Blog
Insights on agentic data engineering and how modern platforms are opening the web's data.
Knowledge BaseSep 3, 2026Why business context should come before building semantic layers
Why is appetite for semantic layers so high when adoption is thin? Learn why semantic layers need resolved business context and well-modeled data before AI agents can build accurate, governed data models.
Knowledge BaseAug 28, 2026Reverse-engineering a chart of accounts you inherited
A data team has to turn accumulated judgement into a repeatable system. A dashboard answers one question, but the record of how those numbers are defined improves every financial data project that follows.
Knowledge BaseAug 28, 2026The case for spec-driven development in analytics engineering
Spec-driven development can give agents the structure to find the business rules, resolve the open decisions, define what correct means, then build against the spec.
Knowledge BaseAug 10, 2026The spec is the new source code
When implementation becomes abundant, the bottleneck moves upstream: can you describe business rules precisely enough for an agent to build with all the right assumptions baked in?
Knowledge BaseJul 30, 2026How to steer coding agents amid rising token costs
How should engineering teams get more out of every agent run? Through two jobs: reading the trace of agent activity, and knowing the organization’s specific business logic well enough to minimize agent prompt loops.
Knowledge BaseJul 21, 2026Before you work with a coding agent, talk to Robert
"Value creation comes from Robert, who has been here for twenty years and has never documented anything." Every business has a Robert you should go talk to before automating code that relies on accurately capturing your business logic.
Knowledge BaseJun 15, 2026A data pipeline that argues for its own correctness
Verification has always been part of data engineering: profiling columns, testing keys with dbt, checking how tables relate. With a self-verifying system, what’s new is where the checks come from: derived directly from the business logic behind a transformation and generated alongside the pipeline, instead of added by a human afterward.
Knowledge BaseMay 6, 2026What is Data Harmonization? (And Why Your Business Needs It)
Knowledge BaseMar 6, 2026The questions every CFO should ask before buying another AI tool
Knowledge BaseMar 5, 2026The 2026 CFO AI stack
Knowledge BaseFeb 26, 2026AI in Excel is the most exciting way to solve the wrong problem.
Knowledge BaseFeb 17, 2026A semantic layer is not enough for agentic enterprise.