Brandon Mathis sits down with Rafael Mendiola, co-founder of OK Think, to explore how AI agents are changing the way software gets built. They discuss loop engineering, agent control planes, managing multiple coding agents, and why the development environment is moving from the laptop to the cloud.

From AI-assisted migrations to mobile-first agent management, this conversation looks at what it means for engineers to shift from writing every line of code to designing the systems where agents can work effectively.

Keypoints:

Brandon Mathis sits down with Emerson Huitt to unpack when and why teams should run AI inference locally. They explore the business case for more control over sensitive data, privacy, compliance, and costs; compare on-premises hardware, developer machines, and rented GPU capacity; and share practical advice for testing workloads before investing in expensive infrastructure. The conversation also covers model selection, quantization, VRAM and cache planning, and evaluating local coding models for real-world development workflows.5 Key Points from this Episode:

• Local AI gives organizations more control over sensitive data, especially in regulated industries such as healthcare, defense, and businesses handling proprietary IP.

• The key value of local inference is not always lower cost, but more predictable cost, stronger privacy controls, and the ability to limit data leaving an approved environment.

• Start small before investing in hardware: rent GPU capacity, test real workloads, and determine whether on-premises, cloud-hosted, or developer-device inference fits the team’s needs.

• Model choice and quantization involve tradeoffs. Teams need to account for VRAM, context windows, performance, and quality, then test models against evaluations that reflect their actual workflows.

• Running local LLMs at team scale is an operations challenge. Reproducible environments, pinned versions, model checksums, secure sandboxes, and credential-injecting proxies are essential for reliability and security.

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Emerson Huitt on Linkedin: https://www.linkedin.com/in/emersonhuitt/

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot: https://ai.thisdot.co/

Dev Agrawal joins Brandon Mathis to unpack why framework choices still matter in the age of AI coding. They explore what Solid 2.0 changes for asynchronous data handling, how idiomatic patterns can keep code fast and readable, and why developers should guide AI with strong architectural decisions. Dev also shares how Solid’s migration codemod is designed to combine deterministic analysis with AI-assisted judgment, and why a CLI is the right interface for a local developer tool.

5 Key Takeaways:

• Framework choices still affect outcomes: even when agents write more code, the framework shapes how reliably they can turn intent into a good user experience.

• Solid 2.0 makes async work native to the reactive model, replacing the special createResource primitive with async derivations through familiar primitives such as createMemo.

• Solid aims to make idiomatic code performant by default, favoring clear patterns and fast failure over silent reactivity and performance problems.

• The Solid 1.0-to-2.0 migration codemod analyzes a codebase’s AST, reports the areas that need attention, and gives targeted guidance an AI agent or human can act on.

• AI is excellent at generating plausible code, but humans still need to provide architectural direction, codebase conventions, and judgment when debugging reveals deeper problems.

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Dev Agrawal on Linkedin: https://www.linkedin.com/in/dev-agr/

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot Labs: https://www.thisdot.co/

Brandon Mathis talks with Jeff Escalante of Clerk about what it actually takes to go all in on AI-assisted software development. They compare Codex and other coding tools, examine why subscription pricing changes the economics of agentic work, and make the case for keeping humans firmly in the loop—especially for security-critical products. The conversation also explores AI code review, productivity signals, and why today’s project-management habits are struggling to keep up with a multi-agent workflow.Explore Clerk at clerk.dev and join the conversation on how AI is reshaping practical engineering work.5 Key Takeaways- Codex is a practical daily driver for AI-assisted development, but the real value comes from active human direction—not simply handing work to an agent.- Subscription plans can make intensive AI coding far more economical than API-priced cloud agents; high token usage can represent thousands of dollars of theoretical monthly spend.- Unmonitored agent swarms are not dependable enough for security- and reliability-sensitive systems. Authentication platforms such as Clerk cannot afford autonomous mistakes.- AI can meaningfully increase engineering output, including drafting and reviewing code, yet its work still requires close reading, frequent course correction, and human accountability.- Traditional productivity metrics and project-management systems are increasingly mismatched with a workflow where engineers supervise multiple concurrent AI-driven projects.Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/Jeff Escalante on Linkedin: https://www.linkedin.com/in/tracyslee/This Dot Labs Twitter: https://x.com/ThisDotLabsThis Dot Media Twitter: https://x.com/ThisDotMediaThis Dot Labs Instagram: https://www.instagram.com/thisdotlabs/This Dot Labs Facebook: https://www.facebook.com/thisdot/Sponsored by This Dot Labs: https://www.thisdot.co/

OpenAI's new GPT Sites feature makes it possible to go from an idea in ChatGPT to a live, shareable web application in just a few prompts. In this episode of The Context Window, Brandon Mathis sits down with Jon Abrams, Technical Lead for GPT Sites at OpenAI, to explore how the platform works, why it was built, and what it means for developers and non-developers alike.

They discuss deploying full-stack applications directly from ChatGPT, built-in authentication, SQLite databases, Cloudflare Workers, custom domains, internal business tools, rapid prototyping, and why GPT Sites could fundamentally change how software gets built and shared.

5 Key Things You'll Learn in This Episode

- How GPT Sites lets you deploy AI-generated web apps directly from ChatGPT without managing hosting infrastructure or traditional deployment workflows.

- How built-in features like authentication, SQLite databases, and Cloudflare Workers make it possible to build full-stack applications with just a few prompts.

- Why GPT Sites is ideal for rapid prototyping, internal tools, and side projects, allowing developers to move from idea to a shareable application in minutes.

- How developers can extend GPT Sites with custom domains, external services, and existing infrastructure while avoiding vendor lock-in.

- Why AI is changing the economics of software development, reducing the need to manage infrastructure so builders can focus on solving real problems instead of repetitive engineering tasks.

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Jon Abrams on Linkedin: https://www.linkedin.com/in/thejonabrams/

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot: https://ai.thisdot.co/

Claude Code Workflows introduce a new way to orchestrate AI coding agents, but what do they actually change for engineering teams?In this episode of The Context Window, Brandon Mathis, Jonathan Fontanez, and Coston Perkins break down how they're using workflows to automate repetitive development tasks, coordinate multiple AI agents, and build more reliable AI-assisted engineering systems. They discuss practical use cases, workflow patterns, evaluation loops, codebase maturity, and why deterministic orchestration is becoming just as important as the models themselves.Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/Coston Perkins on Linkedin: https://www.linkedin.com/in/costonperkins/Jonathan Fontanez on Linkedin: https://www.linkedin.com/in/jonathan-fontanez-27715428/ This Dot Labs Twitter: https://x.com/ThisDotLabsThis Dot Media Twitter: https://x.com/ThisDotMediaThis Dot Labs Instagram: https://www.instagram.com/thisdotlabs/This Dot Labs Facebook: https://www.facebook.com/thisdot/Sponsored by This Dot: https://ai.thisdot.co/AI Workshop Series from This Dot Labs: ⁠https://ai.thisdot.co/workshops⁠Use Code THISDOTX at Checkout for $50 tickets!Chapters00:00 Introduction to Claude Code Workflows01:25 What Workflows Are and Why They Matter06:34 Real-World Workflow Use Cases10:13 Workflow Patterns and Engineering Loops15:13 Building Self-Driving Development Workflows20:03 Codebase Readiness and AI Workflow Success25:32 Custom Workflow Demos and Practical Examples32:15 Workflow Ideas for Every Engineering Team38:05 The Future of AI Workflow Engineering42:04 Final Thoughts and Getting Started

AI is making it easier than ever for individuals to build software, but speed alone doesn't create sustainable products. In this episode of The Context Window, Brandon Mathis sits down with Gant Laborde to discuss how engineering teams may need to evolve as AI becomes a core part of the software development lifecycle.

The conversation explores the concept of the "AI Triforce," a framework centered on three emerging roles: the Product Experience Architect, Integrity Engineer, and Systems Engineer. They examine why giving every developer an AI coding assistant is not enough, the risks of unchecked AI generated code, and how organizations can balance rapid feature development with quality, reliability, and long term maintainability.

Along the way, they discuss vibe coding, guardrails, technical debt, team structure, and the new skills that may define the next generation of software engineering. If you're thinking about how AI changes not just how code gets written but how teams work together, this episode offers a practical look at what comes next.

What You’ll Learn:

- AI is forcing teams to rethink software development workflows, not just developer productivity.

- Giving every engineer an AI coding assistant without guardrails creates new risks around quality, security, and maintainability.

- The AI Triforce framework separates feature creation, quality assurance, and system architecture into distinct responsibilities.

- Faster development cycles require stronger validation, testing, and oversight processes.

- The most successful engineering organizations will be the ones that combine human expertise and AI through intentional team structures.

Chapters

00:00 Why AI Needs New Engineering Philosophies

04:39 The AI Triforce: A New Team Model

08:06 The Risks of Vibe Coding and AI-Generated Software

13:48 From Individual Contributors to AI-Assisted Teams

16:13 The Builder: Product Experience Architect (PXA)

19:23 The Integrity Engineer: Guardrails, Testing, and Quality

25:26 The Systems Engineer: Architecture and Long-Term Maintainability

29:24 Why "Everyone's a Builder" Doesn't Scale

34:15 AI Team Structures, New Roles, and the Future of Engineering

43:05 Chain React and Closing Thoughts

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Gant Laborde on Linkedin: https://x.com/GantLaborde

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot: https://ai.thisdot.co/

Claude Code's recent quality issues sparked a broader conversation about transparency, reliability, and vendor lock-in across AI-powered developer tools. Brandon Mathis, Coston Perkins, and Jonathan Fontanez discuss Anthropic's explanation for the degradation, the challenges of relying on closed agent systems, and the risks organizations face when critical development workflows depend on tools they cannot fully inspect or control.

The conversation also explores the rapidly evolving coding harness landscape, including Codex, OpenCode, Pi, Goose, Gemini CLI, and Quinn Code. Topics include benchmark performance, open source versus closed source approaches, customization, context engineering, long-running agents, and why many developers are beginning to view harnesses, not models, as the next major battleground in AI-assisted software development. The discussion examines what engineering teams should consider when evaluating AI tooling and why flexibility may become increasingly important as the ecosystem continues to evolve.

What You'll Learn:

- Why recent Claude Code quality issues pushed many developers to reevaluate their AI tooling choices.

- How coding harnesses influence agent behavior, performance, and developer workflows beyond the underlying model.

- The tradeoffs between open source and closed source AI coding tools, including transparency, customization, and vendor lock-in.

- How tools like Codex, OpenCode, Pi, Goose, and Gemini CLI compare as the coding harness ecosystem rapidly evolves.

- Why many developers believe the next major wave of AI innovation will come from harness design rather than model improvements alone.

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Coston Perkins on Linkedin: https://www.linkedin.com/in/costonperkins/

Jonathan Fontanez on Linkedin: https://www.linkedin.com/in/jonathan-fontanez-27715428/

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot: https://ai.thisdot.co/

AI Workshop Series from This Dot Labs: ⁠https://ai.thisdot.co/workshops⁠

Use Code THISDOTX at Checkout for $50 tickets!

In this episode of The Context Window, Brandon Mathis and Jonathan Fontanez explore a provocative question emerging in AI-assisted development: could Markdown become the next programming language? Using examples from agentic workflows, Claude Code skills, MCP integrations, and evolving AI harnesses, they unpack how structured Markdown files are increasingly being used to orchestrate repeatable workflows, prototype systems, and guide AI agents with surprisingly programmatic behavior.

The conversation digs into the tradeoffs of treating Markdown like executable infrastructure, including maintainability, entropy, security risks, token costs, hallucinations, and the challenges of testing non-deterministic workflows. Brandon and Jonathan debate where Markdown-based “programming” fits compared to traditional software engineering, especially for short-lived automations, prototyping, internal tooling, and rapidly evolving startup environments. Along the way, they discuss concepts like skill.md files, harness maturity, vibe coding, structured prompting, evals, repeatable workflows, and how AI agents are reshaping the boundary between natural language and software development itself.

In This Episode, You’ll Learn:

- How AI agents are turning Markdown into a lightweight way to define repeatable development workflows

- Why short-lived automations and fast-moving projects may benefit from “programming” with Markdown instead of traditional code

- The risks involved with agentic workflows, including hallucinations, security concerns, token costs, and workflow entropy

- How skills, MCPs, and AI harnesses work together to connect agents to external systems and automate real engineering tasks

- A practical framework for deciding when to use prompts, Markdown workflows, or full software systems in AI-assisted development

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Jonathan Fontanez on Linkedin: https://www.linkedin.com/in/jonathan-fontanez-27715428/

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot: https://ai.thisdot.co/

AI Workshop Series from This Dot Labs: https://ai.thisdot.co/workshopsUse Code THISDOTX at Checkout for $50 tickets!

In this episode of The Context Window, Brandon Mathis and Coston Perkins unpack one of the biggest shifts happening in AI-assisted development: when to let agents explore freely, and when to pull workflows back into deterministic, repeatable systems. Using real engineering examples like database migrations, CI pipelines, financial reporting, and code cleanup, they break down why relying entirely on non-deterministic agents can introduce risk, hallucinations, and hidden failures into critical workflows.

The conversation explores a practical mindset for modern engineering teams: agents should build the tool, not become the tool. Brandon and Coston discuss how developers can use AI to generate scripts, workflows, dashboards, and automations that are inspectable, shareable, and reliable, instead of depending on one-off prompts and unpredictable outputs. Along the way, they dive into token efficiency, deterministic validation tooling, CI/CD automation, skills vs scripts, and the growing importance of accountability in AI-driven systems.

In this episode, you will learn:

- Why deterministic workflows are becoming critical as AI agents take on more engineering tasks

- How to use AI agents to build reliable scripts, automations, and CI pipelines instead of relying on one-off prompts

- The tradeoffs between non-deterministic agent behavior and repeatable engineering systems- How hallucinations, hidden failures, and inconsistent outputs can create risk in production environments

- Practical ways to reduce token usage, improve reliability, and increase accountability in AI-assisted development

Brandon Mathis on Linkedin: https://www.linkedin.com/in/mathisbrandon/

Coston Perkins on Linkedin: https://www.linkedin.com/in/costonperkins/

This Dot Labs Twitter: https://x.com/ThisDotLabs

This Dot Media Twitter: https://x.com/ThisDotMedia

This Dot Labs Instagram: https://www.instagram.com/thisdotlabs/

This Dot Labs Facebook: https://www.facebook.com/thisdot/

Sponsored by This Dot: https://ai.thisdot.co/