April 14, 2026
Community Voice
.png)
Your AI-assisted product change starts brilliantly. The first analysis is excellent, and the second builds reasonably well. By the fourth interaction, the AI contradicts earlier decisions and forgets critical constraints.
This isn’t AI failure; it’s context degradation. Large language models have fixed context windows. As conversation accumulates, earlier exchanges compress or disappear.
The scaffolding pattern, as demonstrated by Benedict Smith, addresses this through structured techniques mapping directly to CM governance.
Context engineering maintains structured project files providing consistent information to each AI interaction. Effective implementations use explicit configuration state documents capturing scope, affected components, constraints, and design intent. This is standard change control documentation. Organizations maintaining rigorous CM baselines already have this discipline.
Task decomposition breaks workflows into atomic, verifiable units. Instead of “complete this change,” decompose it into discrete tasks: generate CAD modifications, run FMEA, and validate BOM consistency, each as a separate interaction with clear acceptance criteria.
Sub-agent execution deliberately discards context between tasks. Each discrete task executes in a fresh AI instance with only relevant context, preventing error propagation.
According to research on context degradation, effective context windows are “much smaller than advertised token limits.” This phenomenon—”context rot”—means LLM performance degrades as the context window fills, making scaffolding essential.
Scaffolding aligns with governance requirements. Organizations maintaining rigorous CM2 baselines, clear change processes, and structured documentation already have what scaffolding requires.
PLM systems should become an infrastructure that scaffolded workflows interact with, not monolithic interfaces that engineers navigate manually. Context files maintained in version control capture design intent. Validation agents enforce constraints automatically. Human approval gates preserve accountability.
One could start with scaffolding for specific, bounded workflows where governance requirements are well-understood. Engineering change orders affecting well-characterized part families. Build expertise where failure is recoverable before extending to safety-critical applications.
If your team can’t explicitly articulate CM requirements for structured prompting, do they lack the discipline needed to manage CM effectively, even without automation?
What’s your experience with sustained AI workflows? Have you encountered context degradation in multi-day configuration management tasks?
Use code Martijn10 for 10% off training—and don’t forget to tell them Martijn sent you 😉.
Copyrights by the Institute for Process Excellence
This article was originally published on ipxhq.com & mdux.net.
Known by his blog moniker MDUX—Martijn is a leading voice in enterprise configuration management and product lifecycle strategy. With over two decades of experience, he blends technical depth with practical insight, championing CM2 principles to drive operational excellence across industries. Through his blog MDUX:The Future of CM, his newsletter, and contributions to platforms like IpX, Martijn has cultivated a vibrant community of professionals by demystifying complex topics like baselines, scalability, and traceability. His writing is known for its clarity, relevance, and ability to spark meaningful dialogue around the evolving role of configuration management in Industry 4.0.
