Training course · Make · Pharma & Life Sciences

Make for Pharma and Life Sciences

Automation with Make (formerly Integromat) and AI modules: build scenarios, routers and AI steps while keeping data protection in check.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects Make with the everyday processes of Pharma & Life Sciences. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

Make, formerly known as Integromat, is a visual automation platform that lets you connect applications and automate recurring processes without writing code. Over two days you will learn to build scenarios systematically, from triggers and modules through routers and filters to iterators, aggregators and data stores. You will understand how data flows through a scenario, how to reshape it with functions and how to keep an eye on operations consumption.

The second focus is AI. You connect language models through Make’s AI modules and provider integrations to classify text, extract information from emails and documents, draft replies or enrich content. You learn to catch errors with error handlers, test scenarios and document them clearly. Finally, you address data protection topics such as hosting region, data processing agreements and data minimisation, so that your automations can be run safely within your organisation.

Pharmaceutical, biotech and medtech companies operate in one of the most heavily regulated environments of all. Documentation, validation and traceability shape daily work from research and clinical trials to manufacturing. Generative AI offers significant potential: AI assistants review scientific literature, help draft study protocols, regulatory documents and SOPs, summarise deviation reports, support pharmacovigilance case processing and prepare medical information for healthcare professionals. Automation supports change control, CAPA tracking and regulatory intelligence. At the same time, as soon as AI touches GxP-relevant processes, validation, data integrity according to ALCOA+ and clear accountability are mandatory. Adoption succeeds when companies clearly separate non-regulated support from GxP use and involve quality assurance early.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Regulatory affairs professionals
  • Quality assurance and Qualified Persons
  • Clinical operations and medical writers
  • Pharmacovigilance and drug safety teams
  • Medical affairs and R&D scientists

Typical challenges we address

  • Producing extensive regulatory and scientific documents to a high standard
  • Processing deviations, CAPAs and change controls on time
  • Systematically evaluating growing volumes of literature and regulation
  • Using AI tools in a GxP-compliant, validatable way

What you will be able to do

  • You can build Make scenarios independently using triggers, routers, filters and data transformations.
  • You can process lists and records with iterators, aggregators and data stores.
  • You can integrate AI modules for classification, extraction and text generation into your processes.
  • You can safeguard scenarios with error handlers, validation and human approval.
  • Use AI for literature review, medical writing and regulatory intelligence.
  • Distinguish non-regulated AI use from GxP-relevant applications and understand validation requirements.
  • Safeguard data integrity, confidentiality and patient data protection when using AI.

Course outline

Day 1

Module 1 Fundamentals: scenarios, modules and data flow
  • Interface layout, scenario editor and execution history
  • Triggers, actions and searches: module types and their role in a scenario
  • Understanding bundles, mapping and data types and using them deliberately
  • Choosing between schedules, webhooks and instant triggers
Module 2 Logic: routers, filters, iterators and aggregators
  • Using routers and filters for branching and conditional flows
  • Splitting lists with iterators and combining them with aggregators
  • Applying text, date and maths functions to transform data
  • Using data stores and variables for interim values and duplicate checks
Module 3 AI building blocks in Make
  • Connecting language models via AI modules and provider integrations
  • Automating classification, structured data extraction and text generation
  • Building prompts from scenario variables and processing output as JSON
  • Combining AI agents in Make with tools and scenarios as actions
Module 4 Integrations, error handling and testing
  • Connecting common business applications and any API via the HTTP module
  • Applying error handlers such as Resume, Ignore, Break and Rollback
  • Validating AI output and routing unusable results to a person
  • Testing scenarios, optimising operations and documenting them for the team

Day 2

Module 5 Data protection, governance and operations
  • Assessing hosting region, data processing agreements and data flows to AI providers
  • Applying data minimisation and pseudonymisation within scenarios
  • Managing connections, teams and permissions across the organisation
  • Defining approval steps, monitoring and ownership for live operation
Module 6 Practice lab: Pharma & Life Sciences
  • Literature review and evidence
  • Medical writing support
  • SOPs and training materials
  • Deviations and CAPA
  • Regulatory intelligence
  • Pharmacovigilance support
Module 7 Data protection, quality & transfer to daily work
  • When AI systems are used in GxP-relevant processes, computerised system validation under EU GMP Annex 11 or 21 CFR Part 11 and data integrity according to ALCOA+ must be ensured. Clinical trial and pharmacovigilance data contain health data under Article 9 GDPR and may only be processed in pseudonymised form in approved environments.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Literature review and evidence

An AI assistant summarises scientific publications, extracts study design, endpoints and results into tables and supports systematic reviews, with experts checking every data point against the original source.

Medical writing support

AI creates outlines and first drafts of study protocols, clinical study reports, investigator brochures or modules of the regulatory dossier based on approved templates and source data.

SOPs and training materials

Process descriptions and regulations are turned into draft SOPs, training slides and comprehension questions, which are then reviewed and approved through the validated document management system.

Deviations and CAPA

AI summarises deviation reports, structures root cause analyses, finds similar past cases and suggests CAPAs, which quality assurance evaluates and decides on.

Regulatory intelligence

Automations collect new guidelines and publications from the EMA, national authorities or the FDA; AI summarises changes and maps them to affected products and processes for an impact assessment.

Pharmacovigilance support

AI helps pre-structure case reports from unstructured text, extract relevant information on product, event and patient and detect duplicates, while medical assessment remains with qualified staff.

Prerequisites

You should be comfortable with common office and cloud applications and have some experience with AI assistants. No programming skills are required. You work in the pharmaceutical, biotech or medtech industry and know the GxP basics of your area.

Technical requirements

You will need a laptop with an up-to-date browser and a Make account; the free plan covers most exercises. API access for a language model is set up together during the course.

Data protection & compliance

When AI systems are used in GxP-relevant processes, computerised system validation under EU GMP Annex 11 or 21 CFR Part 11 and data integrity according to ALCOA+ must be ensured. Clinical trial and pharmacovigilance data contain health data under Article 9 GDPR and may only be processed in pseudonymised form in approved environments.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Tue, 1 December 2026 – Wed, 2 December 2026 Kaiserslautern Request
  • Tue, 8 December 2026 – Wed, 9 December 2026 Online Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Bremen Request
  • Wed, 13 January 2027 – Thu, 14 January 2027 Online Request
  • Mon, 25 January 2027 – Tue, 26 January 2027 Salzburg Request

Frequently asked questions

Is Make the same as Integromat?

Yes. Integromat was renamed Make and substantially developed along the way. The core principle of visual scenarios made of connected modules remains, while a redesigned interface, many new integrations and AI building blocks have been added. If you used Integromat in the past, you will quickly feel at home and discover the new capabilities on the course.

How do I keep operation costs under control?

Every module that runs consumes operations or credits, and AI calls also use quota with the respective model provider. On the course you learn to design scenarios so that filters apply early, unnecessary runs are avoided and data is processed in batches. This keeps your automations economical and predictable as volumes grow.

Can Make be used in a GDPR-compliant way?

In principle yes, provided you set up the framework deliberately. This includes choosing the hosting region, signing a data processing agreement, reviewing connected AI services and applying data minimisation. On the course you work through these points with a checklist and learn to filter or pseudonymise sensitive data within scenarios.

Do AI tools need to be validated in pharma?

It depends on the use. For activities without GxP relevance, such as internal communication or literature overviews, general IT and data protection rules apply. If results feed into GxP-relevant decisions or records, a risk-based validation approach is required. We show you how to classify use cases.

How do we ensure data integrity?

AI output must be attributable, traceable and verifiable. That means documented inputs and prompts, clearly assigned reviewers, versioning and release through your validated systems. In the course we discuss how ALCOA+ principles apply to AI-supported work steps. Clear retention rules complete the picture.

How much does “Make for Pharma and Life Sciences” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Pharma and Life Sciences

More Make courses

All 45 Make courses

Make · MunichMake · SalzburgMake · BerlinMake · AugsburgMake · HanoverMake · BremenMake · StuttgartMake · KaiserslauternMake · Online