Chapter 12 opens Part III: The Architect's AI Team with the architect as a user of AI, before it turns to the agents the architect designs. This chapter describes what the architect can usefully do with assistants, what the evidence says about speed and quality, how architecture information stays confidential, and which records make the use reviewable. It concerns Shift 1, from documents to code, because the architect's drafts are artefacts in a repository that tests and reviewers can check, and Shift 4, from sole author to conductor of an AI team, because the first step towards conducting a team is to answer for the output of one assistant.
The chapter treats Mode 1 Conversational assistants, Mode 2 Embedded workplace assistants and Mode 3 Agentic work tools (AI Governance, Chapter 2; AI Platform and Security, Chapter 2) (162, Nordqvist, 2026) (163, Nordqvist, 2026). Here the AI acts with the architect's identity, and the architect answers for its output. This book builds on the conclusion that the usage mode, not the model, sets the risk, and that an AI acting with a person's identity differs in kind from a Mode 5 agent with an identity of its own (AI Red Team, Chapter 6) (164, Nordqvist, 2026).
The architect's work divides into four kinds of task where an assistant can take part, and each fails differently, so the verification that suits one does not suit the others. Drafting covers decision records, policy text and tender annexes; its failure is a fluent draft that states a position the architect never reached. Research covers standards, regulatory texts and incident reports; its failure is a fabricated or misattributed source. Package names are a documented instance: a study of code-generating models found that they recommend packages that do not exist, at a higher rate for open-weight than for commercial models (186, Spracklen et al., 2025), so an architect who researches with an open-weight model on self-hosted capacity, as Nordvik Region does, must verify more, not less. Review reads a design or pull request against a standard or the control catalogue (Chapter 9); its failure is the invented gap and, more dangerous, the real gap left unmentioned. Analysis reads logs and configurations for patterns; its failure is a pattern drawn from an unrepresentative sample.
Primary topics explored
- What architects use AI for
- Modes 1 to 3 for architecture work
- The evidence on productivity
- The evidence on quality and security
- Confidentiality of architecture information
- Skills, instructions and prompt records
About The Transformed Security Architect
The Transformed Security Architect is Book 6 of The Transformed Architecture. It describes how the security architect role is transformed when architecture is code, when AI drafts and acts, and when adversaries move at machine speed: the craft, the architect's own AI team, the role in the organisation, the competences and the career, for European enterprises and public authorities.
It builds on the conclusions of Architecture as Code, AI Governance, AI Platform and Security, AI Red Team and AI Threat.
Security architects, CISOs and heads of security architecture, enterprise, solution and AI architects, engineering leads, competence and hiring leads, procurement and programme leaders, and risk, compliance and audit.
Gunnar Nordqvist
Conceived, directed and published the books of The Transformed Architecture.
Continue with the full chapter
Chapter 12: The Architect's Own Use of AI: Drafting, Research and Review in Modes 1 to 3 in The Transformed Security Architect gives the detailed explanations, practical examples and implementation patterns behind this summary.
This whitepaper belongs to “The Architect's AI Team” and is one of 31 drawn from the manuscript.