[Online] Building an AI Harness for Your Data Team

​Continuing our DPM webinar series aimed at upskilling & knowledge-sharing, we’re joined by Xavier Gumara Rigol, Head of Data at Manychat and author of Data as a Product Driver.

​An AI-generated query can run successfully and still answer the wrong question. If your team is experimenting with agents for analytics or data engineering, how do you make their work trustworthy?

​Xavier Gumara Rigol's team at Manychat has been experimenting with harness engineering for data workloads: the context, tools and checks around an AI model, such as one that answers analytics questions or monitors data quality. For data teams, this raises practical questions. Does the model know your business definitions? Can it keep up when the data changes? How do you check its output? Where can it run safely before it touches production? He’s also written about this here.

​In this session, we’ll explore what a useful harness looks like for data work, which foundations teams can reuse, and what they need to put in place before relying on agents.

​What we’ll unpack

• ​What does a harness add beyond the model, and which parts matter for data workflows?

• ​Why can a successful query still produce the wrong business answer?

• ​How do metadata, reusable workflows and deterministic checks work together?

• ​Where can evaluators help, and what still needs human judgement?

• ​What does a safe environment for testing agent-driven data changes require?

​What you’ll walk away with

• ​A practical way to assess where your team is ready and where it has gaps.

• ​Questions to guide investment in context, validation and test environments.

• ​A starting point for applying these ideas to one data workflow.

​Perfect for: data leaders, data platform and product managers, and analytics or data engineering practitioners exploring AI agents.

​Bring a workflow or a reliability problem you’d like to discuss.

​About our speaker

​Xavier Gumara Rigol is Head of Data at Manychat and the author of Data as a Product Driver (Apress, 2026). He has worked across data and product development for more than a decade. His career spans consulting for small businesses and data transformation work at Schibsted, Adevinta, Oda and Manychat, covering business intelligence, engineering, experimentation and product information management. His book examines how organisations can connect data work to product decisions and business outcomes.

​How to join

​This livestream will be held in our digital community space.

​Make sure you’ve joined us on Circle - signing up is free.

​About the Data & AI Product community

​Data and AI product management is still a young discipline, and there aren't many spaces dedicated to learning from peers.

​So we started this meetup in 2023 to change that! Since then, it's grown into a vibrant community with chapters in London, Barcelona, and Paris.

​Whether or not "product" is in your job title, if you're involved in shaping data, analytics, and AI initiatives (e.g. product managers, strategists, BAs, data scientists, engineers, analysts) you'll find like-minded people here.

​This is an informal, welcoming space to swap lessons and share challenges.

​You can meet us in person at our in-person meetups, but also join our global community where we have expert webinars, training courses, job postings, resources, and discussions.

​Quick FAQ

• ​Will this event be recorded? Yes, we will upload the recording here, along with previous DPM Community webinars

• ​If I sign up to this event, will I be opting into any marketing emails? No. We only use the Luma mailing list to invite you to upcoming community events and share community updates (like our end of year membership survey). You can always opt out of the Luma calendar.

• ​Can I mention this to a friend or colleague? Yes, of course! If they're based in London, send them this event. If they're not, it might be better to send them the community join link, so they don't get invited to all our in-person meetups too.

• ​Why are you doing this? Data & AI Product Management is a nascent field, and we created this community to bring together practitioners and help share our skills and experiences with those newer to DPM.