Summary: Thinking Like an Architect in the Age of AI-Assisted Coding

Podcast: Scrum Master Toolbox Podcast – BONUS Episode
Host: Vasco Duarte
Guest: Brian Childress, CTO & Software Architect
Date: January 24, 2026

Episode Overview

This bonus episode explores how the rise of AI-assisted coding tools is changing the software development landscape, especially the role of software architects. Vasco Duarte talks with Brian Childress—a CTO and architect with rich experience across regulated industries—about how engineers and leaders can adapt, avoid common pitfalls, foster a constructive team culture, and future-proof their roles by focusing on designing systems, not just generating code.

Key Discussion Points & Insights

1. Complexity in the Era of AI-Assisted Coding

• AI tools multiply complexity: Brian highlights that AI can produce copious amounts of code quickly, which, if unguided, can lead to overly complex, confusing systems.

  • "Most engineering projects and software engineers themselves lean more towards complexity. And I find that that complexity really is multiplied. When we bring in the power of AI..." (02:34 – 03:13)

• Need for architectural thinking: The faster pace enabled by AI demands a higher-level approach to design and systems thinking, shifting engineers from pure "code authoring" to architectural roles.

2. From "Vibe Coding" to Intentional Architecture

• Defining “vibe coding”:

  • Vibe coding = rapid prototyping via AI prompting until "something works."
  • Valuable for product owners and designers to quickly test ideas, akin to moving from wireframes to high-fidelity prototypes.
    • "I'm just going to prompt until I get something works that really demonstrates what I'm trying to do. That's an incredibly powerful tool set..." (06:15 – 07:06)

• Limits of vibe coding for production:

  • While great for experimentation, there's a risk of complexity, lack of maintainability, and unclear problem-solving if teams stop at this stage.
  • The critical transition: moving from raw AI outputs to intentional, structured system design.

3. What Does It Mean to “Think Like an Architect” with AI?

• Role shift:

  • More focus on how high-level components fit together, less on detailed code or framework specifics.
  • The architect’s mindset centers on fully understanding the problem (business, customer/user, technical), then designing the simplest, most effective system to meet those needs.
  • "When I'm thinking more like an architect, I'm thinking more around, okay, how do bigger components, higher level components start to fit together..." (08:57 – 09:40)

• Collaboration with AI:

  • Use AI as a thought partner or sparring partner; explain the problem and strategy, get feedback, and challenge assumptions.
  • AI can help uncover solutions and challenge assumptions—but only if prompted and directed well.
  • "I have the ability to collaborate just like I would some other technology partner. I just have something... that has just a huge corpus of knowledge..." (10:49 – 11:54)

• Explaining & simplifying problems:

  • Clear communication (with humans and AI) is essential. Engineers often "hide behind complexity," but using AI requires concise, jargon-free explanations.
  • "Most software engineers will hide behind complexity because they don't understand the problem... AI back and forth, it really forces us to be able to explain what it is that we're working on..." (12:33 – 13:36)

• Diagrams over text:

  • Diagrams and visualizations outperform written explanations for building shared understanding—especially important when guiding both humans and AI.
  • Brian recommends using basic shapes (square, triangle, circle, line) to map out systems at a high level.
    • "If I can't diagram everything out, then we're still... we still have too much complexity..." (17:15 – 18:21)

4. AI as a Culture- and Capability-Shaper

• Adoption challenges:

  • More senior engineers may resist AI (fear of job loss, concern about code quality—"AI slop").
  • Leadership should frame AI as a tool to learn, not a threat, and encourage experimentation/failure as part of the process.
    • "I like to frame it as, we're all going through this, we're all learning it..." (19:08 – 20:14)

• Guardrails and best practices:

  • To use AI safely, teams need the same guardrails as with human engineers: code standards, testing, automation, reviews, and documentation.
  • AI can help deliver those practices (like docs and tests) that are often neglected.

5. Failure Stories & Lessons Learned

• AI as an unreliable autopilot:
  • Brian shares a failure where he generated an implementation plan with AI, didn’t review it critically, and handed it to the team—leading to confusion and wasted effort.
    • "The mistake I made was I took what it put out and I didn't really think through what it was... And it became a big point of tension within the team..." (22:14 – 23:23)
  • Emphasizes the need for review, reflection, and critical thinking over blind trust in AI outputs.

6. Looking Ahead – The Evolving Role of Software Engineers & Architects

• Architectural thinking for all:

  • Brian predicts that more engineers will need to think like architects—focusing on overall system design and problem-solving, with AI handling repetitive coding.
    • "I'm going to see more engineers acting like architects. More engineers are going to be thinking in ways of how do I construct this system, how do I move data around..." (24:38 – 25:18)

• Experimentation & continuous learning:

  • AI unlocks time for engineers to improve systems, documentation, and testing. But risks remain—a need for best practices and vigilant oversight.
  • Anticipates continued debate over "AI slop" and more high-profile failures as AI’s use expands.

7. Resources & Practical Next Steps

• Brian’s learning approach:

  • Leans on YouTube channels for up-to-date knowledge about AI trends and coding practices.
  • Recommends hands-on experimentation—“play with everything”—and documenting learnings to share with others.
    • "What I've always found helpful is to document what I'm learning as I'm learning it, not only for a resource for me, but then potentially I can share it with others." (27:05 – 27:49)

• Where to follow Brian:

  • Best place: Brian-Childress on LinkedIn
    • "I'm most active on LinkedIn..." (28:16)

Memorable Quotes

• On the core AI challenge:

  • “The real challenge isn't writing of the code, it's designing systems that scale with users, features, and teams.” — Vasco Duarte (01:42)

• On why simplification matters:

  • “Technology is the easiest part of what we do. I can Google my way to a solution, I can now generate my solution. But is that solution the thing that I needed?” — Brian Childress (16:07)

• On future-proofing your skills:

  • “We need to learn to use AI for that. And this episode will, I'm sure, unveil some secrets and clarify some mysteries about that.” — Vasco Duarte (01:23)
  • “Being open to it, being willing to learn and to fail and to… keep pushing forward. Those are the engineers that I want on my teams.” — Brian Childress (27:50)

Timestamps for Key Segments

• The multiplier effect of AI on system complexity: 02:34
• Defining “vibe coding” and spectrum of AI tool use: 06:05
• Architectural thinking vs. coding details: 08:37
• AI as a thought partner/sparring partner: 10:49
• Importance of clearly explaining problems/simple diagrams: 13:36 & 17:15
• Cultural aspects and resistance to AI, the “AI slop” fear: 19:08 & 24:38
• Failure story: blindly trusting the AI: 22:14
• Future of engineering roles with AI: 24:38
• Brian’s resource and learning recommendations: 27:05
• Where to follow Brian Childress: 28:16

Tone

The episode maintains a candid, practical tone—punctuated by humor, humility, and encouragement. Both participants speak as practitioners immersed in ongoing change, emphasizing learning, adaptability, and community-driven best practice sharing.

This summary was created to offer a comprehensive, context-rich overview, with key moments and actionable insights for software professionals navigating the AI-assisted future of coding and architecture.