Episode 6 · May 21, 2026 · Hosted by Sebastian
AI Meets Your Process Models: Updating, Querying and Restructuring Live
An open, live session connecting AI directly to a BPMN process to see what happens when it can work on the model itself. No slides, just live prompting: enriching a diagram with cost and time, asking it questions, checking consistency across a landscape, and restructuring a whole landscape, which went surprisingly far.
Four AI and BPMN use cases we pulled off live.
The big takeaway
AI doesn't replace BPMN modelling. It removes the friction around it.
Bulk edits, consistency checks, restructuring, enrichment and analysis. The judgement stays with you. The grunt work doesn't.
What we walked through
- 01
Enriching a diagram with cost and time in seconds
We took a process with empty attributes and pasted spreadsheet values directly into the prompt. The AI matched the values to the right tasks, populated the attributes, and instantly calculated total cost and cycle time.
- 02
Asking the diagram questions
"What's the most expensive step?" "Where are we losing the most time?" "How would you improve this process?" The AI answered directly from the BPMN model, identified the high-cost path and suggested optimisation levers. First-pass analysis without a reporting tool.
- 03
Consistency and governance across a landscape
The AI scanned multiple diagrams and surfaced inconsistent naming and modelling patterns. The kind of cleanup work that becomes painful once you operate at scale.
- 04
Restructuring an entire process landscape
Could AI extract an outsourced back-office lane from 100 processes, rebuild the target processes and reconnect the interfaces? The answer was: surprisingly far, yes. That opens up interesting possibilities for outsourcing, reorganisations and M&A scenarios.
Discuss this episode
Ask a question, share how you would model it, or suggest the next topic.
More episodes
All episodes →
From As-Is to To-Be, Faster with AI
The full improvement loop on a lead-to-signature process, sped up with AI: validate the as-is, capture improvement opportunities, analyse with AI, design the to-be, align stakeholders, then implement and repeat. And why none of it pays off unless the people who run the process validate the as-is first.
The Hidden Context Layer: Clean Diagrams, Rich Metadata
How to make diagrams leaner and smarter at the same time. Instead of stacking labels on tasks, we put time, cost, system, owner and risk into a structured attribute layer behind the canvas, then looked at the reporting, system mapping and compliance use cases that layer unlocks.
Where Should AI Go First? Prioritizing Processes and Tasks With Attributes
How to prioritise AI initiatives from your process models instead of case by case. We ran two passes: on the process level, two simple attributes and a filter produced a shortlist; on the task level, value potential against feasibility picked the first initiatives. In our example that left five concrete opportunities.