Automating the Monthly Compliance File Review
Regulated financial-advice firm (client anonymised)
A regulated financial-advice firm reviews every client advice file by hand each month: dozens of mechanical checks per file plus a judgement call on suitability, all under a regulator's eye. We proposed a four-stage multi-agent pipeline that does the mechanical work and drafts the review, with a compliance reviewer keeping the final sign-off. It is designed to run entirely inside the firm's own Microsoft tenant, in the EU.
Book a Case Walkthrough
The client is a regulated financial-advice firm. We have anonymised them here. Every month their compliance team reviews client advice files to prove each piece of advice was suitable and properly documented. It is careful, repetitive work: opening each file, checking the fact find and statement of suitability against dozens of requirements, confirming the recommendation matched the client's needs, and recording it all in case a regulator asks. The checks are mostly mechanical, but the volume makes the monthly review slow, and the firm is accountable for getting every file right.
The Challenge
Compliance file review is mostly mechanical checking, done by hand, every month, in an environment where a mistake carries regulatory weight.
- Each file needs around 40 yes/no checks against documentation and suitability requirements, repeated across the whole book of advice.
- The work mixes mechanical checks with a real judgement call on whether the advice suited the client, so it cannot simply be scripted away.
- Everything has to be evidenced. If a regulator inspects, the firm needs to show what was checked and where it came from.
- It is a regulated, data-sensitive environment, so any tooling has to keep client data inside the firm's own controlled systems.
- The review competes with everything else the compliance team does, so it is a steady monthly drain on senior time.
Our Solution
We proposed a multi-agent pipeline that does the mechanical heavy lifting and drafts the review, while a compliance reviewer keeps the final sign-off. It works in four stages. An extraction agent parses each advice file, the fact find, the statement of suitability and supporting documents, and maps the sections. A mechanical-checks agent runs roughly 40 yes/no checks per file, each one cited to the page it came from. A suitability agent compares the client's needs and objectives against the recommendation and the firm's consumer-protection obligations. A final stage assembles a one-page review pack and writes the result to the firm's existing Power BI dashboard. The reviewer reads the pack, sees every finding cited to its source, and signs off. The whole thing is designed to run inside the firm's own Microsoft tenant in an EU region, so no client data leaves their environment. This is the approach we proposed; the firm is at the pre-discovery stage.
- Four-stage pipeline: extraction, around 40 mechanical checks, suitability assessment, and a one-page review pack.
- Every finding is cited to its source page, so the output is inspection-ready and a reviewer can verify it in seconds.
- A human compliance reviewer keeps the final sign-off. The agents prepare the review; the person makes the decision.
- Designed to run inside the firm's own Microsoft tenant in an EU region, using their existing SharePoint and Power BI, so nothing new has to be trusted with client data.
- Built on Microsoft's agent platform with role-based access, a full audit trail, and no customer data used to train any model.
Built with Enterprise-Grade Technology
Goals and Objectives
The client came to us with clear objectives to transform their operations.
Automate the Mechanical Checks
Take the ~40 yes/no checks per file off the compliance team and run them automatically.
Keep the Human in Charge
Prepare the review, but keep the final sign-off with a qualified compliance reviewer.
Cite Every Finding
Tie every check to its source page so the output is inspection-ready and easy to verify.
Assess Suitability, Not Just Boxes
Compare the advice against the client's needs and the firm's consumer-protection obligations, not only documentation.
Keep Data In-House
Run everything inside the firm's own Microsoft tenant in an EU region, with no client data leaving.
Fit the Existing Stack
Use the firm's existing SharePoint and Power BI so the review lands where the team already works.
Build for a Regulated Environment
Role-based access, a full audit trail, and no customer data used to train any model.
See the Platform in Action
From intake to completion, explore how the solution transforms operations.
The Compliance Review Pipeline
Each advice file runs through four agent stages, extraction, mechanical checks, suitability and a review pack, then a compliance reviewer signs off. Every finding is cited to its source page.
How It All Works Together
Extraction Agent
Parses each advice file, the fact find, statement of suitability and supporting documents, and maps the sections so the right content reaches the right check.
Mechanical Checks Agent
Runs around 40 yes/no checks per file against documentation and compliance requirements, each one cited to the page it came from.
Suitability Agent
Compares the client's stated needs and objectives against the recommendation and the firm's consumer-protection obligations, the part that needs judgement.
Review Pack Generator
Assembles a one-page summary of every finding and writes it to the firm's existing Power BI dashboard for the reviewer.
Human Sign-off
A compliance reviewer reads the pack, checks the cited findings and signs off. The agents prepare the review; the person makes the call.
Microsoft-Native Hosting
Designed to run inside the firm's own Azure tenant in an EU region on Microsoft's agent platform, using existing SharePoint and Power BI, with role-based access and a full audit trail.
Value and Impact Delivered
Measurable improvements across every dimension of operations.
Mechanical Work, Automated
The roughly 40 yes/no checks on every file are designed to run automatically, so the compliance team's time goes to judgement, not box-ticking.
Inspection-Ready by Design
Every finding is cited to its source page, so the output stands up to a regulator's inspection and a reviewer can verify it quickly.
Human Sign-off Retained
The reviewer keeps the final decision. The pipeline prepares the review and shows its working; a qualified person signs it off.
Built for Regulated Data
Designed to run inside the firm's own Microsoft tenant in the EU, with role-based access and no customer data used to train any model.
Fits the Existing Stack
Uses the firm's existing SharePoint and Power BI, so the review lands in the tools the team already uses, with nothing new to trust with client data.
A Monthly Drain, Lifted
The repetitive monthly file review is designed to run as a pipeline, freeing senior compliance time across the whole book of advice.
Frequently Asked Questions
Ready to Transform Your Financial Services Operations?
See how AI can help your organisation reduce errors, speed up processing, and improve outcomes. Let's discuss your specific challenges.
Book Discovery CallExplore Other Projects
Discover more AI solutions delivering measurable results across industries