Products
Data-Agents Swarmagents that detect, fix & govern your stackData Context Wizardthe cross-cloud memory your agents can trustSpellbook Data Catalogcommand, approve & audit the fleetAutonomous Data-Conductorloop engineering for data - the autonomous orchestratorPricingMerch
Book a DemoPilot Program

Blog

Thoughts on the future of data infrastructure.

Industry

Pricing Report 2026 on the Agentic Data Industry

Nineteen vendors invented their own billing unit. Ten apply a margin to model tokens. One publishes the multiplier. A complete map of published pricing - with sources - and the total-cost arithmetic behind our claim. A survey of 52 published pricing pages and why we are hands down the best price in the market.

14 min read
Product

Inside the Pipeline Building Agent

Pipeline work is the quiet tax on every data team: weeks of boilerplate, brittle jobs that break at 3 AM, and a request queue that never shrinks. The Pipeline Building Agent turns a plain-English description into a tested, deployed pipeline - and keeps it alive.

9 min read
Product

Inside the Incident Debugging Agent

On-call for data is a slow, lonely 3 AM root-cause hunt - and half the time the data was quietly wrong for days before anyone noticed. The Incident Debugging Agent detects the break in seconds, traces the cause, and resolves the reversible incidents on its own.

7 min read
Product

Inside the Quality Monitoring Agent

Most data is wrong long before anyone notices, and the teams who wire up alerts just drown in noise. The Quality Monitoring Agent learns each dataset's baseline, surfaces only the anomalies that matter, and fixes the reversible ones on its own.

7 min read
Product

Inside the Schema Evolution Agent

Upstream schema changes are the number-one way data pipelines break, and the fix is still a manual, multi-day scramble across four tools. The Schema Evolution Agent detects the change on landing, maps its full blast radius, and authors the migration for a single review.

7 min read
Product

Inside the Data Change Review Agent

Code review answers "does this read well?" - never "what did it do to the data?" So the fan-out that doubled revenue passes inspection and surfaces weeks later. The Data Change Review Agent diffs the data impact and renders a risk verdict before a change can merge.

7 min read
Product

Inside the Data Access & Governance Agent

Access takes days of tickets; audits take a 400-hour scramble; the policy doc gathers dust. The Data Access & Governance Agent turns governance into executable, self-enforcing code - least-privilege access in minutes, with a full audit trail.

7 min read
Product

Inside the Data Security Agent

Sensitive data sits exposed, the misconfig is real, the secret is committed - and the finding waits in a dashboard nobody acts on. The Data Security Agent unifies data and cloud posture into one ranked list and routes each finding to the agent that fixes it.

7 min read
Product

Inside the Identity Agent

"Who is this?" and "who did this?" rarely have a clean answer when one person is six usernames and actions hide behind shared service logins. The Identity Agent resolves every actor - human, service account, or agent - to one identity, and attributes every action.

6 min read
Product

Inside the Cost Savings & Data Cleanup Agent

Warehouse bills arrive as surprises, and the manual audit to explain them is stale before it's finished. The Cost Savings & Data Cleanup Agent attributes spend to the exact cause, finds the stale data and idle compute, and reclaims the waste it can prove is safe.

7 min read
Product

Inside the Data Migration Agent

Warehouse migrations run for quarters - not because moving data is hard, but because translating the logic and proving the result matches is. The Data Migration Agent runs the translate-validate-prove-parity loop and gates the cutover for a single sign-off.

8 min read
Product

Inside the Data Science & Insights Agent

Data teams burn their week as a human query engine, and self-service BI still routes everything back to them. The Data Science & Insights Agent answers plain-English questions in seconds - charted, cited to the source, and digging into the why.

7 min read
Product

Inside the MLOps & Models Agent

ML in production is mostly plumbing, and models rot silently once they ship. The MLOps & Models Agent runs the whole lifecycle - features, training, a versioned registry, canary deploys, and drift detection - so a small team ships and keeps a model honest.

7 min read
Product

Inside the Observability Agent

You usually learn a pipeline broke from a stakeholder, and the silent drift never trips an alert at all. The Observability Agent watches the whole stack and the agents on it, correlates a symptom to its upstream cause, and hands the fix a reason - not just an alert.

7 min read
Product

Inside the Real-Time Streaming Agent

Streaming is gated on one scarce skill and a lifetime of operating lag, backpressure, and CDC. The Real-Time Streaming Agent turns a plain-English spec into a configured topology, then continuously tunes and holds the SLA - on top of the Kafka you already run.

7 min read
Product

Inside the Conductor Agent

The orchestration layer became its own full-time job, and no one owns the cross-team fix. The Conductor Agent is the control plane: it decides what runs, routes it to the right specialist, sequences the work, and gates the irreversible for a human.

7 min read
Product

Inside the Data Ingestion Agent

Ingestion is the most fragile, least-owned, most-rewritten code in the stack: it breaks on the first messy file and double-loads on a re-run. The Data Ingestion Agent lands raw sources idempotently, dedupes by key, runs reversible backfills, and reroutes around outages.

6 min read
Product

Inside the Search & Research Agent

Answering one question means hunting across the catalog, Slack, the open web - and then arguing about which number is right. The Search & Research Agent searches everywhere at once, names the authoritative source, and returns a cited conclusion.

6 min read
Product

Inside the Data Context & Catalog Agent

Analysts spend more time hunting for the right table than using it, and the catalog meant to fix that goes stale the moment nobody maintains it. The Data Context & Catalog Agent answers in seconds across every platform, sources every fact, and documents itself.

7 min read
Product

Inside the Usage Intelligence Agent

Teams ship hundreds of dashboards, can't prove who uses what, and can't justify the data team's value. The Usage Intelligence Agent reads the tool calls themselves - surfacing adoption, workflows, power users, and shelfware, continuously.

7 min read
Product

Inside the Connectors Agent

Connectors break on every upstream change, bill you per row, and quietly eat a data team's week. The Connectors Agent makes integration a shared substrate - one endpoint, the plumbing handled, every source change an event the swarm reacts to.

6 min read
Industry

Databricks Genie Ontology vs Data Workers: A Fair Comparison

Databricks' Genie Ontology validates that AI agents need trusted context. A fair comparison with Data Workers' cross-platform, human-governed context approach.

8 min read
Product

Meet the Data Guardrail Agent: Code Review's Missing Half

The Data Guardrail Agent diffs your data between environments, buckets the risk, and hands HIGH-risk findings to remediation agents as structured tool calls.

6 min read
Engineering

What Ralph Kimball's Dimensional Modeling Taught Our Pipelines Agent

Ralph Kimball's four-step dimensional design process is one of the most durable ideas in data engineering - here is what it taught our pipelines agent.

7 min read
Engineering

What Jay Kreps's Log-Centric Architecture Taught Our Streaming Agent

Jay Kreps's core insight is deceptively simple: an append-only, totally-ordered log is not just a message bus - it is the single source of truth that eliminates N² integration pipelines and makes reprocessing routine. We studied his published writing and built a reusable streaming skill around the method.

8 min read
Engineering

What W. Edwards Deming's Plan-Do-Study-Act Taught Our Data Quality Agent

W. Edwards Deming spent a career arguing that quality comes from improving the process, not inspecting for defects. His Plan-Do-Study-Act cycle is the most rigorous improvement loop in the field. Here is how we encoded it into our data quality agent.

8 min read
Engineering

What Charity Majors's Wide-Event Method Taught Our Observability Agent

Charity Majors's core insight - emit wide, store raw, slice later - turns out to be exactly the right architecture for an agent that has to debug things it was never told to expect.

8 min read
Engineering

What John Allspaw's Blameless Postmortem Method Taught Our Incident Analysis Agent

John Allspaw's blameless postmortem method is not just a culture document - it is a precise analytical framework. Here is what encoding it into a swarm agent actually required.

7 min read
Engineering

What Martin Kleppmann's Evolutionary Compatibility Method Taught Our Schema Agent

Martin Kleppmann's core insight is that schema changes are never instantaneous: producers and consumers always run different versions simultaneously, so every change must be safe in both directions at once.

7 min read
Engineering

What Andrew Ng's Data-Centric AI Method Taught Our Machine Learning Agent

Andrew Ng's data-centric AI framework reframes the ML improvement loop: hold the model constant and fix the data first. Here is how that method shaped the dw-ml agent.

8 min read
Engineering

What Martin Fowler's Evolutionary Database Design Taught Our Migration Agent

Martin Fowler's evolutionary database design method - decompose, track, parallel-change, validate - is the clearest framework we know for moving a production warehouse without a maintenance window.

7 min read
Engineering

What Corey Quinn's Architecture-as-Cost Method Taught Our Cost Agent

Corey Quinn's core insight is that your AWS bill is not a finance problem - it is a direct readout of every architectural decision your team made. Here is how that principle shaped the way our cost agent thinks.

7 min read
Engineering

What DJ Patil's Five-C Ethical Checklist Taught Our Governance Agent

DJ Patil's core insight is that data ethics oaths give cover to unethical work while checklists connect principle to practice - and that distinction shaped how we built the dw-governance agent.

7 min read
Engineering

What Bruce Schneier's Adversarial Security Thinking Taught Our Security Agent

Bruce Schneier's core insight is deceptively simple: good engineering asks how systems work; security thinking asks how they fail. Here is how that adversarial method runs inside our security agent.

8 min read
Engineering

What Benn Stancil's Trust-Signal Method Taught Our Context Catalog Agent

Benn Stancil has spent years arguing that data's real problem is not technical accuracy but trust legibility - and that insight turns out to be a precise blueprint for a catalog agent.

7 min read
Engineering

What Joe Reis's Data Engineering Lifecycle Taught Our Connectors Agent

Joe Reis's core insight is that data engineering is a lifecycle, not a toolset, and the lifecycle persists long after any specific tool is replaced.

8 min read
Engineering

What Zhamak Dehghani's Data Mesh Taught Our Catalog Agent

Zhamak Dehghani's data mesh reframed the catalog problem: ownership and product fitness matter more than where data lives. Here is how that method shaped the dw-connectors-catalog agent.

7 min read
Engineering

What Gregor Hohpe's Enterprise Integration Patterns Taught Our Connector Agent

Gregor Hohpe spent two decades watching enterprises fail at integration the same way. His pattern language - async by default, coupling named by dimension, correlation spanning the whole conversation - turns out to be exactly what a connector agent needs.

7 min read
Engineering

What Doug Turnbull's Judgment-First Search Method Taught Our Search Agent

Doug Turnbull's core insight is simple and hard to internalize: before you tune any retrieval component, you need a judgment list. Here is what that principle looks like encoded into an agent.

7 min read
Engineering

What John Cutler's Data-Informed Product Cycle Taught Our Usage Intelligence Agent

John Cutler's data-informed product cycle reframes measurement as a learning practice - here is how we encoded that discipline into the agent that watches how our own tools are used.

8 min read
Engineering

What Simon Willison's Friction-Free Learning Method Taught Our Open-Source Agent

Simon Willison's TIL practice and vibe engineering framework encode a surprisingly rigorous method: drop the publishing bar to almost nothing, stay accountable for every output, and choose the simplest tool that survives contact with reality.

7 min read
Comparison

Atlan Alternatives: 6 Open-Source Data Catalogs Compared (2026)

Atlan is a strong catalog, but six open-source options cover the same surface area for zero license cost. Here is the honest matrix - strengths, gaps, where each one is genuinely better, and where you should still pay.

10 min read
Tutorial

MCP Servers for BI Tools: Looker, Tableau, Power BI, Mode (2026)

BI tools hold the highest-trust definitions in most companies - and they are the last surface to get connected to AI agents. Here is what is shipping in 2026.

8 min read
Tutorial

How to Give Claude Access to Snowflake Without Exposing PII

MCP servers make it trivial to connect Claude to Snowflake. They also make it trivial to leak PII to a model that just wants to be helpful. Here is how to do it without that risk.

9 min read
Product

Why AI Agents Hallucinate on Your Data (And How to Fix It)

AI agents writing SQL against your data warehouse get it wrong 66% more often without semantic grounding. Here is why context is the missing layer in every data stack - and what we are building to fix it.

10 min read
Industry

The Context and Semantic Layer Market: Why Nobody Has Solved This Yet

We mapped the entire landscape of data context and semantic layer tools. Here is what we found and where the gaps are.

12 min read
Industry

What We Learned Studying the Data Engineering Market Before Building

Before we wrote a single line of product code, we spent four months doing something unsexy: reading earnings calls, mapping vendor acquisitions, talking to data engineers, and building spreadsheets of market gaps.

10 min read
Engineering

Why We Bet on MCP (And What We're Still Figuring Out)

When we started building Data Workers, we had to make a foundational decision: how do our AI agents connect to the dozens of tools in a modern data stack?

8 min read
Industry

Why Your Data Stack Still Needs Humans at 2 AM

It is 2026 and your data pipeline still breaks at 2 AM. Not because you chose bad tools. Because the fundamental problems of data engineering are genuinely hard.

7 min read
Product

Copilots, Agents, and Swarms: A Decision Framework for Data Teams

The AI discourse in data engineering has collapsed into a single word: agents. Every vendor is an "agent" now. The word has lost meaning.

8 min read
Engineering

Building an Incident Debugging Agent: What We've Learned So Far

Incident debugging is where we started building. Not because it is the easiest problem, but because it is the most painful.

12 min read
Product

Our Agent Roadmap: What We've Built, What We're Building, and Why

The average data team spends 60-70% of their time on reactive maintenance. Here is how 11 specialized agents address that - and why the order we build them matters more than the features.

12 min read
Engineering

Your Data Governance Is a PDF Nobody Reads

Most enterprises have governance policies documented in PDFs that gather dust. We are building an agent that turns them into executable code.

9 min read
Industry

Why Your Data Stack Needs an ML Agent (Not Just a Notebook)

The notebook-to-production gap kills more ML projects than bad algorithms. An ML agent that lives inside your data stack closes that gap.

11 min read
Engineering

Why Your 200 DAGs Need a Brain (Not Another Dashboard)

Your orchestrator runs DAGs. But it does not know that three of them have undocumented dependencies that cause cascade failures every month.

8 min read
Engineering

Dear Open Claw: Your Data Stack Is Now an MCP Call Away

An open letter to AI coding agents, data agents, and autonomous systems everywhere. We built 202 MCP tools across 14 specialized agents so you can query catalogs, build pipelines, debug incidents, and govern data - without guessing. Here is how to use them.

9 min read
Engineering

Why We Open-Sourced 14 Autonomous Data Engineering Agents

We released 14 MCP-first autonomous agents for data engineering under Apache 2.0. Here is why we chose radical transparency over a black-box product, and how the trust model works.

9 min read
Industry

Why Every MCP Server for MLOps Is Read-Only (And Why That Is About to Change)

The MCP ecosystem exploded in 2026. Every major MLOps platform shipped an MCP server. But they all share one blind spot: none of them can actually operate your ML infrastructure. Here is why that matters and what comes next.

10 min read
Engineering

What Glenn McDonald's Data Alchemy Taught Our Analytics Agent

The best data people carry mental models you can't get from a tutorial. We studied Glenn McDonald's public work - the self-described Data Alchemist and creator of Every Noise at Once - and built a reusable analytics skill around his method. Here is what we learned, and why it is one of more than 400 skills we have built.

8 min read
Engineering

What Maxime Beauchemin's Functional Data Engineering Taught Our Orchestration Agent

Maxime Beauchemin - creator of Apache Airflow - argued that ETL pain mostly comes from one design error: tasks with side-effects. His functional data engineering method fixes it. Here is how we encoded it into our orchestration agent.

9 min read