Case study Financial Services / Snowflake, Snowflake Cortex, Copilot Studio, MCP, Agentic Workflow, Semantic Views

Governed Answers with Snowflake Cortex and Microsoft Copilot

A UK digital bank's users ask one Copilot assistant in Teams and Dynamics 365 and get governed answers from Snowflake, SharePoint and an external API, under their own permissions.

Headline result 3 sources answered by one Copilot assistant in Teams and D365
1 definition per metric, from Snowflake semantic views
0 middleware servers to host or patch
Industry Financial Services
Region United Kingdom
Client UK digital bank
Solutions Snowflake, Snowflake Cortex, Copilot Studio, MCP, Agentic Workflow, Semantic Views

Key takeaways

  • A Copilot Studio router answers from Snowflake, SharePoint and an external API in one reply.
  • 3 sources sit behind one assistant in Teams and D365, with no dashboard request or analyst ticket.
  • 1 definition per metric: every AI-generated query expands from Snowflake semantic views.
  • Queries run as the signed-in user, data stays in Snowflake, and there's 0 middleware to patch.

THE CHALLENGE

Three systems, one question, no room to bend governance.

The bank’s teams work in Teams, Outlook and Dynamics 365. The answers they need sit in Snowflake, SharePoint and third-party systems. Every question that crossed those systems meant a dashboard change, an analyst ticket, or someone stitching exports together by hand.

Generic AI assistants made trust worse: each invented its own definition of revenue or margin. Shortcuts such as exporting data into Microsoft 365 or sharing one service account bypassed the row-level and masking policies that protect customer data.

Before

  • Cross-system questions waited on dashboards or tickets
  • Each AI assistant invented its own revenue definition
  • Shortcuts bypassed row-level and masking policies

THE APPROACH

Copilot routes the question. Every source keeps its governance.

We set up Copilot Studio as a multi-tool router. It reads each question, picks the tools it needs, and merges the partial answers into one reply. Numbers come from a Snowflake Cortex Agent, documents from a SharePoint site, and live third-party data from an external API.

We assessed four routes to Snowflake and chose MCP with one governed agent: a standard protocol, per-user identity, and one governed Snowflake tool instead of raw query tools, so all data reasoning stays inside Snowflake.

  1. Question in Teams or D365

    Business users ask in plain language, where they already work

  2. Copilot Studio router

    Sends each part to Snowflake, SharePoint or the external API

  3. One governed answer

    Merged reply, each source under its own access rules

THE OUTCOME

Governed answers in Teams, under each user’s own permissions.

Users now ask in Teams or Dynamics 365 and get one answer from 3 sources, with no dashboard request or analyst ticket. Every metric has 1 definition, set in Snowflake semantic views. Snowflake queries run as the signed-in user, only the question and the final answer cross into Microsoft 365, and there’s no middleware to host or patch.

Outcome

  • 3 sources answered in one reply
  • 1 governed definition per metric
  • Snowflake queries run as the signed-in user
  • 0 middleware to host or patch

Copilot sees one governed Snowflake tool, not raw query tools, so all data reasoning stays inside Snowflake.

Still routing cross-system questions through dashboards and analyst tickets?

Put governed answers in front of your business users. IWConnect designs and delivers Snowflake AI solutions end to end, from the semantic layer and the knowledge graph to Copilot. Talk to us to plan a pilot.

iwconnect.com | sales@iwconnect.com

More proof

Related case studies.

Have a problem that looks like this? Let's talk.

Tell us what you are trying to connect or trust. We will show you the proof that fits and the team that can help.