What Will Remain Human in Software Architecture? A Focus Group Report
Source
Uwe van Heesch, Olaf Zimmermann, Christian Kohls
Author
Uwe van Heesch, Olaf Zimmermann, Christian Kohls
Date
Key takeaways · AI-distilled
In a 22-person focus group at EuroPLoP 2026, practitioners broadly agreed that architectural decisions, accountability and writing architectural guardrailsThe checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.Full definition → remain human work even as AI agents take on architecture tasks.
Participants named agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → engineering as a new discipline: building the system that governs AI-assisted development, including validation mechanisms, knowledge layers and company-specific standards.
The group proposed criticality, the combination of uncertainty and cost of change, as the single criterion for deciding how much human oversight an AI-assisted decision needs.
A recurring worry was cognitive debt, the gradual loss of human understanding of a system when AI-assisted decisions are accepted without real engagement.
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
Why it matters
Practitioners at EuroPLoP 2026 argue accountability and architectural decisions stay fundamentally human even as AI takes on more design work, and name 'harness engineering' as the emerging discipline of building the systems that govern AI-assisted development.
articleAI Agents Push Humans Out of the LoopMargaret Mitchell, Avijit Ghosh, Samir Passi
articleAI Evaluation Should Work With HumansJan Kulveit, Gavin Leech, Tom\'a\v{s} Gaven\v{c}iak, Raymond Douglas
articleDo AI Agents Understand Computer Architecture?Ambika Sharan, Grigory Chirkov, Soheil Abbasloo