Christopher Cole

Richard Jaenisch and Christopher Cole discuss AI in pharma manufacturing, covering learning steps, output evaluation, hallucinations, and FDA/EMA guiding principles.

Manufacturing Intelligence: AI Integration in Pharmaceutical Lifecycle Management

In this inaugural episode of Manufacturing Intelligence—a biweekly, conversational series taking deep dives into all things digital technology in pharma manufacturing and development, Christopher Cole, associate editorial director at 

, sits down with Richard Jaenisch, senior director of Education, Outreach, and Digital Experience at Open Biopharma, to explore the practical integration of AI within pharmaceutical manufacturing and development. 

This discussion is specifically designed for industry professionals seeking to move beyond the hype and toward technical proficiency and begins with a foundational inquiry as Cole asks about the essential first step for professionals learning to use AI in their specific contexts. Jaenisch shares insights into the educational frameworks required to build internal expertise. 

A core focus of the conversation is the necessity of human oversight. Cole poses critical questions regarding how to train professionals to critically evaluate AI outputs and how to determine if a system is operating within its competency or merely “hallucinating confidently.” Jaenisch further explores the pedagogy of limitation—teaching staff to recognize exactly when a model is incapable of answering a question. 

Finally, the dialogue shifts to the regulatory environment, specifically an analysis of the EMA and FDA guiding principles for good AI practice throughout the drug lifecycle. Jaenisch evaluates the applicability of these principles and highlights the specific areas where current guidance may be missing key details. Click the video above to join a comprehensive roadmap for pharmaceutical professionals navigating the intersection of cutting-edge technology and rigorous regulatory standards.

Videos

Susan Schniepp, Regulatory Compliance Associates Inc.

Susan Schniepp, Regulatory Compliance Associates Inc., shared her insights on the transformative role of emerging technologies in drug manufacturing. Having participated in the planning committees for P

, Schniepp is at the forefront of introducing new technologies like digital twins and artificial intelligence to the industry.

Check out the 3-part video interview with Schneipp:

Digital Twins and the Future of Pharma Validation

Identifying Data Integrity Hotspots Using AI Technology

PharmTech: How Do You Define a Digital Twin in the Context of Pharmaceutical Manufacturing?

Schniepp: My understanding of a digital twin is that it is a system designed to mimic exactly what you have put into live operation. It runs alongside your actual production line. Potential issues come when the two systems, the physical and the digital, begin to divert from one another. If they are no longer in sync, it triggers a specific response from the team, such as a new validation, a technical correction, or another corrective activity to bring them back into alignment.

How Does This Tech Help Address Concerns of Data Integrity?

Data integrity is a major concern as we move away from traditional paper systems or middle electronic systems. In those older models, humans handled every document and performed every approval manually. Now, we use digital twins to identify hotspots, specific areas where there is a high potential for data integrity violations based on how documents are being handled. Once the AI identifies these risks, the human staff can shore up"the system to prevent a violation from ever actually occurring.

How Does AI Change Workflow Compared to a Middle Electronic System?

A middle electronic system is like Documentum, where you use electronics to move files around, but a human still has to physically look at and approve everything. With AI and machine learning, we are allowing the machine to do much more. The system itself collects the data and assures its correctness. The human's role shifts from doing the primary approval of every detail to reviewing the data the digital twin or system has already aggregated.

How Does AI Impact the Batch Release Process?

This is a significant shift for the industry. AI acts like one centralized brain that compiles information from various sources that a person would normally have to hunt for manually. The AI creates a dossier for the batch, noting that parameters were met and identifying any deviations. It can then essentially tell the human, "All of these things related, and there were no deviations. You can release this batch.” This speeds up the process significantly because the human professional is reviewing a summarized dossier rather than starting the data collection from scratch.

What Happens When the Human Professional Disagrees with the Machine's Assessment?

We treat a conflict between the human's opinion and the machine's data as a deviation. Because our industry relies on Corrective and Preventive Action systems, this discrepancy prompts a formal investigation to determine why these two events are conflicting. The traditional model is to investigate the root cause. Since the technology is still so new, I believe the human should take precedence. The investigation should focus on why the digital twin conflicts with the human, though we may occasionally find that the human was actually the one who was wrong.

Do You Have Concerns About The Human-In-The-Loop Model?

The industry is currently struggling with exactly where to place the human in the loop to be most efficient. My concern is that at some point, the machine will absorb so much data and learn so much faster than a person can that it will become more capable than the human. I worry that the human will be out of the loop eventually. However, for now, the human must remain the final decision-maker, absorbing the data provided by the AI to make the final call on whether a batch is safe for release.

Articles

Emerging manufacturing technologies are reshaping validation, data integrity assurance, and batch release decision-making. Digital twins are positioned as parallel, continuously updated models of live operations that flag divergence requiring corrective action, revalidation, or technical remediation. AI/ML shifts quality workflows from manual document review toward automated data aggregation, verification, and risk-based identification of data integrity hotspots. For batch disposition, AI can compile cross-system evidence into a release-ready dossier, accelerating timelines. Disagreement between human judgment and machine output is treated as a deviation triggering CAPA-driven investigation, with human precedence maintained.

Susan Schniepp discusses how AI and digital twins speed up pharma batch release and detect data integrity issues while maintaining human oversight.

Managing Deviations Between Humans and Digital Twin Data

Susan Schniepp, Regulatory Compliance Associates Inc., explains how AI and digital twins speed up pharma batch release and detect data integrity issues with human oversight.

In part 2 of a 2-part interview,Susan Schniepp, Regulatory Compliance Associates Inc., discusses the evolving relationship between AI and human oversight. She highlights how emerging technologies, such as digital twins, are transforming traditional manufacturing and validation processes, as a part of 

Schniepp explains that AI can significantly streamline operations by acting as a highly efficient data aggregator. Rather than requiring a person to manually hunt through disparate files, the technology centralizes information to provide a comprehensive overview of a batch. She observes, "it's compiling all of this information coming at it like one big centralized brain and then saying, 'All of these things related, and there were no deviations.’” This centralized brain allows for the creation of a batch dossier that summarizes parameters and deviations, greatly speeding up the timeline for product release.

The technology also serves as a proactive tool for quality assurance. By analyzing vast amounts of data, AI can pinpoint specific areas where errors are likely to occur. Schniepp notes, "As you put AI in, it's gonna identify places where there, is potential for data integrity." Once these hotspots are identified, humans can take action to shore up the system and prevent actual violations from happening.

Schniepp advocates for a human-in-the-loop model. While machines are capable of learning faster and absorbing more data than humans, she emphasizes that the human professional must remain the final decision-maker. The human's role is to absorb the data provided by the digital twin and AI to make the final call on whether a batch is safe for release, ensuring accountability in a complex and high-stakes industry.

Susan Schniepp, Regulatory Compliance Associates Inc., discusses digital twins and AI in pharma, focusing on data integrity, human-in-the-loop roles, and evolving machine learning risks.

In part 1 of a 2-part interview, and as a part of 

, Susan Schniepp, Regulatory Compliance Associates Inc., discusses the evolving role of technology in the manufacturing landscape. A central focus of her discussion is the implementation of digital twins, which she describes as systems that mimic live operators. Schniepp explains that when these digital models diverge from physical operations, it prompts corrective actions or new validations to bring the two back into alignment. A primary benefit of this technology is the ability to identify data integrity hotspots, areas where violations might occur due to how documents are handled.

The shift toward AI represents a significant change from traditional paper or middle electronic systems where humans perform every approval. With machine learning, the system can now perform much of the data collection and verification itself, allowing the machine to take on a larger role. However, this shift raises critical questions regarding where human oversight is most efficient. Schniepp suggests that discrepancies between human opinion and machine data should be treated as deviations requiring a formal investigation. She notes, "The traditional model that we have is to do an investigation on it."

Looking ahead, Schniepp acknowledges the rapid pace of machine learning and its potential to surpass human capability in data processing. She observes, "At some point the machine ultimately is probably more capable at looking at some of these things as it learns, it’s gonna absorb so much more data and information and learn at a faster pace than the human can, that at some point the human's gonna be, and this is where I get concerned, the human will be out of the loop." For now, she advocates for human precedence, suggesting that because the technology is so new, humans should investigate the digital twin during conflicts to determine the root cause of any discrepancy.

Susan Schniepp, Regulatory Compliance Associates Inc., as a part of 

, shares her insights on streamlining quality systems, the financial value of robust inspections, and the necessity of looking at the big picture in manufacturing. She breaks down why quality shouldn’t be a burden and how transparency can save millions.

Why Robust Quality Systems Save Pharmaceutical Companies Millions

How AI Can Connect Pharma Manufacturing Data Systems

How Small Pharma Companies Can Simplify Quality Compliance

How Do You Define a Culture of Quality for an Organization?

Schniepp: It is actually quite simple. When we talk about a culture of quality, we are really talking about the culture of the entire organization. It boils down to a few basic behaviors: if you see something, say something, and if you make a mistake, fess up. Maintaining a quality system is not as difficult as people claim. It requires control over documents, validated manufacturing processes, and technology transfer data, especially if you are working with a CDMO.

Is There a Way to Streamline the Administrative Weight of These Systems?

Absolutely. I think people often make a bigger deal out of it than it is, and we need more flexibility and creativity. For instance, small or virtual companies often feel they must have an SOP for everything listed in the Code of Federal Regulations. But if you don't actually perform a specific operation, like a recall, you shouldn’t have an SOP for it. Instead, just have a statement saying you have contracted that procedure out to another party.

The goal is to avoid being burdensome. The FDA has a beautiful system where they don’t tell you 

 to do something; they tell you what standards you must meet. Whether your SOPs are text-heavy or full of pictures is up to you, as long as you achieve the end result: a thoroughly documented operation with investigated deviations and appropriately released batches.

What Is the Biggest Challenge in Maintaining These Systems?

The hardest part is maintaining the proper ratio of people to run the systems versus people to interpret the data. Robust investigations require significant manpower. While an investigation might take resources away from running product, it is worth it if it solves a problem and prevents a future, equally bad issue from occurring.

How Do You Justify the Cost of a Robust Quality Program to Stakeholders?

You justify it through the value of catching defects early. I call it the Rule of 10. It costs nothing to catch a defective component at incoming inspection; you just ship it back. However, if that defect makes it to your shelf, it costs $10,000. If it hits the manufacturing floor, it’s $20,000. If it gets into a batch and you must abort midterm, you’re at $50,000. Catching it in the final product costs 1$,000,000 or more. Beyond the money, any recall, even for a cosmetic defect like a smeared label, damages the company's reputation.

What Does Focusing More on the Big Picture Look Like for the Industry?

We need to understand how all the separate data points, smoke studies, particulate matter data, and environmental monitoring, relate to each other to protect the product. Traditionally, we treat these as isolated data points. But they work together to keep the product safe.

Think of it this way: there is a continuous background of activities like media fills and water results that must run 24/7 to maintain the facility, even when you aren't running a batch. Then you have snapshots, which are your specific chemistry or micro results for a particular batch. We need to better understand how that background supports the release of every single batch.

What Is Your Advice for Working with CMOs?

Transparency is everything. Operations run smoother and cost less when there is a robust quality agreement and both parties understand each other. Complexity arises when a client forces a CMO to use a special requirement that differs from the CMO's general standards. This creates duplicate standards, which makes the system far more complicated than it needs to be.

A culture of quality is fundamentally an organizational culture anchored in transparency: speak up when issues are observed and disclose errors early. Quality systems need not be administratively oppressive when aligned to actual operations, emphasizing controlled documentation, validated processes, and clear technology transfer—particularly with CDMOs. The primary operational strain lies in resourcing rigorous investigations, yet early defect detection delivers outsized financial and reputational returns. Industry performance improves when “background” facility monitoring is interpreted alongside batch-specific “snapshot” data to support sound release decisions and product protection.

Susan Schniepp, Regulatory Compliance Associates Inc., shares strategies to streamline pharma quality, reduce costs via early detection, and use data to ensure safety.

How to Streamline SOPs for Better FDA Compliance

In part three of this three-part series, Susan Schniepp, Regulatory Compliance Associates Inc., discusses pharma quality systems don't have to be complex. Sue Schniepp explains how flexibility, right-sized SOPs, and transparency keep compliance simple.

In part 3 of a 3-part interview, Susan Schniepp, Regulatory Compliance Associates Inc., makes a candid argument maintaining a robust pharmaceutical quality system doesn't have to be as complicated as the industry often makes it out to be.

, Schniepp breaks down the fundamentals of a sound quality system, document control, validated methods, validated manufacturing processes, thorough technology transfer, and strong investigation procedures, and insists that the framework itself is straightforward. The real challenge isn't the system; it's having the right people to run it. As she put it, "What's hard to maintain is the proper ratio of people to run the systems and people to interpret the data, because sometimes you get an interesting investigation, one that requires a lot of manpower."

She also pushes back against the tendency of smaller and virtual companies to overengineer their quality documentation by copying requirements from larger organizations or regulatory listings without considering whether those procedures apply to their operations. Her advice is if an organization doesn’t perform a function, don't write a lengthy SOP for it. A simple contracted service agreement will suffice.

This pragmatic philosophy extends to her views on the FDA's regulatory framework, which she stated, "It's a beautiful system the FDA has — they don't tell you what you have to do, they tell you what you have to meet." She argues this outcome-based approach gives companies of all sizes the freedom to design quality systems that fit their specific operations.

Schniepp closes with a pointed reminder about CMO and CDMO relationships, that transparency and well-crafted quality agreements are essential. When clients impose duplicative or conflicting standards on contract manufacturers, costs rise and complexity compounds, an outcome that benefits no one.

Susan Schniepp, Regulatory Compliance Associates Inc., explains how flexibility, right-sized SOPs, and transparency keep compliance simple.