Frontmatter

About Frontmatter

In The Leanpub Podcast, we interview authors and special guests about their lives & careers, their areas of expertise and the issues of the moment, and their experiences as writers. Every episode is deeply researched and covers areas that are equally of human interest, general interest, and professional interest.

Publisher

Leanpub

Category

arts

Language

en

Explicit

No

First episode

4 Apr 2012

Latest episode

8 Oct 2026

Latest episodes

49 of 340 episodes have a transcript.

1. 

   8 Oct 2026TRANSCRIPT

   The Leanpub Podcast 🎙 Feat. Fiodar Sazanavets, Author of Production-Grade Python, LangChain & LangGraph

   Host Len Epp interviews Fiodar Sazanavets, author of Production-Grade Python, LangChain & LangGraph, about building robust AI systems and the enduring value of engineering fundamentals.

2. 

   11 Sept 2026

   The Leanpub Podcast 🎙 Feat. Yevgen Nebesov, Author of The Architecture of Power

   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.

3. 

   13 Aug 2026

   The Leanpub Podcast 🎙 Feat. Ediz Najim, Author of Systems Thinking for Agentic AI

   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.

Inside a recent episode

The Leanpub Podcast 🎙 Feat. Fiodar Sazanavets, Author of Production-Grade Python, LangChain & LangGraph

Published 8 Oct 2026 · Transcript excerpt

[…] It's a bit more complex than that, but this is what, in a nutshell, they are. By production grade, what I mean is How are applications developed? How is repository structured? How are tests executed? How do you integrate Python into release pipeline? When the Python application is running, what are the caveats? What do you have to watch out for? Those kind of things. And I started taking a lot of notes in my own documents, in chat, GPC charts, everywhere. I ended up with a lot of different notes. And then I kind of realized, wait a minute, because this field is growing while every other niche of software development is shrinking, there are probably going to be a lot more people that will be looking to go through exactly the same process as I went. […]

Who has been a guest on Frontmatter

Names identified in recent episode analyses. Showing up to five guests.

• Fiodar Sazanavets
• Sal Kimmich
• Matthew Hawthorne
• César Antonio López Segura
• Rich Allen

Reach and audience

Public platform figures. Ratings count people who left a rating, not total listeners.

YouTube views

474,075

Score snapshot 15 Sept 2025

Apple Podcasts (US)

4.8 / 5

5 ratings

Podcast Authority Score: 64 / 100

A composite of feed quality, social presence, YouTube performance and engagement. Read the methodology.

Quality

81

Social presence

0

YouTube

86

Engagement

32

Contact Frontmatter

Guest appearances

Books guests

Based on episode analysis; this does not confirm that the show is currently accepting guests.

Questions about Frontmatter