how to build canonical models. This blog takes that further: declare a BigQuery property graph over those models, query it with GQL, then ask it questions in plain English.
Aug 25
Why you still need data people in the agentic era & what for
AI can automate data pipelines, but only humans can own business accountability.
Aug 18
Step by step: Hubspot connector from Fivetran to dlthub
Migrating a HubSpot pipeline from Fivetran to dlt: reverse-engineering the vendor schema, rebuilding the load and 13 dbt models.
Aug 6
dltHub: dlt made agents good at building pipelines. Now they're safe enough to run for your whole team
dlt made agents good at building pipelines. dltHub makes their work safe to run: agentic alerts, team workspaces, and managed infrastructure for your whole team.
Aug 4
Validating Trust in Data: How dltHub Delivers GxP-Ready, Auditable Ingestion into Snowflake
In regulated life sciences, "can you explain your data?" has moved from a QA question to a board-level one. dltHub turns ingestion into validated, testable code - built on dlt, run on dltHub - so your team and their agents produce data...
Aug 3
Transformations that know their context
dlthub ships 2 ways to run transformations - you can bring your own dbt project or use dlthub native transformations. This posts aims to explain to practitioners and technical decision makers how the two methods are different.
Jul 29
Composable canonicals: from tribal data knowledge to versioned artifact
In this article, I'm exploring an AI-native architecture that aims to solve the traditional central data team problem.
Jul 22
dlt vs dltHub: the five ecosystem layers dltHub adds
dlt handles ingestion. dltHub adds the five ecosystem layers you'd otherwise build yourself: AI harness, context catalog, transformation, orchestration, managed infra.
Jul 21
Moving off Airbyte
Moving off Airbyte: what the switch to dlt does to your ops load, your bill, and who can build pipelines. Real numbers on cost, reliability, and maintenance.
Jul 15
Productionize Python ETL Scripts: Migrate to dlt & dltHub
Schema breaks, OOM deaths, duplicate loads, bus factor of one. What it takes to make hand-rolled pipelines production-grade, and what it costs to run them after.
Jul 14
Migrating from Fivetran: how the move actually works
What does the move do to my bill and my renewal? And how to move?
Jul 9
Consulting is becoming software
dltHub ships four Migration Blueprints: Python scripts, dlt, Fivetran, and Airbyte to dltHub. LLM-native tooling turns multi-month, senior-only migration projects into weeks of work at a fraction of the cost.
Jul 8
We are launching two dltHub Blueprints for agent spend: Agent Cost & Usage to understand it, Agent Distillation to optimize it
dltHub launches two Blueprints for agent spend: Agent Cost & Usage to break down what each model, person, and customer costs, and Agent Distillation (with distil labs) to replace expensive agents with cheaper specialist models.
Jul 7
How I Tracked the Tech Job Market as a Working Student
I analyzed 987 job posts to see what the data job market really wants. Built with dlt + Claude in one conversation, deployed to auto-update every month.
The latest 200 of 210 posts on file; older ones are under Months.
About this blog
dltHub's own blog on dlthub.com, found by the daily check.
Posts per week, last 26 weeks
Posts by month
Writes about
Data engineering (17), AI and agents (14), Product and company (4) in the last six months.
dltHub
dltHub on Companies (companies.fru.dev)Across Glyph:awards·Roundup·marketplaces·Changefeed·socials
History
Listed on Blogs Sep 27, 2026. No changes to its feed, status or cadence since.