pair programming Archives - Scrum Master Toolbox Podcast

AI Assisted Coding: Treating AI Like a Junior Engineer – Onboarding Practices for AI Collaboration

In this special episode, Sergey Sergyenko, CEO of Cybergizer, shares his practical framework for AI-assisted development built on transactional models, Git workflows, and architectural conventions. He explains why treating AI like a junior engineer, keeping commits atomic, and maintaining rollback strategies creates production-ready code rather than just prototypes.

Vibecoding: An Automation Design Instrument

“I would define Vibecoding as an automation design instrument. It’s not a tool that can deliver end-to-end solution, but it’s like a perfect set of helping hands for a person who knows what they need to do.”

Sergey positions vibecoding clearly: it’s not magic, it’s an automation design tool. The person using it must know what they need to accomplish—AI provides the helping hands to execute that vision faster. This framing sets expectations appropriately: AI speeds up development significantly, but it’s not a silver bullet that works without guidance. The more you practice vibecoding, the better you understand its boundaries. Sergey’s definition places vibecoding in the evolution of development tools: from scaffolding to co-pilots to agentic coding to vibecoding. Each step increases automation, but the human architect remains essential for providing direction, context, and validation.

Pair Programming with the Machine

“If you treat AI as a junior engineer, it’s very easy to adopt it. Ah, okay, maybe we just use the old traditions, how we onboard juniors to the team, and let AI follow this step.”

One of Sergey’s most practical insights is treating AI like a junior engineer joining your team. This mental model immediately clarifies roles and expectations. You wouldn’t let a junior architect your system or write all your tests—so why let AI? Instead, apply existing onboarding practices: pair programming, code reviews, test-driven development, architectural guidance. This approach leverages Extreme Programming practices that have worked for decades. The junior engineer analogy helps teams understand that AI needs mentorship, clear requirements, and frequent validation. Just as you’d provide a junior with frameworks and conventions to follow, you constrain AI with established architectural patterns and framework conventions like Ruby on Rails.

The Transactional Model: Atomic Commits and Rollback

“When you’re working with AI, the more atomic commits it delivers, more easy for you to kind of guide and navigate it through the process of development.” Continue reading AI Assisted Coding: Treating AI Like a Junior Engineer – Onboarding Practices for AI Collaboration

AI Assisted Coding: From Deterministic to AI-Driven—The New Paradigm of Software Development, With Markus Hjort

In this BONUS episode, we dive deep into the emerging world of AI-assisted coding with Markus Hjort, CTO of Bitmagic. Markus shares his hands-on experience with what’s being called “vibe coding” – a paradigm shift where developers work more like technical product owners, guiding AI agents to produce code while focusing on architecture, design patterns, and overall system quality. This conversation explores not just the tools, but the fundamental changes in how we approach software engineering as a team sport.

Defining Vibecoding: More Than Just Autocomplete

“I’m specifying the features by prompting, using different kinds of agentic tools. And the agent is producing the code. I will check how it works and glance at the code, but I’m a really technical product owner.”

Vibecoding represents a spectrum of AI-assisted development approaches. Markus positions himself between pure “vibecoding” (where developers don’t look at code at all) and traditional coding. He produces about 90% of his code using AI tools, but maintains technical oversight by reviewing architectural patterns and design decisions. The key difference from traditional autocomplete tools is the shift from deterministic programming languages to non-deterministic natural language prompting, which requires an entirely different way of thinking about software development.

The Paradigm Shift: When AI Changed Everything

“It’s a different paradigm! Looking back, it started with autocomplete where Copilot could implement simple functions. But the real change came with agentic coding tools like Cursor and Claude Code.”

Markus traces his journey through three distinct phases. First came GitHub Copilot‘s autocomplete features for simple functions – helpful but limited. Next, ChatGPT enabled discussing architectural problems and getting code suggestions for unfamiliar technologies. The breakthrough arrived with agentic tools like Cursor and Claude Code that can autonomously implement entire features. This progression mirrors the historical shift from assembly to high-level languages, but with a crucial difference: the move from deterministic to non-deterministic communication with machines.

Where Vibecoding Works Best: Knowing Your Risks

“I move between different levels as I go through different tasks. In areas like CSS styling where I’m not very professional, I trust the AI more. But in core architecture where quality matters most, I look more thoroughly.” Continue reading AI Assisted Coding: From Deterministic to AI-Driven—The New Paradigm of Software Development, With Markus Hjort

AI Assisted Coding: Agile Meets AI—How to Code Fast Without Breaking Things, With Llewellyn Falco

In this BONUS episode we explore the practice of coding with AI—not just the buzzwords, but the real-world experience. Our guest, Llewellyn Falco, has been learning by doing, exploring the space of AI-assisted coding from the experimental and intuitive—what some call vibecoding—to the more structured world of professional, world-class software engineering. This is a conversation for practitioners who want to understand what’s actually happening on the ground when we code with AI.

Understanding Vibecoding

“You can now program without looking at code. When you’re in that space, vibecoding is the word we’re using to say, we are programming in a way that does not relate to programming last year.”

The software development landscape shifted dramatically in early 2025. Vibecoding represents a fundamental change in how we create software—programming without constantly looking at the code itself. This approach removes many traditional limitations around technology, language, and device constraints, allowing developers to move seamlessly between different contexts. However, this power comes with responsibility, as developers can now move so fast that traditional safety practices become even more critical.

From Concept to Working App in 15 Minutes

“We wrote just a markdown page of ‘here’s what we want this to look like’. And then we fed that to Claude Code. And 15 minutes later we had a working app on the phone.”

At the Agile 2025 conference in Denver, Llewellyn participated in a hackathon focused on helping psychologists prevent child abuse. Working with customer Amanda, a psychologist, and data scientist Rachel, the team identified a critical problem: clinicians weren’t using the most effective parenting intervention technique because recording 60 micro-interactions in 5 minutes was too difficult and time-consuming.

The team’s approach embodied lean startup principles turned up to eleven. After understanding the customer’s needs through exposition and conversation, they created a simple markdown specification and used Claude Code to generate a working mobile app in just 15 minutes. When Amanda tested it, she was moved to tears—after 20 years of trying to make progress on this problem, she finally had hope. Over three days, the team released 61 iterations, constantly getting feedback and refining the solution.

Iterative Development Still Matters When Coding With AI

“We need to see things working to know what to deliver next. That’s never going to change. Unless you’re building something that’s already there.” Continue reading AI Assisted Coding: Agile Meets AI—How to Code Fast Without Breaking Things, With Llewellyn Falco

BONUS: Mastering Remote Work in Agile Teams With Antony Marcano

NOTE: We want to thank the folks at Tuple.app for being so generous with their stories, and supporting the podcast. Visit tuple.app/scrum and share them if you find the app useful! Remember, sharing is caring!

In this BONUS episode, Antony, co-founder of RiverGlide and Head of Engineering at Ford Digital, joins us to share his experiences and insights from 30 years in software development, including 25 years in Agile practices. As a technical practitioner, leader, and consultant, Antony reflects on navigating remote work, overcoming challenges, and setting up successful remote software teams, while exploring future trends in the industry.

The Shift to Fully Remote Work

Antony reflects on his first fully remote software project, which took place during the pandemic when everyone was forced to work from home. While his team had been working together for 12 months, they struggled with traditional video conferencing tools that lacked the ability to support pair programming or mob programming effectively. This is when Antony and his team discovered Tuple, a tool that allows for seamless control sharing and a co-located pairing experience.

“Switching to Tuple was a game-changer for us in making remote pairing feel as interactive as in-person collaboration.”

Overcoming Challenges in Remote Collaboration

Continue reading BONUS: Mastering Remote Work in Agile Teams With Antony Marcano

BONUS: Mastering Product Management in a Remote World, Insights from Tuple’s Head of Product, Eli Goodman

In this episode, Eli Goodman, Head of Product at Tuple, shares insights from his extensive experience in software development and product management. Having transitioned from engineering management to product leadership, Eli reveals the key strategies Tuple uses to develop its remote pair programming service, which is trusted by companies like Figma and Shopify. Tune in to discover how Tuple handles remote team dynamics, customer-driven development, and balances tech debt with client needs, all while maintaining a customer-centric focus.

Introduction to Tuple and Why It’s Unique

Tuple, a remote pair programming service designed by engineers, solves a pain point that its founders, all pairing enthusiasts, experienced firsthand. They were unsatisfied with generic screen-sharing tools that disrupted the flow of coding collaboration. Tuple’s product philosophy is about staying “one inch wide, one mile deep” to ensure the tool stays focused on enhancing the pairing experience without getting in the way.

“The details matter. Generic screen-sharing tools just don’t cut it for productive pairing.”

Managing a Remote Team at Tuple

Managing a distributed team across the U.S. and Europe comes with its challenges. Eli highlights the importance of alignment and ensuring everyone is on the same page, despite working remotely. He emphasizes the role of Product Owners as “connective tissue” and the power of connecting team members with key initiatives. Through personal conversations, Eli uncovers what motivates his team, allowing him to support them without micromanaging.

“What makes you proud? What brings you shame? Understanding these emotions helps uncover what drives our team.”

Ensuring Effective Communication in a Remote Environment

Effective communication is the backbone of remote work, and Eli shares some of the practices that have helped Tuple’s team stay aligned and collaborative. From using spontaneous pairing sessions to fostering a culture of checking in, Tuple has created a remote work environment where conversations are naturally sparked, and collaboration is effortless.

“We have more space in our schedules for spontaneous pairing, which keeps collaboration flowing.”

Lessons Learned from Pairing Remotely

One of the key insights Eli shares is how Tuple has evolved its remote pairing process. In the past, pairing might have felt like a formal meeting, but now it happens more spontaneously. Tuple’s app facilitates this by offering the metaphor of a phone call—engineers can call each other at any time, making collaboration easy, especially when someone is deep into a task and needs quick support.

“At Tuple, engineers only have three meetings a week, leaving the rest of the time open for pairing and creative work.”

Pairing Beyond Programming Tasks

While pairing is typically associated with programming, Eli explains how Tuple uses pairing for other activities, like design or planning sessions. This practice has extended beyond coding, fostering a culture where team members collaborate on various tasks that benefit from shared perspectives and live problem-solving.

“We’ve expanded pairing beyond coding, using it for activities like design reviews and project planning.”

Balancing Customer Feedback with Product Vision

Responding to customer feedback is vital, but it can also lead to losing focus. Eli explains how Tuple balances this by capturing as much feedback as possible, using tools like Product Board to keep track of customer requests. However, instead of building every requested feature, Eli focuses on synthesizing broader patterns and emotional triggers that align with Tuple’s long-term vision.

“Focus on discovery as a product person. Understand the emotional context behind customer feedback—that’s what drives great products.”

Tuple’s Ideal Customer and Core Value

Tuple’s ideal customers are teams that value deep collaboration through pair programming. The platform’s most important offering is the ability to make remote pairing seamless and intuitive, something traditional tools fail to deliver.

“Tuple is built for teams that believe in the power of collaboration and want a tool that enhances their pairing experience, not disrupts it.”

Roadmapping: How to Prioritize the Right Work in Product Development

Looking ahead, Eli shares Tuple’s plans to continue investing in quality and lowering the barriers to remote pairing. One exciting potential direction includes creating a “social layer” within the app to help users feel more connected with their teammates. Another idea is incorporating non-human pairing agents that could assist with specific tasks.

“We want to see if we can make it feel like you’re right there with your teammates, lowering the barriers to start pairing.”

Recommended Resources

Eli recommends The Mom Test by Rob Fitzpatrick, a must-read for anyone working in product management. The book teaches how to talk to customers in a way that gets honest, useful feedback rather than polite responses that don’t help improve the product.

“I thought caring about people was enough to talk to customers, but The Mom Test taught me what not to do during customer interviews.”

About Eli Goodman

Eli Goodman has been working on software teams for 17 years. He’s been a full-stack developer and engineering manager at both large and small companies, including Etsy and Headspace. A few years ago, Eli transitioned to product management and is now the Head of Product at Tuple, a remote pair programming service used by companies such as Figma, Shopify, and many others in the software industry.

You can link with Eli Goodman on LinkedIn, or email Eli at Eli@Tuple.app.