# DLT Hub

See the latest articles from dltHub.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## dltHub brings data and meaning into ClickHouse

DevFeed: [dltHub brings data and meaning into ClickHouse](<https://devfeed.tech/articles/dlthub-brings-data-and-meaning-into-clickhouse-131083.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/dlthub-clickhouse-ontology-agents>)

Author: Adrian Brudaru

Published: 2026-11-12T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [etl](<https://devfeed.tech/topics/etl.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [business](<https://devfeed.tech/tags/business.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [column](<https://devfeed.tech/tags/column.md>), [comment](<https://devfeed.tech/tags/comment.md>), [commit](<https://devfeed.tech/tags/commit.md>), [concepts](<https://devfeed.tech/tags/concepts.md>), [counts](<https://devfeed.tech/tags/counts.md>), [data](<https://devfeed.tech/tags/data.md>), [has](<https://devfeed.tech/tags/has.md>), [meaning](<https://devfeed.tech/tags/meaning.md>), [preview](<https://devfeed.tech/tags/preview.md>), [private](<https://devfeed.tech/tags/private.md>), [product](<https://devfeed.tech/tags/product.md>), [table](<https://devfeed.tech/tags/table.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

dltHub's Private Preview writes business definitions into ClickHouse table and column comments so ClickHouse Agent can consult them before generating SQL. The workflow uses an agent to build and deploy data pipelines, elicit and document business concepts with human owners, and create an ontology and canonical data model; pipeline runs can update the comments as data changes. The excerpt's GitHub dataset example distinguishes commits, pull requests, issue labels, and shared issues/pull requests endpoints, giving the agent context beyond table names. The article argues that raw-data access can leave agents guessing and that definitions stored in a separate governance tool can drift from the warehouse. dltHub says keeping definitions alongside data lets agents use the same context; this is the company's approach, not comparative evaluation evidence. Private Preview access is described as open to dltHub and ClickHouse customers.

### Source excerpt

Private Preview: dltHub writes your business definitions into ClickHouse table and column comments, so ClickHouse Agent gives trusted answers.

## dltHub on ClickHouse: the ClickHouse Agent walkthrough

DevFeed: [dltHub on ClickHouse: the ClickHouse Agent walkthrough](<https://devfeed.tech/articles/dlthub-on-clickhouse-the-clickhouse-agent-walkthrough-131082.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/clickhouse-agent-ontology-walkthrough>)

Author: Thierry Jean

Published: 2026-11-10T23:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [etl](<https://devfeed.tech/topics/etl.md>), [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI agent hallucinations](<https://devfeed.tech/topics/ai-agent-hallucinations.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [aggregates](<https://devfeed.tech/tags/aggregates.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [bug](<https://devfeed.tech/tags/bug.md>), [business](<https://devfeed.tech/tags/business.md>), [business-context](<https://devfeed.tech/tags/business-context.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [ci](<https://devfeed.tech/tags/ci.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [data](<https://devfeed.tech/tags/data.md>), [demo](<https://devfeed.tech/tags/demo.md>), [github](<https://devfeed.tech/tags/github.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [product](<https://devfeed.tech/tags/product.md>), [updates](<https://devfeed.tech/tags/updates.md>), [waste](<https://devfeed.tech/tags/waste.md>)

### AI overview

The walkthrough shows how dltHub makes ClickHouse Agent answers about GitHub CI waste more consistent by supplying shared business definitions. Without context, the agent invents a definition; dltHub instead stores table and column descriptions in ClickHouse comments and keeps the "CI waste" definition in a versioned ontology alongside pipeline code. The AI Harness helps create and schedule a pipeline, shape data into a canonical model, and deploy tested transformations. The agent can then answer from the defined metric, with results traceable to it and data prepared for follow-up analytics. Loading data with the AI Harness is available today; writing ontology meaning into ClickHouse is in private preview. Comments are updated on pipeline runs, not immediately when a schema changes.

### Source excerpt

Demo walkthrough: dltHub loads GitHub data, its definitions and an ontology into ClickHouse, so ClickHouse Agent answers how much CI is waste.

## Introducing performance optimization in dltHub

DevFeed: [Introducing performance optimization in dltHub](<https://devfeed.tech/articles/introducing-performance-optimization-in-dlthub-127524.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/introducing-performance-optimization>)

Author: Matthaus Krzykowski

Published: 2026-11-10T12:00:00Z

Content type: release

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [cloud cost management](<https://devfeed.tech/topics/cloud-cost-management.md>)

Tags: [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-optimization](<https://devfeed.tech/tags/performance-optimization.md>), [product](<https://devfeed.tech/tags/product.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

dltHub's performance toolkit helps teams diagnose and improve slow, failing, or memory-heavy pipelines, then assign each job suitable CPU, memory, and timeout settings. Its agent profiles extraction, normalization, and loading, guides changes to batching, buffers, workers, or parallelism, and measures again to check the result. Source-specific skills cover filesystem, REST API, and SQL tuning. For SQL databases, pyarrow and ConnectorX can skip schema type inference and are reported to offer up to 30x speed gains, with memory and parallelism considerations. The platform offers four instance sizes and lets teams extend the 120-minute default timeout; dltHub manages the infrastructure. In a stated benchmark, a tuned pipeline ingested a 20 GB database in under five minutes versus 74.6 minutes with defaults. Results depend on the source, data types, and resources available.

### Source excerpt

TODO: meta description (about 150 characters).

## MCP on raw data is just Excel hell again

DevFeed: [MCP on raw data is just Excel hell again](<https://devfeed.tech/articles/mcp-on-raw-data-is-just-excel-hell-again-124273.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/mcp-on-raw-data-is-excel-hell-again>)

Author: Adrian Brudaru

Published: 2026-11-09T00:00:00Z

Content type: opinion

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [Analytics Pipeline](<https://devfeed.tech/topics/analytics-pipeline.md>), [data analyst](<https://devfeed.tech/topics/data-analyst.md>), [reproducibility](<https://devfeed.tech/topics/reproducibility.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [code](<https://devfeed.tech/tags/code.md>), [crm](<https://devfeed.tech/tags/crm.md>), [customer](<https://devfeed.tech/tags/customer.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [definition](<https://devfeed.tech/tags/definition.md>), [department](<https://devfeed.tech/tags/department.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [excel](<https://devfeed.tech/tags/excel.md>), [finance](<https://devfeed.tech/tags/finance.md>), [governance](<https://devfeed.tech/tags/governance.md>), [harness](<https://devfeed.tech/tags/harness.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [rules](<https://devfeed.tech/tags/rules.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [warehouse](<https://devfeed.tech/tags/warehouse.md>)

### AI overview

The article argues that agents connected directly to raw MCP data can produce conflicting business answers across departments, and may change data when given write access. It proposes two layers: an ontology in the platform catalog that maps business terms to data and definitions, and tested code that applies business rules consistently across sources. Agents can then use MCP tools mapped to the meaning layer. It names Databricks Unity Catalog Business Semantics and Genie Ontology, and Snowflake Semantic Views and governed MCP servers as platform examples. The text says raw MCP may work for individual use, but offers no shared precision for company-wide answers. It also describes dltHub as building pipelines, models, ontology, and metric views from business definitions, storing meaning in existing catalogs, with work done at build time.

### Source excerpt

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.

## Trusted answers on new data from day one, with dltHub on Databricks

DevFeed: [Trusted answers on new data from day one, with dltHub on Databricks](<https://devfeed.tech/articles/trusted-answers-on-new-data-from-day-one-with-dlthub-on-databricks-119631.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/dlthub-databricks-unity-catalog-pages-genie>)

Author: Matthaus Krzykowski

Published: 2026-11-05T00:00:00Z

Content type: release

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [databricks](<https://devfeed.tech/topics/databricks.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [Analytics Pipeline](<https://devfeed.tech/topics/analytics-pipeline.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [announce](<https://devfeed.tech/tags/announce.md>), [audit](<https://devfeed.tech/tags/audit.md>), [banks](<https://devfeed.tech/tags/banks.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [data](<https://devfeed.tech/tags/data.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [genie](<https://devfeed.tech/tags/genie.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [pages](<https://devfeed.tech/tags/pages.md>), [preview](<https://devfeed.tech/tags/preview.md>), [private](<https://devfeed.tech/tags/private.md>), [product](<https://devfeed.tech/tags/product.md>), [unity](<https://devfeed.tech/tags/unity.md>), [unity-catalog](<https://devfeed.tech/tags/unity-catalog.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

The private preview connects dltHub with Databricks Unity Catalog Pages and Genie Ontology so teams can govern business definitions in the platform catalog and use them across pipelines and agent answers. The dltHub AI harness reads Pages into a repository context file, checks and builds the dlt pipeline, model, and transformation, then deploys a metric view to Unity Catalog. People publish proposed new terms, and Genie answers using the definitions used to build the data. The article says this keeps ownership, review, and access governance with the catalog and makes answers traceable; it contrasts this with raw-data MCP access, where agents infer meaning repeatedly and answers may vary. The integration is in private preview for dltHub and Databricks customers.

### Source excerpt

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.

## dltHub on Databricks: the Unity Catalog Pages walkthrough

DevFeed: [dltHub on Databricks: the Unity Catalog Pages walkthrough](<https://devfeed.tech/articles/dlthub-on-databricks-the-unity-catalog-pages-walkthrough-119630.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/databricks-unity-catalog-pages-genie-ontology-walkthrough>)

Author: Adrian Brudaru

Published: 2026-11-05T00:00:00Z

Content type: tutorial

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Databricks Unity Catalog integration](<https://devfeed.tech/topics/databricks-unity-catalog-integration.md>), [databricks](<https://devfeed.tech/topics/databricks.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [api](<https://devfeed.tech/tags/api.md>), [ci](<https://devfeed.tech/tags/ci.md>), [data](<https://devfeed.tech/tags/data.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [demo](<https://devfeed.tech/tags/demo.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [genie](<https://devfeed.tech/tags/genie.md>), [github](<https://devfeed.tech/tags/github.md>), [github-actions](<https://devfeed.tech/tags/github-actions.md>), [governance](<https://devfeed.tech/tags/governance.md>), [metric](<https://devfeed.tech/tags/metric.md>), [model](<https://devfeed.tech/tags/model.md>), [pages](<https://devfeed.tech/tags/pages.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [product](<https://devfeed.tech/tags/product.md>), [unity-catalog](<https://devfeed.tech/tags/unity-catalog.md>), [updates](<https://devfeed.tech/tags/updates.md>), [waste](<https://devfeed.tech/tags/waste.md>)

### AI overview

The demo uses a Unity Catalog Page as the shared definition of CI waste: paid GitHub Actions jobs that were rerun before finishing, canceled, or timed out; failed jobs alone do not count. The dltHub agent finds the definition, asks two questions to resolve gaps, turns the agreed rules into requirements, builds and checks an ingestion pipeline, then derives the data model, ontology, and metric view from those same rules. After deployment to Databricks, Genie answers from the metric view and cites the Page. New terms are proposed for human publication, and a person approves changes. For pipeline failures, a background agent reads Databricks logs and proposes a fix. The walkthrough presents this as a private preview; its claims about low upkeep and trusted answers describe the demo setup.

### Source excerpt

Demo walkthrough: one CI waste definition in a Unity Catalog Page drives the dlt pipeline, the model, the metric view and Genie's answer.

## Building pipelines has become easy. Knowing if they work correctly is now easy, too

DevFeed: [Building pipelines has become easy. Knowing if they work correctly is now easy, too](<https://devfeed.tech/articles/building-pipelines-has-become-easy-knowing-if-they-work-correctly-is-now-easy-too-115755.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/introducing-pipeline-observability>)

Author: Adrian Brudaru

Published: 2026-11-03T11:30:00Z

Content type: release

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [data observability](<https://devfeed.tech/topics/data-observability.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [alert](<https://devfeed.tech/tags/alert.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [api](<https://devfeed.tech/tags/api.md>), [availability](<https://devfeed.tech/tags/availability.md>), [context](<https://devfeed.tech/tags/context.md>), [context-graph](<https://devfeed.tech/tags/context-graph.md>), [data](<https://devfeed.tech/tags/data.md>), [general-availability](<https://devfeed.tech/tags/general-availability.md>), [graph](<https://devfeed.tech/tags/graph.md>), [interface](<https://devfeed.tech/tags/interface.md>), [missing-data](<https://devfeed.tech/tags/missing-data.md>), [observability](<https://devfeed.tech/tags/observability.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [product](<https://devfeed.tech/tags/product.md>), [ui](<https://devfeed.tech/tags/ui.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

dltHub's observability UI is generally available, with pipeline and run views plus configurable alerts to help teams investigate incomplete or unexpected data even when a run succeeds. The workspace overview highlights jobs needing attention; pipeline charts track success rate, rows, bytes, and duration over time. Run details show job pipelines and their row counts and statuses, while pipeline-run details list loaded tables, rows, bytes, duration, and logs. Teams can alert on failed runs and optionally successful ones by email or Slack, scoped to all jobs or selected pipelines; each alert links to the run and logs. The article notes that changes in row counts can flag issues such as late source data or repeated records, but require investigation rather than proving a failure. Run history, traces, and logs are also available to engineers through the UI and agents through MCP.

### Source excerpt

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.

## The future of data work, as discussed in a panel at Helsinki data week

DevFeed: [The future of data work, as discussed in a panel at Helsinki data week](<https://devfeed.tech/articles/the-future-of-data-work-as-discussed-in-a-panel-at-helsinki-data-week-107092.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/panel-future-data-teams>)

Author: Adrian Brudaru

Published: 2026-10-29T15:15:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [AI for data automation](<https://devfeed.tech/topics/ai-for-data-automation.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [elt](<https://devfeed.tech/topics/elt.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [actions](<https://devfeed.tech/tags/actions.md>), [added](<https://devfeed.tech/tags/added.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [agents](<https://devfeed.tech/tags/agents.md>), [community](<https://devfeed.tech/tags/community.md>), [data](<https://devfeed.tech/tags/data.md>), [data-teams](<https://devfeed.tech/tags/data-teams.md>), [discussion](<https://devfeed.tech/tags/discussion.md>), [future](<https://devfeed.tech/tags/future.md>), [motherduck](<https://devfeed.tech/tags/motherduck.md>), [panel](<https://devfeed.tech/tags/panel.md>), [summary](<https://devfeed.tech/tags/summary.md>), [teams](<https://devfeed.tech/tags/teams.md>), [tools](<https://devfeed.tech/tags/tools.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

The panel summary argues that data work is shifting from reporting toward operational automation, while individual gains from LLMs leave collaboration as an organizational bottleneck. It describes agents handling codifiable tasks and taking actions when paired with data and domain expertise; specialists provide ground truth for edge cases, making complex workflows practical to automate. It recommends learning through building and experimentation, alongside understanding data ingestion tradeoffs and virtual knowledge graphs or ontologies. The account assigns humans problem framing and solution selection, with LLMs useful for generating ideas. It also stresses safe experimentation after a reported PII leak, and says practitioners use human-like permission systems; MotherDuck and dltHub are described as handling security in their managed offerings. dltHub presented agent-assisted modeling of raw data into canonical models, with checks, deployment, and maintenance; MotherDuck presented an agentic analytics lifecycle.

### Source excerpt

Summary of the 16:00 Panel discussion: The future of data teams and their tools hosted by MotherDuck

## The post-AI data stack vs. the post-data AI stack

DevFeed: [The post-AI data stack vs. the post-data AI stack](<https://devfeed.tech/articles/the-post-ai-data-stack-vs-the-post-data-ai-stack-95215.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/post-ai-data-stack>)

Author: Adrian Brudaru

Published: 2026-10-22T09:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [analytics stack](<https://devfeed.tech/topics/analytics-stack.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [etl](<https://devfeed.tech/topics/etl.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Full Stack Development](<https://devfeed.tech/topics/full-stack-development.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [ads](<https://devfeed.tech/tags/ads.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data](<https://devfeed.tech/tags/ai-data.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [ai-stack](<https://devfeed.tech/tags/ai-stack.md>), [claude](<https://devfeed.tech/tags/claude.md>), [data](<https://devfeed.tech/tags/data.md>), [data-ai](<https://devfeed.tech/tags/data-ai.md>), [data-stack](<https://devfeed.tech/tags/data-stack.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [hubspot](<https://devfeed.tech/tags/hubspot.md>), [industry](<https://devfeed.tech/tags/industry.md>), [product](<https://devfeed.tech/tags/product.md>), [stack](<https://devfeed.tech/tags/stack.md>), [stripe](<https://devfeed.tech/tags/stripe.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

The article's central distinction is that direct connections from an AI assistant to SaaS systems work well for live, small-scale lookups and actions, but are unreliable for consistent questions across many records, systems, or time. It cites context limits (a page of 100 Stripe invoices can exceed the default context from one MCP call), HubSpot's 10,000-result search limit, weak long-context aggregation, APIs that expose current state, and results that may vary between runs. For historical, repeatable analysis, it recommends retaining data in a scalable online store and defining canonical entities, metrics, and segments as a source of truth. The proposed post-AI stack also includes unstructured data, repositories, company context, an agent harness, and AI-native interfaces. The excerpt notes that older human-oriented models may be unreliable for agents and that semantic-layer scope remains contested; it does not establish that every listed component is necessary.

### Source excerpt

A lot of teams now wire Claude straight into HubSpot, Stripe and Zendesk, and that's the data stack. It's good for today's questions, but ask about last quarter and it often can't tell you. This post covers where that breaks and what to add so it can answer what happened over time, consistently.

## Introducing job-inspector: dltHub's first verified agent for diagnosing failed pipelines

DevFeed: [Introducing job-inspector: dltHub's first verified agent for diagnosing failed pipelines](<https://devfeed.tech/articles/introducing-job-inspector-dlthub-s-first-verified-agent-for-diagnosing-failed-pipelines-80337.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/introducing-background-agents>)

Author: Elisabeth Reitmayr

Published: 2026-10-08T10:00:00Z

Content type: release

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [data observability](<https://devfeed.tech/topics/data-observability.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [all](<https://devfeed.tech/tags/all.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-quality](<https://devfeed.tech/tags/data-quality.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [diagnose](<https://devfeed.tech/tags/diagnose.md>), [dispatch](<https://devfeed.tech/tags/dispatch.md>), [docs](<https://devfeed.tech/tags/docs.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experts](<https://devfeed.tech/tags/experts.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [product](<https://devfeed.tech/tags/product.md>), [slack](<https://devfeed.tech/tags/slack.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

dltHub has released job-inspector in public preview as its first verified background agent. It diagnoses failed data pipeline jobs using run data, logs and job definitions, then reports a likely cause, confidence and supporting evidence to Slack. It operates with read-only access, while engineers review the diagnosis and decide on production fixes.

### Source excerpt

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.

## Towards a Self-Improving Autonomous Data Platform

DevFeed: [Towards a Self-Improving Autonomous Data Platform](<https://devfeed.tech/articles/towards-a-self-improving-autonomous-data-platform-80251.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/autonomous-data-platform>)

Author: Elisabeth Reitmayr

Published: 2026-09-15T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [data-platforms](<https://devfeed.tech/topics/data-platforms.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [data observability](<https://devfeed.tech/topics/data-observability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [automation](<https://devfeed.tech/tags/automation.md>), [context-graph](<https://devfeed.tech/tags/context-graph.md>), [data](<https://devfeed.tech/tags/data.md>), [platform](<https://devfeed.tech/tags/platform.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

The article describes dltHub's vision for an autonomous data platform, using a four-level ladder that gradually gives agents more responsibility for pipeline operations. It emphasizes risk-based approval, guardrails, observability, and a context graph that records actions and lineage. The article says dltHub is currently between the first and second levels, with further autonomy planned as its agent platform develops.

### Source excerpt

A data platform should run like a power grid: routine faults cleared automatically inside a bounded scope, anything risky escalated to a person. This is the four-level autonomy ladder dltHub is climbing, and the context graph that makes each step safe to take.

## Reverse ETL to Attio

DevFeed: [Reverse ETL to Attio](<https://devfeed.tech/articles/reverse-etl-to-attio-80387.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/reverse-etl-dlt-custom-destination>)

Author: Aman Gupta

Published: 2026-09-08T00:00:00Z

Content type: tutorial

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [etl](<https://devfeed.tech/topics/etl.md>), [DuckDB](<https://devfeed.tech/topics/duckdb.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [crm](<https://devfeed.tech/tags/crm.md>), [duckdb](<https://devfeed.tech/tags/duckdb.md>), [has](<https://devfeed.tech/tags/has.md>), [product](<https://devfeed.tech/tags/product.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

A walkthrough shows how dltHub AI Harness builds a three-stage GTM workflow: ingest job postings into DuckDB, enrich company and people records with People Data Labs, then write them to Attio using a custom reverse-ETL destination. It describes deduplication, upserts, API throughput, and how a shared canonical data model could help as the pipeline expands.

### Source excerpt

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.

## From Raw Tables to Conversational Analytics in One Afternoon

DevFeed: [From Raw Tables to Conversational Analytics in One Afternoon](<https://devfeed.tech/articles/from-raw-tables-to-conversational-analytics-in-one-afternoon-80254.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/bigquery-property-graph-dlt>)

Author: Roshni Melwani

Published: 2026-09-01T00:00:00Z

Content type: tutorial

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [BigQuery](<https://devfeed.tech/topics/bigquery.md>), [JOIN](<https://devfeed.tech/topics/join.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Analytics Pipeline](<https://devfeed.tech/topics/analytics-pipeline.md>), [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>)

Tags: [bigquery](<https://devfeed.tech/tags/bigquery.md>), [database](<https://devfeed.tech/tags/database.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gql](<https://devfeed.tech/tags/gql.md>), [graph](<https://devfeed.tech/tags/graph.md>), [models](<https://devfeed.tech/tags/models.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

The article demonstrates a workflow that loads the Chinook relational dataset into BigQuery with dlt, creates canonical views, declares a property graph, and queries it with GQL. It also tests BigQuery Conversational Analytics on a natural-language question, reporting a correct answer and generated query. The article argues that resolving business meaning in the canonical model helps the graph and conversational interface produce useful results.

### Source excerpt

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. The ontology resolved in the first step is what makes the answers right at the end.

## Why Human Accountability Still Matters in AI-Built Data Pipelines

DevFeed: [Why Human Accountability Still Matters in AI-Built Data Pipelines](<https://devfeed.tech/articles/why-you-still-need-data-people-in-the-agentic-era-what-for-80242.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/ai-data-pipelines-accountability-dlthub>)

Author: Adrian Brudaru

Published: 2026-08-25T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [DataOps](<https://devfeed.tech/topics/dataops.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [data-engineers](<https://devfeed.tech/tags/data-engineers.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

The article argues that AI agents can speed up building data warehouses and pipelines, but cannot take responsibility for business decisions such as metric definitions. It emphasizes that human accountability, domain knowledge, and team knowledge transfer remain central to data work.

### Source excerpt

AI can automate data pipelines, but only humans can own business accountability.

## Step by step: Hubspot connector from Fivetran to dlthub

DevFeed: [Step by step: Hubspot connector from Fivetran to dlthub](<https://devfeed.tech/articles/step-by-step-hubspot-connector-from-fivetran-to-dlthub-80334.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/hubspot-connector-fivetran-to-dlthub>)

Author: Aman Gupta

Published: 2026-08-18T00:00:00Z

Content type: tutorial

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [build vs buy database solutions](<https://devfeed.tech/topics/build-vs-buy-database-solutions.md>), [Reverse Engineering](<https://devfeed.tech/topics/reverse-engineering.md>), [elt](<https://devfeed.tech/topics/elt.md>), [hubspot](<https://devfeed.tech/topics/hubspot.md>), [etl](<https://devfeed.tech/topics/etl.md>), [API Business Models](<https://devfeed.tech/topics/api-business-models.md>), [API Monetization](<https://devfeed.tech/topics/api-monetization.md>)

Tags: [code-review](<https://devfeed.tech/tags/code-review.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [hubspot](<https://devfeed.tech/tags/hubspot.md>), [product](<https://devfeed.tech/tags/product.md>), [reverse-engineering](<https://devfeed.tech/tags/reverse-engineering.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

This tutorial explains migrating a HubSpot sales data pipeline from Fivetran to dlt. It covers reverse-engineering the connector's schema, rebuilding the pipeline and 13 dbt models, and validating the results. The validation uncovered undocumented field renaming, routing behavior, and expected differences in data freshness and timestamp representation.

### Source excerpt

Migrating a HubSpot pipeline from Fivetran to dlt: reverse-engineering the vendor schema, rebuilding the load and 13 dbt models.

## dltHub adds team workspaces, agentic alerts, and managed infrastructure for data pipelines

DevFeed: [dltHub adds team workspaces, agentic alerts, and managed infrastructure for data pipelines](<https://devfeed.tech/articles/dlthub-dlt-made-agents-good-at-building-pipelines-now-they-re-safe-enough-to-run-for-your-whole-team-80308.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/dlthub-for-teams>)

Author: Matthaus Krzykowski

Published: 2026-08-06T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [ci](<https://devfeed.tech/tags/ci.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [product](<https://devfeed.tech/tags/product.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

dltHub presents its platform for data teams using coding agents to build and operate data pipelines. Its AI Harness provides pipeline skills and production context, while agentic alerts help diagnose and validate failures. Team workspaces support staging and production separation, Git based review and deployment, and managed infrastructure for scaling pipeline workloads. The article also describes roadmap plans for temporary workspaces for pull requests.

### Source excerpt

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.

## Validating Trust in Data: How dltHub Delivers GxP-Ready, Auditable Ingestion into Snowflake

DevFeed: [Validating Trust in Data: How dltHub Delivers GxP-Ready, Auditable Ingestion into Snowflake](<https://devfeed.tech/articles/validating-trust-in-data-how-dlthub-delivers-gxp-ready-auditable-ingestion-into-snowflake-80428.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/validating-trust-in-data-how-dlthub-delivers-gxp-ready-auditable-ingestion-into-snowflake>)

Author: Matthaus Krzykowski

Published: 2026-08-04T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Snowflake streaming data architecture](<https://devfeed.tech/topics/snowflake-streaming-data-architecture.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [etl](<https://devfeed.tech/topics/etl.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ci](<https://devfeed.tech/tags/ci.md>), [coding](<https://devfeed.tech/tags/coding.md>), [product](<https://devfeed.tech/tags/product.md>), [snowflake](<https://devfeed.tech/tags/snowflake.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

The article describes dltHub's code-native data ingestion approach for regulated life sciences. Pipelines are versioned and tested, while the context catalog records lineage, schema, and run evidence to support audits and governed changes. Snowflake is the featured destination, and coding agents can help build and operate pipelines under review.

### Source excerpt

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 that lands in Snowflake with the lineage, tests, and evidence regulators expect.

## Transformations that use shared context for data workflows

DevFeed: [Transformations that use shared context for data workflows](<https://devfeed.tech/articles/transformations-that-know-their-context-80425.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/transformations-that-know-their-context>)

Author: Adrian Brudaru

Published: 2026-08-03T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [data](<https://devfeed.tech/tags/data.md>), [data-mesh](<https://devfeed.tech/tags/data-mesh.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

The article presents dltHub's native transformations and its option to run existing dbt projects after ingestion. It describes a shared runtime and metadata context for schemas, lineage, annotations, and run state, along with scheduling and event-based job triggers. The article also explains how these features are intended to support centralized, decentralized, and AI-native data teams.

### Source excerpt

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. Let's dive in!

## Composable canonicals: from tribal data knowledge to versioned artifact

DevFeed: [Composable canonicals: from tribal data knowledge to versioned artifact](<https://devfeed.tech/articles/composable-canonicals-from-tribal-data-knowledge-to-versioned-artifact-80264.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/composable-canonicals>)

Author: Adrian Brudaru

Published: 2026-07-29T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [Analytics Pipeline](<https://devfeed.tech/topics/analytics-pipeline.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [data](<https://devfeed.tech/tags/data.md>), [data-engineers](<https://devfeed.tech/tags/data-engineers.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

The article proposes using composable canonical data models and LLMs to capture domain knowledge across teams. It describes inferring schemas, bootstrapping an ontology, and combining source-specific models into a shared customer model that resolves identity and definitions across systems.

### Source excerpt

In this article, I'm exploring an AI-native architecture that aims to solve the traditional central data team problem.

## dlt vs dltHub: the five ecosystem layers dltHub adds

DevFeed: [dlt vs dltHub: the five ecosystem layers dltHub adds](<https://devfeed.tech/articles/dlt-vs-dlthub-the-five-ecosystem-layers-dlthub-adds-80321.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/from-dlt-to-dlthub>)

Author: Adrian Brudaru

Published: 2026-07-22T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [DataOps](<https://devfeed.tech/topics/dataops.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [libSQL](<https://devfeed.tech/topics/libsql.md>)

Tags: [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-platform](<https://devfeed.tech/tags/data-platform.md>), [database](<https://devfeed.tech/tags/database.md>), [infra](<https://devfeed.tech/tags/infra.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

dltHub presents a platform around the dlt data ingestion library, adding an AI harness, context catalog, transformations, orchestration, and managed infrastructure. It describes features for operating and deploying pipelines, including structured run data for people and agents, and says agents can test fixes and wait for confirmation before deployment.

### Source excerpt

dlt handles ingestion. dltHub adds the five ecosystem layers you'd otherwise build yourself: AI harness, context catalog, transformation, orchestration, managed infra.

## Moving off Airbyte

DevFeed: [Moving off Airbyte](<https://devfeed.tech/articles/moving-off-airbyte-80348.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/migrate-from-airbyte-to-dlthub>)

Author: Adrian Brudaru

Published: 2026-07-21T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [DLT](<https://devfeed.tech/topics/data-load-tool.md>), [data observability](<https://devfeed.tech/topics/data-observability.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [cost](<https://devfeed.tech/tags/cost.md>), [devops](<https://devfeed.tech/tags/devops.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

The article compares moving data pipelines from Airbyte to dltHub, describing effects on operating effort, costs, reliability, and who can author and maintain pipelines. It presents dltHub's agent-assisted pipeline building and maintenance, usage-based infrastructure pricing, and reported 99.83% pipeline success across recent open-source production runs.

### Source excerpt

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.

## Productionize Python ETL Scripts: Migrate to dlt & dltHub

DevFeed: [Productionize Python ETL Scripts: Migrate to dlt & dltHub](<https://devfeed.tech/articles/productionize-python-etl-scripts-migrate-to-dlt-dlthub-80377.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/productionize-python-etl-scripts>)

Author: Adrian Brudaru

Published: 2026-07-15T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [DLT](<https://devfeed.tech/topics/data-load-tool.md>), [etl](<https://devfeed.tech/topics/etl.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [etl](<https://devfeed.tech/tags/etl.md>), [python](<https://devfeed.tech/tags/python.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

The article describes how dlt and dltHub can help turn hand-built Python ETL pipelines into production data workflows. It discusses schema evolution, incremental state, parallelism, failure recovery, deployment, maintenance, and team accessibility, and promotes dltHub's managed infrastructure and agent-assisted operations.

### Source excerpt

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.

## Migrating from Fivetran: how the move actually works

DevFeed: [Migrating from Fivetran: how the move actually works](<https://devfeed.tech/articles/migrating-from-fivetran-how-the-move-actually-works-80347.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/migrate-fivetran-to-dlthub>)

Author: Adrian Brudaru

Published: 2026-07-14T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [aws](<https://devfeed.tech/tags/aws.md>), [generation](<https://devfeed.tech/tags/generation.md>), [tutorials](<https://devfeed.tech/tags/tutorials.md>)

### AI overview

The article describes migrating data pipelines from Fivetran to dltHub, covering infrastructure-based pricing, migration effort, and the platform's pipeline management features. It also makes vendor claims about LLM-generated pipelines, reliability, and maintenance.

### Source excerpt

What does the move do to my bill and my renewal? And how to move?

## dltHub introduces LLM-assisted migration blueprints for data pipelines

DevFeed: [dltHub introduces LLM-assisted migration blueprints for data pipelines](<https://devfeed.tech/articles/consulting-is-becoming-software-80267.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/consulting-is-becoming-software>)

Author: Matthaus Krzykowski

Published: 2026-07-09T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>)

Tags: [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [llm](<https://devfeed.tech/tags/llm.md>), [migration](<https://devfeed.tech/tags/migration.md>), [product](<https://devfeed.tech/tags/product.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

dltHub presents four migration blueprints for moving Python scripts, dlt, Fivetran, and Airbyte pipelines to dltHub. It argues that LLM-native tools can codify migration work into agent-run skills overseen by existing engineers, reducing projects that once took months to weeks and lowering costs. The post also describes dltHub's context layer, which gives agents access to pipeline schemas, lineage, traces, and runtime state.

### Source excerpt

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.

[Next page](<https://devfeed.tech/sources/dlt-hub.md?cursor=WyIyMDI2LTA3LTA5VDAwOjAwOjAwKzAwOjAwIiwgImRlZjg1YjdjLTUxMzUtNDk0MC05NmI1LTEyMDc4OTRjYzA3NiJd>)