The Leanpub Podcast

Yevgen Nebesov on The Architecture of Power

In this episode of the Leanpub Podcast, Len Epp speaks with Yevgen Nebesov, an independent systems architect and consultant based in Bruchsal, about his Leanpub book The Architecture of Power: See What Shapes Outcomes. Find Where You Can Act.

Background and career

Yevgen grew up in Kharkiv, Ukraine, and moved to Germany at eighteen, where he studied mathematics and informatics in Hannover. He progressed from software engineer to lead architect and technical project lead over fifteen years, working across regulated environments such as medical devices and defence as well as transport, retail, and logistics. He describes the systems architect role as a “glue” position that bridges business stakeholders, developers, and delivery teams.

The AI question and human agency

The conversation turns to AI as a driver behind the book. Yevgen argues that as intelligence becomes a commodity through large language models, and physical labour is increasingly handled by robots, what remains distinctively human is agency—the ability to act on people and arrangements rather than on software or hardware. Trust, he suggests, is the carrier through which human agency propagates change in ways an algorithm cannot replicate.

The Power Loop

The central model of the book is the Power Loop, which describes power as a flow across six domains: beliefs, institutions (rules, roles, and rituals), agendas, decisions, events, and narratives. Yevgen explains that decisions are far less important than most people assume—by the time an issue reaches a decision, it has already been filtered and framed at the agenda stage, which is itself shaped by institutions grounded in belief. Narratives select events and connect them into stories that either shift beliefs or move items onto agendas, completing the loop and reproducing outcomes.

Power mapping and the Power Canvas

To move from theory to practice, Yevgen introduces the Power Canvas, a static snapshot of the Power Loop applied to a specific situation. By working through each domain and its substructures, a practitioner can map which relationships are sustaining an unwanted outcome and identify where intervention is possible—even without full control of the system.

Narrative tactics and five types of belief

Part II of the book develops intervention tactics. Yevgen outlines five narrative jobs—name, explain, assign, project, and anchor—each designed to operate on a corresponding type of belief: ontological, epistemic, social-order, teleological, and identity beliefs. He illustrates the mechanics with an example from his own practice: logging system failures as a body of evidence, then constructing a narrative that links those events to a prior architectural decision in order to reverse it.

Writing process

Yevgen describes a writing approach inspired by the model-view-controller pattern from software engineering. He maintains a core conceptual model and generates multiple views from it—the book, his website, LinkedIn posts, and articles—rather than writing linearly. This separation of model from representation allows him to make incremental progress in ten-minute windows, fitting the project around full-time consulting work, three non-profit organisations, and three children.

This interview was recorded on September 4, 2026.

The full audio for the interview is here: https://s3.amazonaws.com/leanpub_podcasts/leanpub-podcast-template-1.00.mp3. The Leanpub Podcast is available on our YouTube channel at https://www.youtube.com/leanpub, in Apple Podcasts here https://podcasts.apple.com/ca/podcast/Leanpub/id517117137, and almost everywhere else people listen to podcasts.

Ediz Najim on Systems Thinking for Agentic AI

In this episode of the Leanpub Podcast, host Len Epp sits down with Ediz Najim, a software architect and technical leader based in Istanbul, to discuss his book Systems Thinking for Agentic AI: A Software Architect’s Guide to Building Reliable LLM and Agent Systems.

Background and Career

Ediz was born in Baghdad, where he completed his university education before moving to Istanbul to begin his professional career. His first project was a challenging Java codebase at a large company, and the experience of taking on additional responsibilities early on gave him the confidence to pursue startup work, where he had the freedom to choose technologies and frameworks. His long-term goal was always to become a software architect, and that ambition drove him to read, write, and experiment continuously.

Asked whether he would recommend university to someone starting out today, Ediz gave a clear “yes”—academic foundations matter—but he emphasised that universities should go beyond basics and give students far more hands-on, real-world software-building experience, not just brief company placements.

Why an LLM Is Not a System

The central premise of the book is that a large language model is only one component of an agentic AI system, not the system itself. Ediz uses the analogy of the human brain: a brain can think and decide, but it needs eyes, hands, and other organs to act in the world. Similarly, an LLM needs prompts, retrieval, tools, memory, orchestration, guardrails, and observability working together to form a production-ready system.

Reliability in Practice

Ediz stresses that reliability becomes critical the moment an AI system touches consequential actions—processing payments, controlling accounts, or making decisions with real-world consequences. Because LLMs are non-deterministic, every input and output must be validated by surrounding components. The system must also record every step in a traceable pipeline so that, when something goes wrong, engineers can reconstruct exactly what happened.

Evaluation

Evaluating an agentic AI system is fundamentally different from testing a deterministic one. Unit tests alone are insufficient when a component can produce anything from a perfectly relevant answer to a completely unrelated one. Ediz argues that teams must define clear input validation rules and explicit evidence criteria that determine whether an output is acceptable—before they build, not after.

The Controlled Agent Loop

Ediz offers a crisp definition of an agent: “a system that uses a model inside a controlled loop to pursue a task through actions, observations and state until a stopping condition is reached.” The loop handles user input, validates it, passes it to the LLM, manages tool execution requests from the model, and continues iterating until the LLM signals a final result. Crucially, the loop must never be infinite—engineers should set hard limits such as a maximum number of iterations or a token budget.

Tool Registries and MCP

To manage the tools an agent can call, Ediz recommends an explicit registry—implemented through the Model Context Protocol (MCP)—that declares what each tool does, what input schema it accepts, and what back-end operation it maps to. This lets the LLM simply request an action (“get the weather in Istanbul”) without needing to know the underlying URL, database query, or caching layer.

The Future of the Software Architect

Looking five years ahead, Ediz believes AI will be used everywhere in software, but cautions that the current maturity of AI systems is not yet sufficient to hand over full autonomy. The role of the architect will evolve, but human oversight and systems thinking will remain essential until AI demonstrates the reliability needed to be fully trusted.

Writing Process and STAAI

Ediz writes continuously—articles, LinkedIn posts, and drafts—without a fixed schedule, treating daily writing as a creative habit. The book grew out of accumulated notes and posts. He is also developing the STAAI architecture model, a framework of standards and principles for building agentic AI systems, more details of which can be found at STAAI.com.

The episode closes with Ediz thanking his parents for their encouragement, and with a listener request for Leanpub to offer print book services directly on the platform.

This interview was recorded on July 31, 2026.

The full audio for the interview is here: https://s3.amazonaws.com/leanpub_podcasts/FM338-Ediz-Najim-2.00.mp3. The Leanpub Podcast is available on our YouTube channel at https://www.youtube.com/leanpub, in Apple Podcasts here https://podcasts.apple.com/ca/podcast/Leanpub/id517117137, and almost everywhere else people listen to podcasts.

Leanpub Podcast: Max Guernsey III on Serial Fiction, Automation, and Self-Publishing

In this wide-ranging episode, Len Epp sits down with repeat guest Max Guernsey III — software engineer, consultant, and Leanpub author — to talk about his multiple book projects, his creative use of the Leanpub API, and his pragmatic take on AI in writing and software development.

Automating a Serial Novel with GitHub Actions

Max is currently publishing No Direction: The Severed World, Book One, a fantasy novel set in 1022 AD, as a weekly serial. Because his writing output varies week to week, he built a GitHub Actions workflow that checks for scheduled chapter files and automatically pushes releases via the Leanpub API — including release emails. As a result, he thinks not in terms of what is published, but what is queued in the hopper. Each chapter aims to contain one small narrative arc that advances the larger story, typically running around 12 pages, with the book itself being the first installment in a planned four-part series.

The Leanpub Progress Badge and Chapter Ornaments

Max had previously suggested that Leanpub add a visible writing-progress indicator to book landing pages, and Len confirms that feature is now live. The conversation also touches on chapter ornaments — decorative images at the start of each chapter — which Max requested and a Leanpub co-op student subsequently built into the platform’s Markdown and visual editor.

Marketing Nonfiction to Hard-to-Reach Executives

For his nonfiction title Fixing Software Delivery, Max’s biggest challenge is getting in front of executive readers. Len offers several concrete tactics: building coupon campaigns timed around industry conferences (using Leanpub’s new leanpub.com/coupon entry page, which allows human-readable coupon codes), speaking at conferences with a QR code on the final slide, mailing physical print copies to senior leaders, and cultivating relationships with journalists by sending them genuinely novel insights related to their published articles.

YouTube, Pinterest, and Marketing Fiction Without Spoilers

For The Other Half of Coding, Max has found YouTube — clipped with tools like Opus Clip — and, surprisingly, Pinterest to be his most effective marketing channels. For No Direction, the challenge is different: how do you promote a slow-burn, drip-reveal fantasy world without giving the story away? Max has been experimenting on X (Twitter) with theme-based posts and community building, and is exploring a dedicated YouTube channel for the series. He is also considering video readings of individual chapters, drawing a parallel to the reading tours of Mark Twain and Charles Dickens, even though the idea has met skepticism from others.

A particularly inventive asset-reuse strategy emerged from Max’s world-building work: he built a program to generate glyphs for the constructed language and script of No Direction, and was advised to post those visual assets to Pinterest — where they have generated significant daily impressions and driven traffic to the book.

AI: Useful for Research and Editing, Not for Writing or Coding

Max uses AI selectively. He values it for research — describing it as a sophisticated curve-fitting machine well suited to finding patterns — and as an editing and chapter-review aid that catches errors and occasionally surfaces a better turn of phrase. He does not use it to generate prose or code, arguing that the genuinely hard part of both is the thinking, not the typing. He also raises economic concerns, suggesting that current AI pricing is heavily subsidised and that a significant price increase is likely once investment capital recedes — making generative use cases much harder to justify financially, while research use cases may still hold value.

This interview was recorded on July 29, 2026.

The full audio for the interview is here: [episode-audio-url]. The Leanpub Podcast is available on our YouTube channel at https://www.youtube.com/leanpub, in Apple Podcasts here https://podcasts.apple.com/ca/podcast/Leanpub/id517117137, and almost everywhere else people listen to podcasts.

Gareth Holebrook on Ishi: The Discipline of Determined Intent

In this episode of the Leanpub Podcast, Len Epp speaks with Gareth Holebrook, author of Ishi: The Discipline of Determined Intent. Based in Auckland, Gareth brings together a remarkable set of experiences — Royal Navy weapons engineer, agile transformation specialist, Visa practice leader, partner to L. David Marquet on Intent-Based Leadership, and veteran of over 30 ultra-endurance events - to address a structural problem he sees destroying careers and organisations: the absence of a mechanism to distinguish endurance from self-harm while choice still matters.

From Manchester to the Royal Navy to New Zealand

Gareth grew up in Manchester and joined the Royal Navy at 18 as an engineering apprentice, specialising in electronic warfare and communications. He served in the Adriatic during the Yugoslav wars, where daily maintenance evolutions - stripping and re-greasing weapons systems, fire drills, watchkeeping - embedded the principle that muscle memory built in practice is what holds when conditions become dangerous. After leaving the Navy following redundancies in 1994, he worked in manufacturing at Sony, studied with the Open University while working full-time, moved to New Zealand in 2000, and joined GPS navigation startup Navman before founding his own altitude-training tech startup. When that business failed after the 2008 global financial crisis, he transitioned into agile coaching, eventually becoming Agile Practice Leader at Visa and connecting with former US submarine commander L. David Marquet.

The Collapse at Kona

The book opens with Gareth’s account of collapsing at kilometre 35 of the Ironman World Championships marathon in Hawaii in 2022. After 18 years of qualification attempts and a year of meticulous preparation - ceramic jockey wheels, a top-tier coach, a detailed nutrition spreadsheet - a single overlooked detail proved critical: sodium intake. In the crosswind on the bike leg he had repeatedly missed his salt tablets, and by the run he was severely hyponatraemic. He lay unconscious on the course for 40 minutes with 7 kilometres remaining. A sponsor gave him an electrolyte solution, he recovered, and he finished in 13 hours 16 minutes — two hours slower than planned.

For years Gareth framed this as a story of unstoppable persistence. Writing the book forced a different reading: a lifelong pattern of goal fixation, of becoming so blinkered that awareness switched off while effort continued. That pattern, he argues, is not a character flaw but a structural failure - the absence of a governing mechanism that could have caught the drift before collapse made correction impossible.

The Ishi Spiral

The book presents the Ishi Spiral, a four-phase discipline drawing on Japanese concepts: Decide (Ishi 意志), Forge (Shugyo 修行), Persist (Gaman 我慢), and Reflect (Hansei 反省). Gareth describes the spiral - rather than a closed loop — using the Zen calligraphic form of the Enso circle: when you return to the beginning you are not in the same place; you have grown, the environment has changed, and you have learned. The phases are not sequential stages to complete but interconnected practices active throughout any sustained endeavour.

A central tool is the Ishi card: a written governance artefact on which the practitioner records their intent, their first move, their strategies for persisting when discomfort arrives, their exit triggers, and the questions their future self will ask about the decision quality - not the outcome. Gareth draws on Annie Duke’s work on resulting and on L. David Marquet’s book Distancing (co-authored with Professor Mike Gillespie) to explain why psychological distance from one’s own ego is essential to both the Decide and Reflect phases.

Organisational Case Studies

The book’s fourth section applies the spiral to real organisational failures: American Apparel’s CEO burnout, Kodak’s failure to reflect and redirect, Bonser Aviation’s collapse from insufficient deliberate practice, the 1971 sinking of HMS Artemis in Gosport through accumulated small lapses, and the 2023 grounding and sinking of HMNZS Manawanui in Samoa, whose bridge transcripts reveal crew members unpractised in procedures they were expected to execute under pressure. Each case, Gareth argues, shows the absence of one or more phases of the Ishi Spiral - not individual moral failure but systemic drift that had been accumulating long before the visible collapse.

Writing the Book on Leanpub

Gareth signed up to Leanpub in early 2020, drawn by its incremental, iterative publishing model. The book itself became an Ishi - a declared intent, governed over several years through deliberate daily writing practice (a thousand words a day at one stage, then a daily Kaizen post on LinkedIn), persistence through COVID disruptions, a dropped client, and a week writing in a camper van at the Sydney Ironman World Championships in October 2024. He launched Ishi: The Discipline of Determined Intent on 6 January 2026 - deliberately chosen as Quitter’s Day, the second Friday of January - alongside a companion Ishi Guide and a separate book of 100 Kaizens, all published on Leanpub.

This interview was recorded on July 6, 2026.

The full audio for the interview is here: [episode-audio-url]. The Leanpub Podcast is available on our YouTube channel at https://www.youtube.com/leanpub, in Apple Podcasts here https://podcasts.apple.com/ca/podcast/Leanpub/id517117137, and almost everywhere else people listen to podcasts.

In this episode of the Leanpub Podcast, Len Epp interviews Jay LaCroix, creator of Learn Linux TV and author of Switching to Linux: A Practical Guide for Windows and Mac Users. Jay shares the story of how he discovered Linux, built one of YouTube’s largest Linux education communities, and wrote a practical guide to help newcomers make the transition from Windows or macOS with confidence. Drawing on more than two decades of professional Linux experience, he explains why Linux has never been more accessible and practical for everyday users.

The conversation explores how to choose the right Linux distribution, what new users should expect during the transition, hardware compatibility, gaming on Linux, the role of the terminal, and the misconceptions that often discourage people from making the switch. Len and Jay also discuss AI, open source software, content creation, and why learning Linux remains a valuable skill for developers, IT professionals, and curious computer users alike.

Whether you’re considering Linux for the first time or looking to deepen your understanding of the open source ecosystem, this episode offers practical advice, encouraging stories, and a realistic look at what modern Linux has to offer.

This interview was recorded on July 2, 2026.

The full audio for the interview is here: https://s3.us-east-1.amazonaws.com/leanpub_podcasts/335-Jay+LaCroix-2026-07-02.mp3. The Leanpub Podcast is available on our YouTube channel at https://www.youtube.com/leanpub, in Apple Podcasts here https://podcasts.apple.com/ca/podcast/Leanpub/id517117137, and almost everywhere else people listen to podcasts.