dltHub
Book a demo

The agentic data stack: a coding agent running dltHub into Snowflake

A real dltHub setup: a coding agent operates the whole stack through the dltHub AI harness and context catalog, grounded on 25 live pipelines.

OpenCode

AI code agent

OpenCode

Martin + his coding agent

4 specialized subagents

Data Engineer

ingestion

Data Modeler

the semantic layer

Dashboard Developer

data apps

Platform Admin

infra, ops & build-run-fix

operates through
dltHubthe agentic layer

dltHub AI harness

Agentic primitives to build, run, and fix pipelines

Martin: "skills"

dltHub context catalog

Lineage, schema, data quality, governance, run state, and API context assets

Martin: "observability"

grounds & runs

dlt Sources

25 sources · Jul 19

  • Salesforce

    Salesforce

  • Microsoft Teams

    Microsoft Teams

  • Microsoft Planner

    Microsoft Planner

  • Google Tag Manager

    Google Tag Manager

  • ERP

  • OpenCode traces

    OpenCode traces

+19 more sources

dltHub

the managed infra layer

  • Ingestion

  • Orchestration

  • Managed infra

Warehouse

  • Snowflake

    Snowflake

Serving

  • Streamlit

    Streamlit

    on dltHub

dltHub — agentic data layer + managed infrastructureYour agent & external tools
The coding agent operates the stack through the dltHub AI harness and context catalog, grounded on 25 live pipelines from Salesforce to ERP, landing in Snowflake and served in Streamlit.
Martin Seifert
A real dltHub setup, run byMartin SeifertData Lead at Pro Juventute

Want a setup like this?

Talk it through with the dltHub team and we will help you ship it to production.

Contact usBrowse all blueprints

How it works

This is a real dltHub setup, run by Martin Seifert, Data Lead at Pro Juventute. It reframes the stack around how he actually works: the coding agent sits on top and operates everything below it.

Martin drives the loop from OpenCode. It operates through the dltHub AI harness, the agentic primitives that build, run, and fix pipelines, and the dltHub context catalog, which keeps lineage, schema, data quality, governance, run state, and API context in one place the agent reads from and writes to. Those are the two things he calls out: the harness he thinks of as "skills", the catalog as "observability".

Inside OpenCode, Martin splits the work across four specialized subagents: a Data Engineer for ingestion, a Data Modeler for the semantic layer, a Dashboard Developer for data apps, and a Platform Admin for infra, ops, and the build-run-fix fallback that tries a fix and presents it to him before deploying anything.

Underneath, the data plane runs left to right: 25 live pipelines, from Salesforce and Microsoft Teams to Microsoft Planner, Google Tag Manager, an ERP, and OpenCode traces, ingested and orchestrated on dltHub managed infrastructure, landing in Snowflake, and served in Streamlit.

Key features

  • A coding agent (OpenCode) operates the whole stack top-down
  • The dltHub AI harness gives the agent primitives to build, run, and fix pipelines
  • The dltHub context catalog holds lineage, schema, data quality, governance, and run state the agent reads and writes
  • 25 live pipelines land in Snowflake and are served in Streamlit and Sigma

How to get it

  • This mirrors a live setup rather than a packaged product. Talk to dltHub to build the same agentic stack on your own sources.

Pricing

  • dltHub from $1,190/month: the platform the pipelines run on.
  • Set up a 30-minute scoping call to map it onto your stack.

Put this blueprint to work

Talk it through with the dltHub team and we will help you ship it to production.

Contact us
Find more blueprints