AI compliance monitoring that cut 17 hours a week from a medical team's workload

ClientMid-size pharma company

Location

UK flagUK

IndustryPharmaceutical Manufacturing

About the project

We built an AI system that finds online content mentioning a pharma company, scores it for compliance risk, and drafts the response

The client is a mid-size pharma company operating in the United Kingdom. Its medical team was spending a significant share of the week responding to compliance complaints about content the company had neither written nor controlled.

We delivered this as part of our GenAI solutions for pharma offering.

The Challenges

In the UK, pharmaceutical promotional activity is governed by an industry code, and the regulator investigates complaints against it.

Complaints can be raised about content that mentions a company or its products even when the company did not create that content. Sponsored events, third-party medical platforms, and patient group websites all produce material of this kind, which left the client accountable for material it had never written.

  • 01

    Accountability for content the company did not control

    Complaints arrived about material published by event organizers, third-party medical platforms, and patient organizations. The company had no editorial control, yet it carried the regulatory consequence.

  • 02

    A tight response deadline with potential fines

    Every complaint came with a short window to respond, and an inadequate or late reply meant a fine scaled to how far the content departed from the code.

  • 03

    Manual review absorbing the medical team's week

    Each complaint meant someone had to locate the content, read it against the code, decide what needed to change, and write the official reply from scratch.

  • 04

    No visibility into what was being published

    Without an automated way to monitor the open web, the company learned about a problem only after a complaint had already been raised.

  • 05

    Specialist time displaced from higher-value work

    The people handling compliance reviews were the same people who should have been creating new content, approving existing material, and engaging with physicians.

The Objectives

The client wanted to stop reacting to compliance complaints one at a time and start seeing problems before the regulator did.

01

Find content published across the UK web that mentions the company or its products, including material the company does not own.

02

Separate genuinely relevant mentions from unrelated results, so the medical team is not reviewing noise.

03

Score every mention for compliance risk against the industry code, rather than treating all mentions equally.

04

Hand the team a recommended course of action for each case.

05

Produce a draft official response to the regulator that a human only needs to check and approve.

Our Approach & Solutions

We built the system around a simple division of labor. Software handles the volume, finding and sorting content at a scale no team could match manually. A person handles the judgment, reviews what the system surfaces, and approves the response.

  • 01

    Custom scrapers across UK web sources

    We built scrapers that search the open web for content mentioning the company and its products, covering third-party medical platforms, event and sponsorship pages, and patient organization sites alongside the company's own properties.

  • 02

    Relevance filtering to cut out the noise

    The hardest technical problem was deciding what is relevant. We built filtering logic to keep only mentions that genuinely relate to the business.

  • 03

    An AI agent trained on the compliance code and internal precedent

    The agent was configured against the published compliance code and the client's own history of past cases, so its judgments reflect both the rules and how the company had handled similar situations before.

  • 04

    Three-tier risk classification

    Every mention is sorted into Low, Medium, or High risk. This gives the medical team a queue ordered by what actually matters.

  • 05

    A report with an action plan attached

    Each report covers newly discovered content and pairs every item with a recommendation. For the company's own properties, the recommendation outlines the changes needed to address the issues. For third-party content, it covers how to approach the publisher and what to ask for.

  • 06

    Pre-drafted regulator responses and third-party outreach

    The system generates the official response to the regulator and the notification to the third-party publisher. Both arrive as drafts, ready to review.

  • 07

    Human review kept firmly in the loop

    Reviewers open a link that takes them directly to the non-compliant passage rather than to the top of a long page. They confirm the finding, check or edit the recommended measures, and approve. What used to be research and drafting became verification.

The Results

The system gave the client visibility into what the internet says about the company before the regulator did. The operational gain was immediate, and the reduction in financial exposure was larger still.

Key outcomes included:

  • 01

    An estimated 17 hours per week returned to the medical team

    Time previously spent locating content, drafting responses, and following up on implementation.

  • 02

    Close to £1 million in potential fines avoided

    Based on the client's estimate of exposure across the cases the system caught and corrected.

  • 03

    The medical team moved back to higher-value work

    Including creating new content, approving existing material, and engaging with physicians.

  • 04

    Leadership wanted to take it further

    The project's success raised the possibility of extending the approach across the organization globally.

Highlights

17 hours

saved per week

~£1M

in potential fines avoided

3 risk tiers

automatic classification

Before this system, compliance work landed on us as a series of unpleasant surprises. Now we see the content first, we know how serious it is, and most of the response is already written by the time it reaches us. It changed what my team spends its week doing.

Digital Project Manager

Mid-size UK pharma company

Before this system, compliance work landed on us as a series of unpleasant surprises. Now we see the content first, we know how serious it is, and most of the response is already written by the time it reaches us. It changed what my team spends its week doing.

Digital Project Manager

Mid-size UK pharma company

Technologies
ChatGPT
Custom-built web scrapers
Custom validation system
Automated report generation

The compliance rules in this market are public and well documented, which is exactly what makes them a good fit for AI. The real problem was never interpreting the code. It was finding the content in the first place and deciding which mentions genuinely mattered. Once we solved that, the rest followed, and the client's team got their week back.

Alex Jijie

Alex Jijie

CEO, Digitalya

The compliance rules in this market are public and well documented, which is exactly what makes them a good fit for AI. The real problem was never interpreting the code. It was finding the content in the first place and deciding which mentions genuinely mattered. Once we solved that, the rest followed, and the client's team got their week back.

Alex Jijie

Alex Jijie

CEO, Digitalya

Component could not be found for blok section-project-mockups! Is it configured correctly?

Want to harness the power of generative AI?

Build custom GenAI solutions to support pharma marketing teams and become a digital transformation leader.