Investment policy and procedures assistant

What is the limit per issuer, who approves a trade above the limit, how do I declare a conflict of interest: the answers are in the policies in SharePoint, but before a trade in Bloomberg Terminal the manager spends a long time looking for them. The assistant in Teams answers with a link to the valid document and sees only what the employee can see under their Entra ID permissions.

Built for ISO 27001NIS2 DORA

Investment policy and procedures assistant
  • Copilot Studio agent in Teams
  • Structure of the policy libraries
  • Question log for compliance

The policy is in force, but before a trade the manager looks for it in five places

  • Quotation clause and a link to the SharePoint version
  • Entra ID answers only from documents the employee can see
  • Procedure points to the procedure and Power BI, does not decide
  • 2–4 weeks SharePoint policies and Teams agent running

An investment management firm runs on an investment policy with limits for each fund and strategy, a conflict of interest procedure, a trade approval procedure, rules for suitability and appropriateness assessment of clients and a personal account dealing procedure. The documents sit in SharePoint, and some older versions are in e-mail attachments. A new portfolio manager, before entering an order in Bloomberg Terminal, asks a colleague in Teams whether risk officer approval is needed, and the colleague answers from memory. Every week the compliance officer answers the same questions about the suitability questionnaire on the client record in Salesforce, and the version confusion comes to light during an internal audit.

A Copilot Studio agent runs in your Microsoft 365 tenant as a chat in Teams. The employee asks in plain language, and the agent searches only approved SharePoint libraries and only among documents the employee can see under their Entra ID permissions, and answers with a quotation, the clause number and a link to the valid version. If the question is about a specific trade or client, the agent points to the procedure and the responsible person but does not make the decision, give a recommendation or look at Bloomberg or Salesforce data. The manager checks actual limit usage in your Power BI report, which the agent links to. When no document covers the question, the agent says it has no information. Data stays in your tenant and is not used to train models, and questions are written to a log that the compliance officer can see.

How it works

Four steps from input to a record in your system, with human approval wherever there is risk.

A question in Teams

The employee writes to the agent in a Teams chat, usually before entering an order in Bloomberg Terminal or LSEG Workspace: what is the limit per issuer in the growth strategy, does a transaction with a related party need to be declared, which suitability questionnaire applies to a retail client. The agent may ask for the fund or client segment to be clarified.

What you get

Copilot Studio agent in Teams
Copilot Studio agent in Teams

An agent in your Microsoft 365 tenant, available in a Teams chat to portfolio managers, analysts and client service by Entra ID group.

Structure of the policy libraries
Structure of the policy libraries

SharePoint libraries with version, validity and access metadata, so that the agent answers only from policies in force, and links to Power BI limit reports.

Question log for compliance
Question log for compliance

A log of questions, answers and unanswered topics in your tenant, useful for policy reviews and internal audit.

Training and support
Training and support

Training for employees and document owners, support for the agent and the SharePoint libraries, and adding new policies.

What we build it with

A Copilot Studio agent in Teams that searches approved SharePoint libraries and links to your Power BI limit reports, all within your Microsoft 365 tenant. If you keep the policy register in Salesforce or Dynamics 365, we bring in the documents through an API, file export or an e-mail flow, depending on the version. Learn more about this service and its limits on the service page.

Frequently asked questions

Can the agent advise on a trade or execute one?

No. The agent quotes the policy and procedure, states the limits and who approves, but it does not assess a trade, look at Bloomberg or portfolio data or give recommendations. The decision is made by the manager under your procedures.

Does it work with Power BI and Salesforce limit data?

Not in the first stage. The agent answers only from policy documents in SharePoint and links to your Power BI report, which the manager opens themselves. Connecting Power BI or Salesforce data with read-only permissions is possible in a second stage through an API or dataset queries, depending on licences, and we choose the method after a check.

Does policy content leave our Microsoft 365 tenant?

No. Copilot Studio runs in your tenant under Microsoft's commercial terms, and documents and conversations are not used to train models. The log and settings remain in your administrators' hands.

Related services

Summaries of market reviews and prospectuses

In a day, an analyst receives more reviews, issuer reports and prospectuses from Bloomberg Terminal, LSEG Workspace and e-mail than anyone can read.

More
Meeting summaries and tasks into the CRM

After a client meeting, the manager writes notes into Salesforce or Dynamics 365 from memory, and some of the agreed actions get lost.

More
Drafts of client reports and letters

At the end of the month, the portfolio manager prepares dozens of reports and letters from the same Euroclear statements and Excel tables.

More
Monitoring compliance and risk documents

A new version of ESMA guidelines, an updated decision of the financial regulator, changed stock exchange rules, a changed internal policy: the…

More

Expertise confirmed by certifications

This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.

All certifications
  • AISP badge
    AISP PECB

    Artificial Intelligence Security Professional

    AI systems are deployed with protection against data leakage and model abuse.

  • AAISM badge
    AAISM ISACA

    ISACA Advanced in AI Security Management

    The AI security programme and its controls are managed following the ISACA methodology.

  • AAIR badge
    AAIR ISACA

    ISACA Advanced in AI Risk

    AI risks are identified and managed like any other IT risk.

Let's discuss: investment policy and procedure assistant

Tell us how this process works for you today and which systems you use. Within 1 business day we will tell you how long an implementation for investment management would take.

We reply within 1 business day

Contact us 24/7
+370 630 94 909

Fill out the form, and we will contact you within 1 business day.