00:00 Cold open: “Humans of Earth” intro 00:38 Meet the guest: Colin Masters (Epic Scale AI) 02:40 Colin’s origin story (military → construction → NYSE → dev) 04:00 The EPIC method: Explore–Plan–Implement–Check 05:40 Context isn’t a dump: vector DB + forced session search 06:20 Plans = branches (GitHub issues integration) 07:10 Memory bank: standardize decisions (deposits vs withdrawals) 08:40 Feedback to feature: free tier shipped in 3 hours 10:00 Shared vs project context; 30 MCP tools 11:10 Using AI since 2024; choose simple over complex 12:20 Explore phase prompts → define a shippable MVP 13:10 AI-first ops: branches, artifacts, and shared context 14:20 Context bloat and model limits 15:05 The Claude 4.5 rant (pain points) 16:10 Buy vs build: why consider Epic Scale 17:10 Why “last 20 commits” isn’t enough 18:00 Semantic tasks and progress tracking 19:10 Watching cross-branch changes 20:00 Agent loops—with human review 21:00 Human-in-command: no auto-approve 22:10 Quote: “Developers in control of their tools will succeed.” 23:40 Houses vs software: constraints and collaboration 29:10 Where Epic Scale shines (small teams 10) 32:00 Status without Big‑A Agile: stakeholder visibility 34:10 Failing as a learning loop 38:10 Mindset shift: embrace AI or get left behind 39:20 Where AI beats humans (YAML, cross-file reasoning) 41:10 Juniors are crushing it; Go‑to‑Market Engineer 44:00 Speed breaks sales/support; training new grads 47:00 Where to find Epic Scale + free tier note 47:40 OutroAI dev isn’t “dump more into the context window.” Colin Masters from Epic Scale AI breaks down how the EPIC method (Explore–Plan–Implement–Check), an MCP server, and a shared vector memory turn chaos into shipping velocity—especially for small, AI‑first teams.We get practical about plans-as-branches with GitHub issues, memory banks to stop re‑deciding decisions, why auto‑approve wrecks projects, and how a user comment led to a free tier in three hours. We also debate “houses vs software,” the rise of the Go‑to‑Market Engineer, and what juniors are getting right with AI.Recorded: October 14, 2025What you’ll learn:How to replace “tickets” with plans-as-branches and keep context cleanWhy vector DB + retrieval beats giant context windowsGuardrails for agent loops (human-in-command, no auto‑approve)Where AI truly outperforms humans (cross-file reasoning, YAML, refactors)Team shape for AI‑first orgs (small, sharp, 10)How to create stakeholder visibility without Big‑A Agile ceremonyGuestColin Masters — Epic Scale AI: https://epicscale.ai/Chapters See chapter markers above.Subscribe for more on AI engineering, MCP, and practical agent workflows.Hashtags: #AIEngineering #MCP #DevTools #AIFirst #VectorDB #VSCode #GitHub
Debating AI Models and Efficient Workflow Management with Michael Rollins and ThanosIn this episode, Michael Rollins and his co-host Thanos discuss their experiences and frustrations with various AI models, specifically critiquing Sonnet 4.5 and GPT-5. They delve into the technical details of setting up PR environments using AWS Fargate and Terraform, and how these tools are integrated into their current workflow. The episode also touches on the challenges of maintaining code quality and documentation in a fast-paced development environment. Notably, they reflect on the evolving role of engineers in the context of advancing AI capabilities and consider the implications for future project management and costs.00:00 Introduction and Today's Topics00:11 Debating the Merits of Sonnet 4.501:51 Setting Up PR Environments with Fargate05:12 Challenges with AI Models14:33 Managing Large Codebases and PRs18:42 Empowering Engineers with Broader Scopes22:15 Introduction to Documentation Practices22:41 Artifact Requirements and Agile Integration23:54 Challenges and Future of Documentation24:45 Using Issues and Repositories as Source of Truth25:44 Improving Code Documentation with AI26:30 Exploring Mermaid Diagrams and Figma28:56 Understanding Claude and Its Naming08:08 Discussion on PRDs and Plans32:14 Token Usage and Cost Management34:44 Engineer Independence and Implementation40:52 Concluding Thoughts and Future Plans
In this episode of 'Will AI Snap That,' host Michael Rollins, alongside his therapist Thanos, delves into the complexities of managing AI and engineering projects. Michael discusses the challenges he's facing as the bottleneck in his current project, where the rapid pace of development and code reviews is overwhelming. The conversation covers optimizing PR reviews, managing database migrations, and the integration of automated tools to streamline processes. They also explore the importance of defining clear guidelines and the role of AI in code quality checks. With humorous anecdotes and technical insights, this episode sheds light on maintaining efficiency without compromising quality in fast-moving engineering environments.
The Death of Agile and the Rise of AI in Software DevelopmentIn this episode of 'AI Snap That,' hosts Michael Rollins and Thanos discuss the provocative statement that 'Agile is dead,' particularly critiquing the rigid and ceremonial aspects of Agile with a capital 'A.'
They explore how small 'a' agile principles still hold value. They delve into their personal experiences and methodologies in software development, including leveraging AI tools for coding and project management.
Despite advancements, they stress the importance of traditional software engineering fundamentals. The episode also features discussions about enhancing productivity with a small engineering team, automation in code reviewing, and the balance between human oversight and AI's capabilities in software development.00:00 Introduction and Hosts00:09 Agile is Dead: The Bold Claim00:42 Defining Agile: Big A vs. Small a01:34 The Problems with Big A Agile01:49 Small a Agile: A Reasonable Approach06:12 Agile vs. Waterfall: A Historical Perspective07:14 AI Scrum Master: A Futuristic Idea08:11 The Role of Engineers in Agile14:41 Challenges of Agile Ceremonies17:11 Intern's Journey: From Fear to Freedom23:42 Reflections on Process and Productivity24:17 Challenges of Team and Architecture Changes25:03 Rewriting the Machine Learning Pipeline26:53 Empowering New Engineers27:34 Automating Code Review and Testing34:20 Implementing Standard Artifacts39:45 Ensuring System Reliability46:52 Final Thoughts and Future Plans
Navigating the Future Job Market: Opportunities and Challenges in the Age of AIJoin hosts Michael Rollins and Sean Byrnes as they explore the impact of AI on the job market in this insightful episode of 'AI Snap.' With a focus on new graduates and career paths, the discussion delves into the dislocations caused by technological advancements, overhiring trends, and the pandemic. They provide practical advice for new grads, highlighting the importance of adaptability, creative thinking, and the value of networking. Drawing from personal experiences and industry insights, Rollins and Burns offer a hopeful perspective on how to succeed in an evolving job market shaped by AI.00:00 Introduction and Welcome00:26 Nostalgia: Early Days of Podcasting01:03 The Impact of AI on Jobs02:04 Career Advice for the Next Generation04:50 Challenges in the Job Market06:28 The Role of AI in Job Displacement08:04 Navigating the New Job Landscape12:30 Innovative Solutions for New Grads15:20 Rethinking Career Paths20:20 The Value of Initiative and Adaptability27:08 Applying School Rigor to Career Development27:52 Networking and Making Connections29:35 Changing Career Paths and Market Dynamics31:53 Impact of Technological Shifts on Careers37:21 Outsourcing and Automation in Business41:23 Adapting Skills to New Opportunities50:01 Navigating Career Challenges and Finding Hope
Navigating the Rise of Multi-Agent AI SystemsIn this episode of 'I Snap That,' hosts Michael Rollins and Thanos discuss their experiences and insights into the development and challenges of using multi-agent AI systems versus single-core LLM agents. While Thanos shares his recent travels in Greece and upcoming vacation plans, Michael dives deep into the complexities of AI coordination, the Blackboard model, and the surprising efficiency gains realized through distributing tasks among specialized AI agents. They explore the counterintuitive nature of these improvements, the role of memory and semantic understanding in AI workflows, and touch upon future concerns about QA and ensuring trust in AI outputs. The episode balances technical discussions with light-hearted banter and real-world anecdotes, creating an informative and engaging dialogue about the evolving landscape of AI technology.00:00 Welcome to I Snap That!00:30 Vacation Plans and Travel Stories04:27 Exploring AI Agents06:42 The Blackboard Model Explained11:00 Memory and Data Coordination15:08 Building and Testing Multi-Agent Systems20:02 Performance and Efficiency Insights23:04 Token Usage and Trade-offs in Computer Science24:30 Challenges with Coding Agents and Data Access25:57 Handling Semi-Structured Data and CSV Ambiguities27:20 Improving Coding Agents with MCP Servers32:12 Ensuring Trust and QA in AI Systems39:24 Learning and Implementing Lang Graph42:13 Real-World Coding Agent Experiences46:08 Concluding Thoughts and Future Topics
Surviving the Robotic Apocalypse: Is Anthropic at War?!?!In this episode of 'AI Snap That,' hosts Michael Rollins and Thanos discuss their personal experiences with kitesurfing, wakeboarding, and snowboarding injuries before diving into the intriguing world of AI developments and dramas. They delve into the financial troubles and pricing strategies of AI giants Anthropic and Cursor, exploring how these companies are trying to navigate their cash flow challenges. The conversation touches upon the recruitment dynamics within these companies, egos in Silicon Valley, and the role of anthropic's Claude Code in the evolving landscape of AI tools. Michael and Thanos also ponder the broader implications of AI in coding, best practices for team productivity, and whether standardizing AI tools is beneficial. Tune in for a unique mix of personal anecdotes, industry insights, and thought-provoking discussions on the future of AI and technology.
Will AI Transform General Aviation? Insights with Savvy Aviation's Tech ExpertsIn this episode, Michael Rollins and Thanos are joined by Chris and Adam from Savvy Aviation to explore the intersection of AI and aviation. They discuss how Savvy Aviation helps aircraft owners manage maintenance through machine learning and data analytics. The conversation dives into predictive models for engine health, the future application of large language models (LLMs) for maintenance logs, and the potential for AI-assisted inflight tools. They also touch on the evolution of AI terminology, the challenges of false positives, and possible future developments in the field.00:00 Introduction and Welcome00:14 Meet the Savvy Aviation Team00:38 Chris's Role and Background01:54 Adam's Role and Background03:36 AI in Aviation Maintenance06:08 Machine Learning and Data Analysis07:37 Viva and Predictive Maintenance11:43 Future of AI in Aviation17:08 Combining Machine Learning and LLMs27:19 False Positives in Aviation28:49 Acceptable Levels of Certainty29:40 Pilot's Role and Digital Tools31:49 AI in General Aviation34:21 Personal Flying Experiences38:29 Internet Connectivity in Private Planes46:23 Machine Learning in Aircraft Maintenance
AI Model Reviews and Beach Coding AdventuresIn today's episode, Michael Rollins and his co-host Thanos discuss their recent experiences with various AI models, including Claude, Opus, Sonnet, and Gemini. They delve into the functionalities and differences of each model, focusing on their applications for coding and research. The conversation also touches on recent tech industry news, with a particular interest in the future of SaaS models and the role of frontier AI models. The hosts share personal anecdotes about working remotely from unique locations and discuss the challenges of using tech tools in everyday life.00:00 Introduction and Casual Banter00:24 Kiting Adventures and Sun Protection02:35 Discussing Tech Podcasts and Bias03:48 The Future of SaaS and AI08:10 Opus vs. Sonnet: A Deep Dive16:45 Experiences with Different AI Models22:03 Coding on the Go23:23 Bug Spray Mishap24:12 Wildlife Encounters24:35 Coding and AI Models24:55 Image Generation with AI28:23 Exploring Gemini and Other AI Tools31:20 Challenges with AI and Tech37:17 Meta's AI Struggles41:41 Tech Giants' Hits and Misses42:51 Conclusion and Farewell
Exploring Expert AI Agents: Definitions, Tools, and Real-world ApplicationsIn today's episode of Will AI Snap, Thad, hosts Michael Rollins and Thanos delve into the definition and construction of expert AI agents. They discuss essential components such as LLMs, RAG databases, and working memory. The conversation covers the importance of these agents in various applications, the evolving tech landscape, and the potential of adversarial models to improve AI accuracy. The episode also touches on Claude releasing its prompts and explores a recent, remarkable single-founder startup acquisition. The hosts wrap up by sharing personal anecdotes about their experiences with AI and development tools.00:00 Introduction and Welcome00:29 AI News and Updates01:21 Exploring Claude's Prompts04:58 Political Implications of AI06:34 Base 44 Acquisition by Wix11:26 Defining Expert AI Agents13:12 Components of Expert AI Agents18:55 Memory in AI Systems23:44 Challenges and Future of AI Agents27:50 Understanding User Interaction Loops29:02 Defining Autonomy in Agents32:13 Exploring JUULs: A Practical Example37:28 Challenges in Trusting AI Agents45:29 Future of AI in Software Engineering48:55 Closing Thoughts and Upcoming Plans
Exploring MCP Servers and AI-Assisted CodingIn today's episode, Michael Rollins and Thanos dive deep into the world of MCP servers and discuss how they can significantly enhance productivity and streamline coding workflows. They share personal experiences with various tools, including Claude and Stripe, and the transformative potential of AI in coding and daily productivity. The conversation touches on the challenges and benefits of setting up MCP servers, using memory servers like mem zero, and practical applications such as email and calendar management. Tune in to hear their insights on the evolving landscape of AI tools and their impact on software development.00:00 Introduction and Casual Banter02:46 Discussing MCP Servers04:26 Stripe MCP Server Experience09:22 Challenges with LLMs and Context Management11:53 Exploring Mem Zero and Context Management16:55 SEO and Generative Engine Optimization26:12 Personal MCP Server Setup28:02 Introduction to MCP Plugins28:19 Security Concerns with MCP Servers30:01 Exploring Useful MCP Servers32:55 Challenges with MCP Server Installation35:50 AI Tools for Code Moderation38:54 Using Mermaid for Code Visualization39:57 AI Code Foundry and Prompt Engineering45:38 Fun with AI and Grok49:23 Conclusion and Upcoming Events
Navigating the Future with AI: Balancing Innovation and Job SecurityIn this episode of 'Will AI Snap That?' Michael Rollins and co-host Thanos, along with special guest Jasper Sherman-Presser, dive into the multifaceted impact of AI on our future. They discuss the ethical dilemmas and existential questions surrounding AI's potential to replace human jobs, the importance of product and engineering roles, and whether AI will enhance or diminish the job market. The conversation touches on AI's decision-making capabilities, potential for a single-person billion-dollar company, and the continuing significance of human skills like teamwork and leadership. Join the conversation and explore whether AI leads us to a utopia or a dystopia.00:00 Welcome to 'Will AI Snap That?'00:30 Introducing Jasper Sherman Presser02:27 The Role of Product Managers03:06 Claude's Ethical Dilemma05:42 AI and Sentience Debate15:58 Human Creativity vs. AI21:36 The Future of Work with AI32:55 AI's Impact on Jobs and Resources34:04 Efficiency and Physical Constraints in AI35:37 Automation and Job Enhancement38:28 The Future of Entry-Level Jobs41:28 The Role of AI in Organizational Processes46:19 The One-Person Billion-Dollar Company51:58 The Potential and Challenges of AI01:01:12 Final Thoughts and Personal Reflections
In today's episode, Thanos and Rollins discuss the implications of discontinuing the production of pennies, explore new AI coding models like Claude Opus 4 and Sonnet 4, and delve into how AI can enhance contextual understanding for software engineers. They also examine the potential future of AI-driven productivity tools, including the Open Memory MCP server and the intersection of hardware and AI with initiatives like Meta's smart glasses. The show wraps up with a discussion on how AI could potentially streamline coding practices and impact the role of engineers.0:00 Introduction and Hosts0:24 The Death of the Penny1:49 AI and Paperclip Problem3:00 New AI Models: Claude Opus and Sonnet5:17 AI Persuasion and Security Concerns8:44 AI in Coding and IDE Extensions17:56 Voice Assistants and AI Glasses21:53 Impact of AI on Coding Workflows23:13 Exploring AI's Role in Code Optimization23:55 Challenges in Context Gathering for Engineers26:21 Leveraging AI for Contextual Understanding29:40 Open Memory: A Tool for Context Management35:25 The Future of AI in Software Engineering41:50 Concluding Thoughts and Future Prospects
In this episode, we talk about how AI can figure into engineering processes. Thanos brings the big-brain knowledge because, well, he's really good at this kind of stuff.
Claude FailuresHighlighting the dangers of reliance on AI, Rollins had a critical bug make its way to production. In today's episode, Thanos and Rollins discuss the evolving landscape of AI coding agents and their impact on the software development process. They delve into the challenges of ensuring code quality, including the importance of tests and architectural standards. The hosts share anecdotes about their own experiences with AI tools like Claude and Cursor, highlighting both the successes and humorous failures. They also touch on the broader implications of AI in team dynamics and software project management, setting the stage for future conversations on overcoming organizational hurdles.
In today's episode, Thanos and Rollins are joined by Colin Morris, the CEO of Proofline (proofline.ai), to discuss the future of AI in software engineering. Colin shares insights on the revolutionary impact of generative AI coding, emphasizing the need for guardrails to ensure safety and efficiency. They also delve into the potential of coding agents, the importance of observability, and the evolving role of site reliability engineers. The conversation explores how these advancements are set to transform the industry, providing both unprecedented opportunities and challenges.00:00 Introduction and Welcome00:57 Introducing Colin Morris03:46 Challenges and Risks in AI and Vibe Coding04:18 Experiments and Real-World Applications09:16 Future of Software Engineering and AI21:52 Complexity and Observability in AI Systems24:24 Rethinking Analytics and Observability25:17 Challenges in Debugging and Engineering Training26:38 The Evolution of Testing and Code Management28:35 The Role of Interfaces and Security in Modern Engineering32:49 The Power and Risks of Coding Agents37:41 The Future of Engineering and AI Integration41:11 Concluding Thoughts and Future Prospects
Fact-Checking AI: Jeff's Mission with Fox Checker | Will AI Snap That?Join hosts Michael Rollins and Thanos as they welcome Jeff Mahacek from Fox Checker. In this episode, Jeff dives into the world of AI, discussing the rampant misinformation and disinformation that pervades the digital landscape. He shares his journey of developing Fox Checker, a tool aimed at automated fact-checking and credibility analysis, and highlights the importance of truth in our society. With a mix of humor and insight, they explore how machine learning can verify facts and combat AI-generated falsehoods. Whether you're an AI enthusiast or a concerned individual, this episode sheds light on the pressing need for accuracy in our information-driven world.00:00 Introduction and Guest Introduction03:56 The Origins of Fox Checker05:16 Challenges with AI and Misinformation11:39 Evaluating Credibility and Claims23:06 The Role of Belief and Fact in Society32:18 The Importance of Distinguishing Belief from Fact34:38 The Role of AI in Evaluating Complex Information37:36 Understanding Machine Learning vs. Generative AI43:06 Challenges and Misconceptions of AI Capabilities51:54 Introducing Fox Checker: Ensuring Information Accuracy56:35 The Future of AI and Information Accuracy01:00:02 Concluding Thoughts and Reflections
In today's episode, hosts Michael Rollins and Thanos discuss their experiences and insights with various AI tools such as ChatGPT, Cursor, and Claude Code. They share the strengths and weaknesses of each tool, delve into specific use cases, and reflect on how the evolving role of AI is impacting the future of software engineering. Notable mentions include the advantages of Claude Chat for handling large pastes and images, Aero as an open-source alternative, and the potential applications of Google's Gemini for architectural discussions. They also touch on the emerging responsibilities engineers will face as AI becomes more integrated into software development.00:00 Introduction and Welcome01:56 Debating AI Tools: ChatGPT08:40 Exploring Cursor10:52 Cursor's Integration and Features20:41 Cursor Pricing Discussion22:34 Introduction to Claude Code26:42 Cost and Productivity with Claude Code30:10 Challenges and Limitations of Claude Code32:11 Honorable Mentions and Other Tools37:24 The Future of Engineering Roles43:22 Conclusion and Teaser for Next Episode
Exploring AI Coding Tools: A Deep Dive into Cursor and Coding AgentsIn today's episode, Thanos and Rollins discuss their experiences with AI coding tools, specifically Cursor and various coding agents. They share insights into creating applications, the challenges faced, and the benefits observed. Key topics include the process of leveraging AI for code generation, managing CSV imports, and the nuances of working with different AI models. They also touch on practical tips for effective prompt management, the importance of context windows, and the potential future of integrated AI in software development.00:00 Welcome to Will AI Snap That?00:37 Building an AI-Powered Grocery Chooser01:47 Challenges with Coding Agents06:11 Exploring CSV Import Automation08:25 The Role of Coding Agents in ETL15:13 Cursor's Performance and Limitations16:51 Dealing with Cursor's Quirks20:19 The Frustrations of Debugging with Cursor24:08 From Command Line to Web App24:33 Challenges with React and Next.js24:52 Database Woes and Prisma Migrations25:54 Managing Schemas and Types26:26 Cursor's Struggles and Solutions27:52 Exploring New Tools and Techniques31:58 Voice Commands and Super Whisper35:44 The Future of Coding with AI40:10 Final Thoughts and Reflections47:24 Closing Remarks
Navigating the Future of Software Engineering with AIIn today's episode of 'Will AI Snap That?', hosts Michael Rollins and Thanos dive deep into the implications of AI on the future of software engineering. Joined by guest Sean Byrnes, a veteran in Silicon Valley, they discuss the evolving role of software developers, biases against older founders, and the potential for AI to replace traditional coding. The conversation explores how AI tools like Cursor are reshaping development practices, the abstraction of programming, and the impact of reinforcement learning on code quality. They also touch on societal changes, job displacement, and the transformative power of AI in making software more accessible and customizable.00:00 Welcome to 'Will AI Snap That?'00:44 Introducing Sean Byrnes01:36 Bias Against Older Founders02:10 Sean's Journey in Silicon Valley05:24 The Rise of AI in Software Development05:33 AI's Impact on the Job Market07:14 Experiments with AI Coding Tools09:12 Challenges and Abstractions in AI Coding14:13 The Future of AI in Software Development24:15 Directing AI and Low-Cost Rewrites25:15 Software Maintenance and Disposable Houses27:07 Product Focus and Software Engineering28:53 AI's Role in Code Generation31:30 Reinforcement Learning and AI-Generated Code37:00 The Future of Software Engineering Jobs43:12 Personalized Software and Final Thoughts
