The Mob Mentality Show

In this Mob Mentality Show episode, we sit down with Elizabeth Hendrickson and Joel Tossi for a fascinating deep dive into systems thinking, context, and variability. Drawing from the core ideas in their book, Signals and Levers, this conversation explores how mapping systems can transform organizational alignment, shift how leaders invest their resources, and expose the hidden dependencies across seemingly disconnected departments.
Elizabeth and Joel share practical insights into how causal loop diagramming, managing side effects, and looking closely at structural constraints can help teams escape the traps of rigid delivery cadences. They discuss how a shared systemic perspective shifts conversations away from isolated department goals and toward true organizational adaptability and collaboration.
We dig into:
• How systems thinking and causal loop diagramming can map the hidden intersections between software, hardware, sales, and marketing.
• The way analyzing system delays and constraints can dramatically shift executive investment strategy to focus where it's needed most.
• Why understanding systemic variability is more important for overall organizational health than merely forcing a predictable delivery cadence.
• Moving beyond superficial agile practices to build true, data-driven alignment between cross-functional business leaders.
• Real-world stories from the field of immersive learning, dojos, and designing organizations built to adapt organically.
Whether you are a software crafter, a product leader, or an executive interested in systems design, this episode offers a practical guide to stepping back, seeing the bigger picture, and finding the true levers that drive high-performing organizations.

In this Mob Mentality Show episode, Chris Lucian sits down with Diana Larsen — co-author of Lead Without Blame, Five Rules for Accelerated Learning, and Agile Retrospectives — to explore what leadership looks like when your team is made of both humans and AI agents. Diana, who came into agile "through the XP door" in the late 90s, argues that a team of some number of humans plus some number of agents is still a complex adaptive system: it has a container, an identity, differences among its players, and exchanges that let it collaborate. The practices we built for human teams — retrospectives, chartering, liftoffs, checkpoints — still apply, if we're intentional about bringing them along.

Diana shares her "your agent is your mirror" idea (inspired by the book Your Dog Is Your Mirror): LLMs reflect the behavior they were trained on, and the way we talk to them shapes us too. She types please and thank you to her agents — not for them, but to retain her own humanity. Chris connects this to Theory X vs. Theory Y prompting, his agents.md files with single and double loop learning built in, and his experiments using a frontier model to build a deterministic TDD state-machine MCP server that keeps a less capable model honest — like a senior developer building a process for a junior.

The conversation then turns to mobbing with agents and the leadership challenges of this moment. Chris describes how his mobs use "weighing the ox" (wisdom of the crowd) prompting, collaborative prompting, and rotating across four machines, and why the 20-minute agent runtime is a key threshold for context switching. He argues mobbing is more valuable than ever because the typing was never the hard part. Together they discuss the diffusion of innovation, why "Agile is dead" gets declared at every chasm crossing, token maxing as Goodhart's Law taken to its extreme, the Red Queen hypothesis, why no one should have been laid off over AI, and a broken hiring pipeline where a "beautiful" new-grad resume from three years ago now gets 6 callbacks out of 700 applications.

We dig into:

Human + agent teams as complex adaptive systems — and why the old team practices still apply.

"Your agent is your mirror": blaming language, hallucinations, and retaining our humanity by saying please and thank you.

Theory X vs. Theory Y prompting, and agents.md files that invite single and double loop learning.

Why you should value stream map and remove waste before going agentic — or your agents will just perform bureaucracy.

Keeping prompts small and bite-sized (from Five Rules for Accelerated Learning) while still leaving room for emergence.

"AI gaslighting" in TDD and using a frontier model to build a deterministic MCP server that a smaller model must follow.

Mutation testing and building friction points into flow systems to check you're still heading the right way.

The naive observer in the ensemble — Diana's Roman numerals kata story from one of Woody Zuill's workshops.

"Weighing the ox" prompting, collaborative prompting, and the 20-minute threshold for short vs. long agent workflows.

Why mobbing is more valuable than ever when the typist role has become minimal.

Leading through the diffusion of innovation: AI-forward vs. AI-resistant people, token maxing, and Goodhart's Law.

The Red Queen hypothesis and why laying off developers over AI was a bogus move.

A broken pipeline into jobs: resumes, interviews, and university curricula that need to change.

Agile is dead (again?), the iPod wheel, and how innovations reshape as they cross the chasm.

Why AI is unwittingly nudging people into XP, lean, and good work process — tests included.

Podcast Episode… Apple: https://podcasts.apple.com/us/podcast/the-mob-mentality-show/id1485950034 Spotify: https://open.spotify.com/show/01npjdd1VRiNqw1RZ8aB5g?si=607de4da208a425c PodBean: https://mobmentalityshow.podbean.com/ Amazon: https://music.amazon.com/podcasts/7a695161-1857-466d-83ca-d9a75161823b/the-mob-mentality-show

References… Diana Larsen's LinkedIn: https://www.linkedin.com/in/dianalarsenagileswd/ Diana Larsen's website (Thrive in Turbulent Times program): https://dianalarsen.com/ Lead Without Blame by Diana Larsen and Tricia Broderick Five Rules for Accelerated Learning by Willem Larsen and Diana Larsen Clickchain.ai: https://clickchain.ai/ Your Dog Is Your Mirror by Kevin Behan Diffusion of Innovations by Everett Rogers Pacific Northwest Software Quality Conference: https://www.pnsqc.org/ OOP Conference Munich: https://www.oop-konferenz.de/

Thanks to G-SLiK (https://soundcloud.com/g-slik) for the intro and outro music.

Chris Lucian and Austin Chadwick discuss all things #agile and product development from a #MobProgramming perspective.

Chris Lucian is the Director of Software Development at Hunter Industries and a founder of mob programming. https://www.chrislucian.com/p/chris-lucian-biography.html

Austin Chadwick is a Mob Programmer at Hunter Industries and is a passionate agilist and craftsman with experience in several roles (e.g. coach, developer, tester, scrum master, business analyst). https://www.linkedin.com/in/austin-chadwick-3a58151a4/

We would love your feedback and ideas for future episodes! Please add comments to the video or reach out to us on Twitter ( https://twitter.com/mob__mentality & https://twitter.com/ChristophLucian ).

All statements and opinions expressed by Chris, Diana, and Austin are solely their own and do not represent the views of any company. Chris and Austin are just sharing and not recommending ( https://justsharing.dev/ ).

In this Mob Mentality Show episode, Chris Lucian sits down with Woody Zuill and James Herr to explore one of the most pressing questions in software teaming today: when AI is writing the code and your team is barely touching the keyboard, where does mob programming fit in? Rather than pushing collaboration aside, James and Woody argue that AI is exposing long-standing bottlenecks more clearly than ever — and that the ensemble is more important now, not less. They share the "AIM Mobbing" perspective they are developing, showing how AI and software teaming unlock the full ensemble by finally removing code as a barrier to participation.

Chris adds insights from his own agentic workflow experiments at Hunter Industries — running multiple agents in parallel in a "plate spinning" pattern, using a mutation testing agent running continuously in the background, and crafting large prompts designed to complete 2+ hours of work autonomously. The group also explores how context window management, modular skills files, and code generators solve the consistency problems that make many developers skeptical of AI-generated code. Woody shares his honest experience with LLM reliability and the importance of having strong verification mechanisms in place — including unit tests used as guardrails rather than as a test-driven design tool.

The episode closes with a rich reflection on this chaotic and exciting moment in software history. Woody compares it to the earliest days of programming: discovery happening in real time, the ground shifting underfoot, and ideas growing faster when shared. All three guests agree that teams who use AI as a highly amplified collaborative learning environment will be best positioned to thrive — and that the skill of giving high-level intent, central to mob programming, is the same skill that unlocks the most from an AI agent.

We dig into:
- How AI accelerates the exposure of queuing and bottlenecks throughout the entire software development lifecycle.
- Why removing code as a barrier enables product owners, UX designers, and testers to join the ensemble full-time.
- The "plate spinning" pattern: running multiple AI agents simultaneously to eliminate wait time for the mob.
- Chris's agentic kata practice: 3 months of prompts crafted to run 2+ hours without errors, and what he learned.
- Context window management: keeping LLM context at ~50% capacity using tiny instruction files and modular skills files.
- Using AI to write code generators (not production code directly) for deterministic, consistent output.
- Unit tests as guardrails for AI-generated code rather than as TDD design tools.
- Woody's experience with LLM limitations — hardcoded outputs, forgotten context, and the need for verification.
- The high-level intent parallel: how directing an AI agent mirrors the navigator/driver model in mob programming.
- Why this chaotic period in software development is the most exciting in decades — and why teams will navigate it better than solo developers.

Podcast Episode…
Apple: https://podcasts.apple.com/us/podcast/the-mob-mentality-show/id1485950034
Spotify: https://open.spotify.com/show/01npjdd1VRiNqw1RZ8aB5g?si=607de4da208a425c
PodBean: https://mobmentalityshow.podbean.com/
Amazon: https://music.amazon.com/podcasts/7a695161-1857-466d-83ca-d9a75161823b/the-mob-mentality-show

References…
Woody Zuill's LinkedIn: https://www.linkedin.com/in/woodyzuill/
James Herr's LinkedIn: https://www.linkedin.com/in/james-herr/
Software Teaming / Mob Programming Resources: https://woodyzuill.com/

Thanks to G-SLiK (https://soundcloud.com/g-slik) for the intro and outro music.

Chris Lucian and Austin Chadwick discuss all things #agile and product development from a #MobProgramming perspective.

Chris Lucian is the Director of Software Development at Hunter Industries and a founder of mob programming. https://www.chrislucian.com/p/chris-lucian-biography.html

Austin Chadwick is a Mob Programmer at Hunter Industries and is a passionate agilist and craftsman with experience in several roles (e.g. coach, developer, tester, scrum master, business analyst). https://www.linkedin.com/in/austin-chadwick-3a58151a4/

We would love your feedback and ideas for future episodes! Please add comments to the video or reach out to us on Twitter ( https://twitter.com/mob__mentality & https://twitter.com/ChristophLucian ).

All statements and opinions expressed by Chris, Woody, James, and Austin are solely their own and do not represent the views of any company. Chris and Austin are just sharing and not recommending ( https://justsharing.dev/ ).

Chris Lucian and Austin Chadwick discuss all things #agile and product development from a #MobProgramming perspective. What if you could decompose every agile method down to its essential building blocks and recombine them for your own specific context? In this episode, Chris and Austin are joined by Aria Omidvar to explore the HEXI method — a framework-agnostic approach to understanding and applying agile, lean, and software craftsmanship practices through physical hexagon objects and collective sense-making.

Aria shares his journey from software craftsmanship and clean code, through Scrum and XP, to discovering Dave Snowden's HEXI method and building his own independent "Hexiverse" — a modular knowledge map that spans Software Teaming, Extreme Programming, Kanban, Modern Synthesis, the Agile Manifesto, and more. He unpacks how breaking methods into reusable hexagonal pieces allows teams (and individuals) to see the connections between ideas, surface what is missing, and navigate the overwhelming landscape of agile methods without falling into method wars.

We dig into:

What the HEXI method is and how Dave Snowden and Nigel Thurlow introduced it via Scrum.org

How Aria independently adapted HEXI to create a Hexiverse for software teaming and mob programming

Why decomposing methods into building blocks enables recombination for any specific context

The spatial design choices behind the Hexiverse — and why dotted hexagons signal a concept shared across sets

How Alistair Cockburn validated the Agile Manifesto hexiset (and why that meant the world to Aria)

The learning journey metaphor of islands growing large enough to connect — and how the Hexiverse accelerates that

Why "nice" doesn't cut it in high-collaboration environments — and how kindness, consideration, and respect offer a deeper model

The "turn up the good" retrospective format and why it flips the traditional improvement lens

How the Hexiverse serves both as a personal learning quest and a potential onboarding tool for teams new to agile methods

Aria's call to action: check the original HEXI sources, play with the physical kits, and consider building your own Hexiverse

Scaling Complex Systems by Building on Agile Frameworks with Dave Snowden and Nigel Thurlow: https://youtu.be/AEf1BCffimA
Aria's Hexiverse on Miro: https://miro.com/app/board/uXjVKv84GGU=
The Hitchhiker's Guide to Hexiverse on Medium: https://medium.com/@omidvar.aria/list/the-hitchhikers-guide-to-the-independent-hexiverse-fe509a7c46f8
The Hitchhiker's Guide to Hexiverse on LeanPub: https://leanpub.com/HG2H

In this Mob Mentality Show episode, we join James Herr and Woody Zuill for a one-of-a-kind session James calls the "Hot Sauce Ensemble" — mob programming a video game from scratch in the Godot engine using AI, while eating escalating hot sauces every three-minute rotation. Fair warning to podcast listeners: this episode has a strong YouTube component. If things start sounding chaotic and spicy, that's because they are — jump over to YouTube to see what's happening on screen.

James set up the session with Claude Code in VS Code (backed by Amazon Bedrock) and a blank Godot project containing only one asset: a hot sauce sprite generated by ChatGPT. From there, the mob navigated an AI coding agent through a real-time game build — adding player movement, landing explosions, and physics-based bell pepper enemies that scatter when stomped. The enemies were bell peppers specifically because Chris despises them. The hero is hot sauce. The logic is sound. Along the way, James introduced the "plate spinning" technique: opening multiple AI agents in parallel terminals so one prompt cooks while the mob drives another, keeping momentum even when AI responses run long.

We dig into:

How "Hot Sauce Ensemble" combines traditional mob rotations with escalating spicy food — and why it works as a team-building format

Using Claude Code in VS Code with Godot to build a playable game from a blank project in real time

The plate spinning technique: running multiple AI coding agents in parallel terminals to maintain flow

Why the goal should be "effective," not "productive" — and how mob programming and AI tools both support that shift

How AI procedurally generates game art assets (bell pepper sprites built from polygon shapes and shading) without any image generation tools

Navigating an unfamiliar codebase and engine as a mob, using an AI agent as the technical guide

What happens to your prompting quality when habaneros and The Last Dab are involved

Hot sauce as a hero, bell peppers as villains: designing game mechanics around personal taste (literally)

If you've ever wondered what mob programming looks like when applied to game development, AI-assisted coding, and competitive spice tolerance all at once, this episode delivers all three simultaneously — with physics.

 

References… James Herr's LinkedIn: [PASTE LINK] Woody Zuill's LinkedIn: [PASTE LINK] Godot Engine: https://godotengine.org/ Claude Code: https://www.anthropic.com/claude-code Mobster (mob timer): [PASTE LINK]

Hot Sauces Featured… James: Hot Ones Apricot Sauce (#7), Hot Ones The Last Dab (#10) Woody: Taco Bell Hot Sauce, ~3 lbs pickled jalapeños (stuffed in a burrito) Chris: Fishwife Albacore in Spicy Olive Oil, Oni Yuzu Lemon Hot Sauce (Japan), Marie Sharp's Carrot & Habanero (2-habanero, 4-habanero Blazing Hot, and 5-habanero BEWARE) on a PB&J

Thanks to G-SLiK (https://soundcloud.com/g-slik) for the intro and outro music.

Chris Lucian and Austin Chadwick discuss all things #agile and product development from a #MobProgramming perspective.

Chris Lucian is the Director of Software Development at Hunter Industries and a founder of mob programming. https://www.chrislucian.com/p/chris-lucian-biography.html

Austin Chadwick is a Mob Programmer at Hunter Industries and is a passionate agilist and craftsman with experience in several roles (e.g. coach, developer, tester, scrum master, business analyst). https://www.linkedin.com/in/austin-chadwick-3a58151a4/

We would love your feedback and ideas for future episodes! Please add comments to the video or reach out to us on Twitter ( https://twitter.com/mob__mentality & https://twitter.com/ChristophLucian ).

All statements and opinions expressed by Chris and Austin are solely their own and do not represent the views of any company. Chris and Austin are just sharing and not recommending ( https://justsharing.dev/ ).