Author
Toby Mather
Co-founder and CEO, Rig. Toby co-founded Rig after seeing how hard it was for business teams and AI to work with complex internal data. He was previously co-founder and CEO of Lingumi and CPO at Novakid.
Toby Mather on LinkedInPosts by Toby Mather
An AI policy PDF has never stopped a query
An AI governance framework for data access sets out who, and which agents, can query which data, under which policy, and how every query is logged.
ReadAn MCP gateway is how you stop a server being a free-for-all
An MCP gateway is a control point in front of your warehouse. Each person and agent gets a role, a token and a log in place of a shared database password.
ReadAre the metrics on Snowflake yet, or just the tables?
Inventory sources and pipelines, move the data, rebuild metrics as semantic views or an equivalent layer, run in parallel, then cut over to Snowflake.
ReadCan we stop calling a chatbot on raw tables a company brain?
A company brain is a governed map of your company data that staff and AI agents can ask, built on the warehouse you already run. Here is the build order.
ReadESU is not a migration plan
SQL Server 2016 went out of support on 14 July 2026. Inventory the SSRS reports and Crystal documents people use, then cut over. ESU runs to 17 July 2029.
ReadEveryone's banging on about context, but what actually is it?
A context layer is a navigational map of systems, metric definitions and business meanings. The facts on a deal belong in the warehouse, away from memory files.
ReadFabric, Snowflake or Databricks: maybe look at the estate first?
Inventory pipelines, reports and metrics, then choose Fabric, Snowflake or Databricks against that inventory. Rebuild the metrics once, then cut over.
ReadHorizon and Unity Catalog still won’t tell you which agent ran the query
How Snowflake Horizon, Unity Catalog, BigQuery and Fabric with Purview control what AI agents can query, and what a gateway adds when agents share a login.
ReadHow far do Snowflake Semantic Views actually get you?
Snowflake semantic views keep metrics, dimensions and relationships in the database under normal RBAC. Agents still need a context layer and their own access.
ReadI wouldn't let an agent loose on a Databricks metric view and nothing else
Databricks metric views give you a semantic layer in Unity Catalog. Here is what they cover, and what agents still need: a role, row limits and a log.
ReadI'd stop treating a Power BI model like the company brain
A Power BI semantic model is built for Power BI reports. Keep shared metrics in a warehouse semantic layer so other tools and AI agents use the same definitions.
ReadIf dbt holds the metrics, who decides who can query them?
dbt keeps metrics in your project; Snowflake semantic views and Databricks metric views keep them in the engine. Neither alone decides which agent may query them.
ReadIf you just lift the dashboards, you haven’t migrated
How to move reports and metrics off Cognos, SAP BusinessObjects or MicroStrategy in 2026: inventory, a warehouse semantic layer, a parallel run, then cutover.
ReadLanding the tables in Databricks does not mean you’re done
Move data and pipelines onto the lakehouse, register them in Unity Catalog, rebuild metrics as metric views, run in parallel, then cut over to Databricks.
ReadLeave Looker, keep the metrics
Inventory Looks, dashboards and LookML, rebuild the metrics in a warehouse semantic layer, then point a new BI tool at it. Keep governed metrics and permissions.
ReadLeave the metric mess behind when you leave Power BI
Inventory the reports and semantic models people still use, rebuild the metrics in a warehouse semantic layer, run both in parallel, then cut over.
ReadNobody needs the whole enterprise context layer on day one
Build an enterprise context layer one domain at a time, from a table inventory and agreed metrics to ownership, access and a gateway for agents.
ReadPlease stop giving agents the warehouse password
An MCP server exposes tools and data to AI clients. For a warehouse, run each call as a named agent, against certified metrics, with a log of every call.
ReadPointing Genie at raw tables is a fun way to get confident wrong answers
Genie answers well when metrics live in Unity Catalog metric views and each caller sees only their rows. This guide covers the setup, from metric views to access.
ReadReporting is the bit that usually breaks in a CRM migration
Inventory objects, map customers and owners, run both CRMs in parallel and cut over with a row-level check. History, activity and permissions usually slip.
ReadRevenue Cloud can wait five minutes while you find the quote history
Inventory product, price and quote data, choose Revenue Cloud or another CPQ, run both in parallel, then cut over. Check Salesforce’s current CPQ status first.
ReadSemantics, ontology, context... buzzword bingo, or business value?
Semantic layer, ontology, context layer and knowledge graph are four different things. An agent needs the first three to find the agreed number.
ReadSkip the metric map and the checklist was a waste of time
A shared checklist for moving reports and metrics off a BI tool: inventory what is still used, map the metrics, run old and new in parallel, then cut over.
ReadThe metrics need a home when QlikView goes away
Inventory the apps people still open, rebuild metrics and access in a warehouse semantic layer, run in parallel, then cut over. Stay in Qlik or move tools.
ReadThe metrics should not be hiding in the ingest tool
ELT loads data into the warehouse first and transforms it there, while ETL transforms it before load. When to use each, and where metric definitions belong.
ReadTwo report packs after a deal is how operating partners start arguing
A checklist for the systems and data work after an acquisition: inventory, what to keep, customer and product mapping, history, and a shared reporting layer.
ReadWhat’s the plan for the metrics when the Tableau workbooks move?
Inventory workbooks and data sources, rebuild metrics in a warehouse semantic layer, run old and new in parallel, then cut over. Power BI is one of several targets.
ReadWhere do the metrics live once Fivetran is gone?
Inventory every connector and schedule, stand up the replacement ingest, run both until the row counts match, then cut over. Metrics belong in the warehouse.
ReadWho is Claude logged in as, once you've connected it to Snowflake?
Connect Claude, ChatGPT or Cursor to Snowflake, BigQuery or Databricks over MCP, with certified metrics, a role for each agent and a log of every query.
ReadWho’s looking after the metrics while the pipelines move?
Inventory sources and pipelines, map the metrics people use, run old and new in parallel, then cut over. Works for Snowflake, Databricks, BigQuery or Fabric.
ReadWTF is a semantic layer anyway?
A semantic layer is a dictionary of definitions for business numbers. Each BI tool used to keep its own, in a format agents could not read. Apache Ossie opens it up.
Read