Coding Chats

Coding Chats episode 60 - John Crickett and Paul discuss the transformative impact of AI on software engineering, exploring topics such as spec-driven development, the importance of small batches, and the challenges of requirements gathering. They delve into the evolving role of AI tools, the need for effective communication, and the balance between productivity and code quality. The discussion also touches on the future of AI in development, the significance of ownership in coding, and the potential for specialized AI agents to enhance workflows. Paul shares valuable tips for leveraging AI in software engineering, emphasizing the importance of joy, working in small units, and maintaining humility in the face of rapid technological change.Chapters00:00 AI in Software Engineering: A New Era03:36 The Revelation of Prompt-Driven Development06:08 Spec-Driven Development vs. Waterfall09:16 The Importance of Small Batches in AI Development12:05 Ownership and Responsibility in AI-Generated Code14:57 The Challenges of Outsourcing and Communication in Software Development20:15 The Future of Programming and Communication23:38 AI Tools and Upstream Bottlenecks27:18 Understanding JetBrains' AI Integration31:40 User Experience and AI Interaction35:42 Opinionated Workflows in Software Development37:24 Finding Joy in AI-Assisted EngineeringPaul's Links:https://buildermethods.com/agent-osJohn's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/John’s YouTube: https://www.youtube.com/@johncrickettJohn's Twitter: https://x.com/johncrickettJohn's Bluesky: https://bsky.app/profile/johncrickett.bsky.socialCheck out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.TakeawaysAI is revolutionizing software engineering practices.Spec-driven development formalizes the way we instruct AI agents.Small batches improve productivity and maintain context.Ownership of code is crucial for long-term success.Quality of code generated by AI is more important than quantity.Effective communication is key in AI-assisted development.Specialized AI agents will enhance the development process.JetBrains is evolving its tools to integrate AI effectively.Developers should find joy in their work, even with AI assistance.Humility is essential as we navigate the future of AI in programming.

Coding Chats episode 59 - Josh discusses the AI agent framework Rig, its functionalities, and the benefits of using Rust for its implementation. He explains the concept of agents and embeddings, their applications, and the importance of managing context windows in AI models. Josh shares his journey of learning Rust, transitioning from a technical content writer to a co-maintainer of Rig, and the challenges faced while building a coding agent. He emphasizes effective prompting strategies and the importance of concise communication with AI models. The conversation concludes with insights on contributing to Rig and the future of AI frameworks.Chapters00:00 Introduction to Rig and AI Frameworks02:56 Understanding Agents and Embeddings05:24 Use Cases for Embeddings and Context Management07:53 Benefits of Using Rig in Rust10:10 Learning Rust and Overcoming Challenges12:56 Transitioning to Rig and AI Focus15:21 Building a Coding Agent: Challenges and Insights17:45 Prompting Techniques and Best Practices20:06 Contributing to Rig and Community Engagement22:49 Final Thoughts and Future DirectionsJosh's Links:https://github.com/0xPlaygrounds/righttps://www.rustnationuk.com/speaker/joshua-mohttps://www.linkedin.com/in/joshua-mo-4146aa220/John's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/John’s YouTube: https://www.youtube.com/@johncrickettJohn's Twitter: https://x.com/johncrickettJohn's Bluesky: https://bsky.app/profile/johncrickett.bsky.socialCheck out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.TakeawaysRig is an AI agent framework that simplifies AI integration.Agents in AI are often misunderstood due to marketing hype.Embeddings serve as data representations for various applications.Retrieval augmented generation is a common use case for embeddings.Managing the context window is crucial for effective AI performance.Using Rust for Rig provides type safety and performance benefits.Learning Rust can be challenging but rewarding with the right approach.Josh transitioned from content writing to engineering at Rig.Building a coding agent revealed the complexities of AI.Concise prompts are essential to avoid overwhelming AI models.

In this special holiday episode of Coding Chats, John Crickett answers audience questions about software engineering careers, the impact of AI, programming languages, and the importance of leadership. He discusses how to rebuild an engineering career, the significance of meaningful projects, and the readiness of self-taught developers. The conversation also touches on insights gained from hosting the podcast and the evolving landscape of software development.Chapters00:00 Introduction to the Coding Chats Holiday Special00:22 Rebuilding an Engineering Career in 202501:01 The Future of Software Engineering with AI01:27 Learning Programming: Starting Points and Languages02:27 Breaking the No Experience Loop for Developers04:17 Meaningful Experience: Projects and Contributions05:02 Self-Taught Developers: Readiness and Opportunities06:07 Qualities of a Good Software Engineering Leader06:52 Insights from 18 Months of Coding Chats07:43 Architecture as a Strategic Concern in EngineeringJohn's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/John’s YouTube: https://www.youtube.com/@johncrickettJohn's Twitter: https://x.com/johncrickettJohn's Bluesky: https://bsky.app/profile/johncrickett.bsky.socialCheck out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.TakeawaysLeverage AI to find answers quicker than before.Reading and curiosity are key habits for growth.All parts of software engineering will survive AI advancements.Focus on learning computer science fundamentals first.Choose programming languages based on your interests.Building personal projects can help you get noticed.Self-taught developers can be just as capable as those with degrees.Good leadership adapts to the situation and team needs.The software development field is diverse and evolving.Architecture should be treated as a strategic concern.

Coding Chats episode 58 - John Crickett and Melinda Fekete delve into the concept of feature ops, emphasizing the importance of managing code in production effectively. They discuss feature flags as a mechanism for safe testing and releasing of code, the challenges of managing feature flags, and the significance of user feedback in software development. The conversation also touches on deployment strategies like canary releases, learning from recent outages, and the benefits of testing in production. Additionally, they explore the role of feature flag providers and the trade-offs associated with adopting feature flags in software projects.Chapters00:00 Introduction to Feature Ops02:46 Managing Feature Flags Effectively07:41 Deployment Strategies: Canary Releases and Gradual Rollouts12:23 The Importance of Dogfooding and User Feedback15:05 Learning from Recent Outages19:13 Testing in Production and Its Benefits21:51 Managing Feature Flags at Scale27:01 Feature Flag Providers and Their Benefits30:50 Involving Product Teams in Feature Flag Management31:45 Trade-offs and Downsides of Feature Flags39:35 Exploring Related ContentMelinda's Links:A guide on working with feature flags in code: https://docs.getunleash.io/guides/manage-feature-flags-in-codeOpen-source repo: https://github.com/Unleash/unleashJohn's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/John’s YouTube: https://www.youtube.com/@johncrickettJohn's Twitter: https://x.com/johncrickettJohn's Bluesky: https://bsky.app/profile/johncrickett.bsky.socialCheck out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.TakeawaysFeature ops focuses on managing code in production effectively.Feature flags allow for safe testing and releasing of code without redeployment.Managing the lifecycle of feature flags is crucial for maintenance.Canary releases and gradual rollouts help mitigate risks during deployment.User feedback is essential for improving software products.Recent outages highlight the need for better feature management practices.Testing in production can catch issues that staging environments may miss.Feature flag providers offer tools for managing flags at scale.Trade-offs exist when adopting feature flags, especially for smaller projects.Effective management of feature flags can empower teams and improve deployment speed.

Coding Chats episode 57 - Owain Lewis and John Crickett explore the role of AI in software engineering, discussing the integration of AI into production systems and the challenges faced by AI engineers. They delve into the nuances of AI application, from building scalable systems to the importance of human oversight in AI-driven workflows.Chapters00:00 Defining the Role of AI Engineer03:13 Exploring Large Language Models (LLMs)06:15 Use Cases for LLMs in Business09:22 The Non-Deterministic Nature of AI12:12 AI in Software Engineering: The Future15:11 The Role of AI in Code Review17:53 The Bottleneck of Requirements Gathering20:38 Leveraging AI Throughout the Software Lifecycle29:53 Leveraging AI for Efficient Documentation30:47 AI in API Design and Review32:22 Spectrum Driven Development with AI34:06 The Role of Requirements in Software Engineering40:05 The Future of Programming Languages and AI49:54 Understanding Context and Prompt Engineering56:38 Exploring Related ContentOwain's Links:Substack: https://newsletter.owainlewis.com/subscribe AI Engineer: https://skool.com/aiengineerJohn's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/John’s YouTube: https://www.youtube.com/@johncrickettJohn's Twitter: https://x.com/johncrickettJohn's Bluesky: https://bsky.app/profile/johncrickett.bsky.socialCheck out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.TakeawaysAI engineering involves building software with AI, focusing on production systems.AI engineers bridge the gap between AI model builders and software developers.Understanding AI's unique paradigm is crucial for effective system architecture.AI should be used minimally and where it makes sense, not everywhere.Human oversight is essential in AI-driven workflows to ensure reliability.Large language models (LLMs) are a significant focus in current AI trends.AI can enhance business processes through automation and natural language interfaces.AI's role in software engineering includes improving code quality and efficiency.AI tools can amplify both good and bad engineering practices.Experimentation and building real projects are key to learning AI engineering.