Data everyone has. Context no one can find.
MSA's Dynamics 365 ERP had evolved faster than its documentation. The result: analysts wasting time on trial-and-error queries, business logic locked in a few people's heads, and a data dictionary nobody trusted.
Five tools. One seamless pipeline.
Built entirely within MSA's existing Microsoft 365 ecosystem — no new vendors, no new platforms, no additional training overhead.
Four components. One living data dictionary.
-
1Automated ETL pipelines in Microsoft FabricDesigned Lakehouse-to-Warehouse pipelines that continuously extract SQL metadata from Dynamics 365. Custom stored procedures query
INFORMATION_SCHEMAviews and upsert into staging tables — preserving business definitions while refreshing technical fields on every run. -
2Stored procedure management via Fabric Copilot agentsAutomated the continuous maintenance of stored procedures so documentation evolves in sync with the schema. Columns added, renamed, or dropped — the pipeline adapts without manual rework.
-
3Conversational Copilot Studio agentA prompt-engineered agent that lets data users query definitions in natural language and knowledge owners validate or update them through conversation — no forms, no spreadsheets. Deployable in Teams, Outlook, or any Microsoft tool with a single click.
-
4Power Automate orchestration layerTwo flows merge Fabric-sourced technical metadata and agent-submitted business definitions into a unified SharePoint list — a single, always-current source of truth for enterprise data knowledge.
Documentation that feels like a conversation.
The agent was designed around one rule: meet users where they already work, and make contributing feel effortless. Here's a real interaction from the prototype.
Current definition: "Represents the actual amount recorded for the transaction."
Would you like to update this definition?
Updated definition: "Represents the actual amount for all transactions."
Should I save this?
Tested across three dimensions.
- Trial-domain restrictions (UW–Madison) prevented full Copilot Studio ↔ Power Automate integration; a manual trigger was used as a workaround for the prototype.
- Tested on synthesized ERP data — performance at true production scale is yet to be validated.
- AI-generated definitions were occasionally generic, reinforcing that human review remains essential.
The technical challenge was orchestration — getting Fabric, Copilot Studio, Power Automate, and SharePoint to hand off to each other reliably, at scale, without breaking. That took careful design and a lot of iteration.
The human challenge was subtler: how do you get busy professionals to contribute to documentation without it feeling like a burden? The answer was to embed the experience inside tools they already use — and make it a conversation, not a form. That design decision shaped adoption more than any technical one.
The best AI tools don't replace human judgment. They make it easier to express, capture, and preserve it.
Interested in working together?
Get in touch