Agents for accountants/Adverse media and conflict checks

Accountancy agent

Adverse media and conflict checks

Every new client and every annual refresh is checked, evidenced and filed, without anyone having to remember.

Talk to us about this agent How it runs
Fixed price

Demo video coming soon

See the adverse media and conflict checks run, start to finish.

We're recording the demo now. Until it's here, we'll walk you through it live on a free 30-minute call.

Book a free 30-minute call

How it's sold

Sold with the client onboarding agent as Client Acceptance.

About Client Acceptance

What starts it

It starts on its own.

Standard trigger

A new client record is created in your CRM or practice system. The agent reads the company number and starts.

It could also start when

  • A client onboarding case opens (the onboarding agent calls this one)
  • The annual refresh date comes round, so every live client is re-checked
  • An insolvency pre-appointment check started from Teams
  • A new row in a SharePoint client list, for firms without a CRM

Manual fallback

Ask the agent in Teams to check a company and its directors. Same report, same filing, same evidence line.

  1. Trigger

    A new client record, onboarding case, refresh date or request from Teams.

  2. System

    Companies House: officers, persons with significant control, previous names and filing flags.

  3. AI

    The firm's approved searches run for each name, plus a conflict search across your own clients and engagements.

  4. AI

    Verified findings are separated from possible matches, and the result is scored.

  5. Action

    The report is filed to the client folder, an evidence line is written and the next refresh date is set.

  6. Your team approves

    A review task goes to the MLRO, only if something scores.

What it does

The agent pulls the company's officers, persons with significant control and filing history from Companies House, runs your approved searches on every name and checks for conflicts across your own clients and engagements. It files a scored report with an evidence line on the client, sets the next refresh date and only asks your MLRO to look when something scores.

Where your team approves

The MLRO or a partner reviews the hits only.

You decide what each agent may do on its own and where a person has to approve. By default, anything that goes to a client or raises a bill waits for one of your team.

Standard in every firm

  • Companies House lookup
  • Search set
  • Report template
  • Filing
  • Register
  • Refresh schedule

Set up for your firm

  • Risk categories
  • Search scope
  • Retention period
  • Who gets the review task

Today

A few web searches, some screenshots and a short note, filed and maybe repeated next year. Coverage is uneven and the evidence trail is patchy when the institute inspects.

With the agent

Full coverage in one format, an evidence line on every client and review time spent only where there's a hit.

Worked example

What it could give back to your firm.

Worked example

Checks a year
740
Hours back a year
419
Value of that time a year
£37,740

Illustrative defaults. Put in your own numbers.

How it's worked out

  • Checks a year = new clients a month × 12 + existing clients refreshed a year.
  • Hours = checks a year × (minutes per check now − minutes with the agent) ÷ 60.
  • Value = hours × value of an hour.

What you need in place

Before it can run in your firm.

  • A Companies House API key (it's free)
  • Your search protocol and risk categories
  • A client folder structure

General web search is the weak point. A paid screening service can be plugged in.

Price

Fixed price, confirmed on a free 30-minute call

Once live, it's looked after under Embed from £750 a month, which covers up to two live agents.

Microsoft's own usage charges, such as Copilot Credits, are billed by Microsoft to your firm, separately from our fees.

All prices exclude VAT.

Talk to us about this agent See pricing
Does this replace our AML software?
No. Identity checks and sanctions screening stay in your AML software. This covers adverse media and conflicts, and puts the evidence on the file.
Who decides if something matters?
Your MLRO. The agent separates verified findings from possible matches and scores the result, and a review task only goes out when something scores. The decision is always a person's.
Where does our data go?
We build agents in your own Microsoft 365, not on our servers, and we don't host your data. Agents your team talks to only see what that person can already see. Agents that run on their own use a dedicated service account, limited to the mailboxes, folders and systems the job needs, agreed with you in advance. We build in UK regions wherever Microsoft offers them, and anything that has to run elsewhere is set out for your compliance lead to approve before go-live. Microsoft doesn't use your Microsoft 365 content to train its foundation models, and every run is logged.
What does it cost to run?
Two things, kept separate. First, our fees: a fixed build price, then Embed from £750 a month, which looks after up to two live agents. Second, Microsoft's usage charges, which Microsoft bills to your firm. We build agents so routine steps run as standard automations and AI is only used where judgement is needed, which keeps Microsoft usage low and predictable. We estimate it before you commit.

Next step

Talk to us about this agent.

A free 30-minute call with James. We'll check how your practice would trigger it and confirm the fixed price.

Talk to us about this agent All six agents