Modern Web

Rizel Scarlett, principal developer advocate at Entire and former Goose maintainer, joins Rob Ocel to explore the missing context layer in AI-assisted software development. They unpack why session history, prompts, tool calls, and decision-making need to stay connected to code; how Entire captures that context through Git-based checkpoints; and why AI should be used as a learning partner, not just a code generator. The conversation also covers code-review overload, agent-friendly workflows, and a more sustainable path to adopting AI.

5 Key Takeaways

- AI-generated code makes context and intent more valuable: teams need a clear record of the decisions and experiments that led to a change.

- Entire uses agent hooks and Git-based checkpoints to capture prompts, tool activity, and session context without cluttering the primary codebase.

- AI can be a powerful learning tool: it gives developers a judgment-free way to ask questions, understand unfamiliar code, and build deeper technical intuition.

- Traditional PR descriptions and diff-only reviews struggle with agent-produced changes; reviews need to connect customer pain, intent, design, and implementation.

- Sustainable AI adoption beats chasing every trend: focused, incremental improvements can deliver real value without the cost and stress of full agent autonomy.

Chapters

00:00 — Why AI code needs durable context

04:12 — The documentation and code-review problem

10:11 — AI as a learning tool

13:42 — How Entire captures agent sessions through Git

26:14 — Session handoffs, reusable skills, and better reviews

32:39 — The future of code forges and sustainable AI adoption

41:37 — Where to find Rizel and Entire

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

Rizel Scarlett on Linkedin: https://www.linkedin.com/in/rizel-bobb-semple/

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://www.thisdot.co/

AI models are becoming more capable, but reliability remains one of the biggest challenges. In this episode of the Modern Web Podcast, Rob Ocel and Brandon Mathis are joined by Andrew Baker, Founder & CEO of Balon.ai, and Arif Hosein, COO of Balon.ai, to discuss why AI hallucinations persist and what it will take to reduce them.

The conversation explores Balon.ai's Deep Fusion architecture, which combines multiple AI models through a consensus-driven approach to improve accuracy without sacrificing performance. They also discuss why larger models alone won't solve reliability, the tradeoffs between cost and quality, and what engineering teams should consider as AI moves deeper into production systems.

Chapters

00:00 Introduction & Meet the Guests

01:20 The AI Hallucination Problem

04:32 What Is an AI Hallucination?

08:22 Sponsor Message

08:47 Are Hallucinations Getting Better?

12:53 Balancing Accuracy, Agency & Emergent Behavior

14:07 Deep Fusion: Balin AI's Multi-Model Architecture

17:20 How Consensus Works Across Multiple Models

20:20 Simultaneous Peer Review for AI

22:34 Why Multiple Imperfect Models Can Produce Better Results

27:58 Can Deep Fusion Fix Bad Prompts?

30:41 The Cost of Multi-Model AI

34:21 AI ROI, Vibe Coding & Enterprise Reality

37:56 How to Try Balin AI

39:37 Final Thoughts & Outro

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

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

Andrew Baker on Linkedin: https://www.linkedin.com/in/andrewbakeratl/

Arif Hosein on Linkedin: https://www.linkedin.com/in/arif-hosein/

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/

Rob Ocel sits down with Minko Gechev to unpack one of the fastest-evolving areas in AI-assisted development: skills, agent workflows, and the growing complexity of AI harnesses.Explore AI skills, how they differ from rules and MCPs, and why developers are increasingly treating skills as structured, executable instructions rather than traditional documentation. Minko explains how modern agents operate under the hood, how skills are lazy-loaded into context windows, and why poorly designed skills can create context rot, unnecessary token usage, and degraded performance over time.

Rob and Minko also dig into one of the most important but misunderstood topics in AI engineering today: evals. They break down how teams can evaluate AI workflows, measure pass rates, test deterministic versus non-deterministic outputs, and optimize skills for reliability, token efficiency, and execution quality across evolving models and harnesses. Also learn about prompt structure, workflow orchestration, context compression, state-machine agents, React loops, and why many teams are accumulating rules and skills faster than they are pruning them.

What you will learn:

• Learn how engineering teams are moving AI beyond isolated experiments into repeatable workflows

• Explore strategies for improving reliability, testing, and validation in AI-assisted development

• Hear practical approaches to scaling AI adoption across engineering organizations

• Understand how leaders are thinking about automation, CI/CD, and operational maturity in the age of AI

• Connect with technology leaders discussing the challenges and opportunities shaping modern software delivery

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

Minko Gechev on Linkedin: https://www.linkedin.com/in/mgechev/

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/

In this episode of the Modern Web Podcast, Rob Ocel talks with PlanetScale CEO Sam Lambert about what “database scale” actually looks like in 2026. Sam shares migration stories from companies that moved at the perfect time and others that waited until they were already in trouble, plus why sharding and reliability are never just “magic” if your queries and data model are a mess.

They also cover PlanetScale’s evolution beyond its MySQL and Vitess roots into Postgres, Metal, and what’s coming next for sharding in the Postgres world. Along the way, they connect the dots to AI workloads, which are increasingly write heavy and put new pressure on performance, uptime, and security.

What You'll Learn:

- How to spot the “right time” to migrate databases before you’re on fire (and what happens when you wait too long)

- What PlanetScale actually gives you “for free” at scale, and what it can’t fix (bad schema, missing indexes, terrible SQL)

- Why “auto” database magic is usually a tradeoff, and what to ask for when you want to peek behind the curtain

- What PlanetScale is becoming beyond MySQL/Vitess, including Postgres, Metal, and Nikky (sharding for Postgres)

- How AI workloads are changing database patterns, especially the shift toward write heavy systems and why that pressures reliability and security

Sam Lambert on Linkedin: https://www.linkedin.com/in/isamlambert/

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

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/

Tracy Lee and A.D. Slaton sit down on The Context Window to unpack a wild week in AI, starting with the eye popping 500 billion dollars spent on AI infrastructure in 2025 and why the Cognizant CEO still says enterprise value is missing. They dig into reports of ChatGPT going “code red” in response to Gemini 3, what that means for OpenAI, and what it means for everyday builders trying to ship real products. Along the way they touch on ByteDance, call out LiveKit as a key piece of infrastructure for voice, video, and physical AI agents, and flag IBM’s move to acquire Confluent as another signal of where data and AI are heading.

What you will learn

- Why 500B spent on AI infrastructure has not translated into clear enterprise value yet

- What the Cognizant CEO’s comments really signal for teams building AI products

- How Gemini 3’s launch is shaking up the landscape for ChatGPT and OpenAI

- What a “Code Red” moment actually means for developers and companies relying on these platforms

- How LiveKit powers voice, video, and physical AI agents and where it fits in the stack

- Why IBM acquiring Confluent matters for data, streaming, and real time AI systems

- How to stay grounded and make practical decisions when AI news makes reality feel unstable

0:00 Intro

0:53 Are we overspending on AI infrastructure and where’s the enterprise value

2:54 Adoption gap, enablement work and why 100% AI generated code is still rare

6:11 High touch AI training, workshops and scaling AI practices across teams

8:58 Grok 4.22, AI trading experiments and quant style tools for everyone

13:51 OpenAI “Code Red,” rising competition and what changes for Agile with agents

20:37 ByteDance agentic phone, AR glasses and AI moving into the physical world

23:20 LiveKit, voice cloning, AI podcasts and the problem of AI slop

27:00 Thinking machines, social media’s role in AI and closing reflections

Tracy Lee on Linkedin: https://www.linkedin.com/in/tracyslee/

A.D. Slaton on Linkedin: https://www.linkedin.com/in/adslaton/

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/

This Dot Labs Bluesky: https://bsky.app/profile/thisdotlabs.bsky.social

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

Environment variables and secrets are usually a mess: out of sync .env files, scattered API keys, painful onboarding, and brittle CI configs. In this episode of the Modern Web Podcast, Rob Ocel talks with Varlock co-creators Phil Miller and Theo Ephraim about how Varlock turns .env files into a real schema with types, validation, and documentation, pulls secrets from tools like 1Password and other backends, and centralizes configuration across environments and services. They also dig into protecting secrets in an AI-heavy world by redacting them from logs and responses, preventing accidental leaks from agents, and pushing toward an open env-spec standard so configuration becomes predictable, portable, and actually pleasant to work with.

What you will learn:

- Why traditional .env files and copy paste workflows break down as teams, services, and environments grow.

- How Varlock turns environment variables into a schema with types, validation, documentation, and generated TypeScript.- How to pull secrets from tools like 1Password and other backends without leaving them in plain text or scattering them across dashboards.

- How to manage multiple environments such as development, staging, and production from a single, declarative configuration source.

- How Varlock helps protect secrets in AI and MCP workflows by redacting them from logs and responses and blocking accidental leaks.

- What the env spec standard is and how a common schema format can make configuration more portable across tools, templates, and platforms.

Theo Ephraim on Linkedin: https://www.linkedin.com/in/theo-ephraim/

Phil Miller on Linkedin: https://www.linkedin.com/in/themillman/

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

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/

This Dot Labs Bluesky: https://bsky.app/profile/thisdotlabs.bsky.social

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

Rob Ocel and Danny Thompson go deep on intentionality, the developer “superpower” that can speed up your growth, sharpen your judgment, and keep you from getting automated away in the AI era. Rob unpacks a simple loop (state intent → act → measure → review) with real stories, including the ticket he challenged on day one that saved a team six figures, and the “it seems to work” anti-pattern that shipped a mystery bug. Together they show how being deliberate before you write a line of code changes everything: scoping tickets, estimating work, documenting decisions, reviewing PRs, and speaking up, even as a junior.What you’ll learn: • The intentionality loop: how to set a hypothesis, capture outcomes, and improve fast • The exact moment to ask “Should we even do this ticket?” and how to push back safely • Why code is the last step: design notes, edge cases, and review context first • Estimation that actually works: start naive, compare to actuals, iterate to ±10% • How to avoid DRY misuse, “tragedy of the commons” code reviews, and stealth tech debt • Where to keep your working notes (GitHub, Notion, SharePoint) so reviewers can follow your logic • How juniors can question assumptions without blocking the room or their careerRob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

Danny Thompson on Linkedin: https://www.linkedin.com/in/dthompsondev/

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

This Dot Media Twitter: https://x.com/ThisDotMediaThis Dot Labs

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

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

Bluesky: https://bsky.app/profile/thisdotlabs.bsky.socialSponsored by This Dot Labs: https://ai.thisdot.co/

On this episode of the Modern Web Podcast, hosts Rob Ocel and Danny Thompson welcome Miles Ward, CTO of SADA, for an in-depth conversation about the intersection of cloud computing and AI. Miles shares his career journey from early days at AWS and Google Cloud to leading SADA through its acquisition by Insight, offering a rare perspective on the evolution of solutions architecture and cloud adoption at scale.The discussion covers the realities of cloud “repatriation,” why GPUs have shifted some workloads back on-prem or to niche “neo-cloud” providers, and how cloud infrastructure remains the backbone of most AI initiatives. Miles breaks down practical concerns for organizations, from token pricing and GPU costs to scaling AI features without blowing budgets. He also highlights how AI adoption exposes weak organizational habits, why good data and strong processes matter more than hype, and how developers should view AI as intelligence augmentation rather than replacement.Key Takeaways:- Miles Ward, former early AWS Solutions Architect, founder of the SA practice at Google Cloud, and now CTO at SADA (acquired by Insight), brings a deep history in scaling infrastructure and AI workloads.- Cloud repatriation is rare. The main exception is GPUs, where companies may rent from “neo-clouds” like CoreWeave, Crusoe, or Lambda, or occasionally use on-prem for cost and latency reasons, though data-center power constraints make this difficult.- Cloud remains essential for AI. Successful initiatives depend on cloud primitives like data, orchestration, security, and DevOps. Google’s integrated stack (custom hardware, platforms, and models) streamlines development. The best practice is to build in cloud first, then optimize or shift GPU inference later if needed.- Costs and readiness are critical. Organizations should measure AI by business outcomes rather than lines of code. Token spending needs calculators, guardrails, and model routing strategies. On-prem comes with hidden costs such as power, networking, and staffing. The real bottleneck for most companies is poor data and weak processes, not model quality.Miles Ward on Linkedin: https://www.linkedin.com/in/rishabkumar7/Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/Danny Thompson on Linkedin: https://www.linkedin.com/in/dthompsondev/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/This Dot Labs Bluesky: https://bsky.app/profile/thisdotlabs.bsky.socialSponsored by This Dot Labs: https://ai.thisdot.co/

In this Modern Web Podcast, Rob Ocel and Danny Thompson break down the recent string of NPM supply chain attacks that have shaken the JavaScript ecosystem. They cover the NX compromise, the phishing campaign that hit libraries like Chalk, and the Shy Halood exploit, showing how small changes in dependencies can have massive effects. Along the way, they share practical defenses like using package lock and npm ci, avoiding phishing links, reviewing third party code, applying least privilege, staging deployments, and maintaining incident response plans. They also highlight vendor interventions such as Vercel blocking malicious deployments and stress why companies must support open source maintainers if the ecosystem is to remain secure.

Key Points from this Episode:

- Lock down installs. Pin versions, commit package-lock.json, use npm ci in CI, and disable scripts in CI (npm config set ignore-scripts true) to neutralize post-install attacks.

- Harden people & permissions. Phishing hygiene (never click-through emails), 2FA/hardware keys, least-privilege by default, and separate/purpose-scoped publishing accounts.

- Stage & detect early. Canary/staged deploys, feature flags, and tight observability to catch dependency drift, suspicious network egress, or monkey-patched APIs fast.

- Practice incident response. Two-hour containment target: revoke/rotate tokens, reimage affected machines, roll back artifacts, notify vendors, and run a post-mortem playbook.

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

Danny Thompson on Linkedin: https://www.linkedin.com/in/dthompsondev/

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/

This Dot Labs Bluesky: https://bsky.app/profile/thisdotlabs.bsky.social

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

In this episode of the Modern Web Podcast, Rob Ocel and Danny Thompson talk with Wes Eklund from AWS ProServe about interviews, practical AI, and the future of developer workflows. Wes shares what trips candidates up in coding and behavioral rounds, how to ask better questions, and why prepping multiple honest STAR narratives matters. Danny introduces the Thrive Framework for behavioral interviews and Rob underscores the discipline required to stand out in a crowded market. The trio then digs into 100 Days of Code in the AI era, smart ways juniors can learn with AI, and how Wes’s team uses MCP servers and Amazon Q to speed design, onboarding, and day-to-day delivery. They cover the lull in MCP hype, real security concerns, the “80 percent is a win” mindset when AI accelerates work, and when it actually makes sense to build agents. They close on thin, purpose-built agents, enterprise adoption patterns, and why frameworks like DSPy could reshape moats and costs.

Key Takeaways from this episode:

- Wes explains how candidates often fail because they neglect behavioral prep, and Danny introduces the Thrive Framework as a system to stand out.

- The group debates whether juniors should use AI. Wes frames it as a tool for strategy and reflection, not a shortcut, while Danny emphasizes using it to deepen knowledge and accountability.

- Wes shares how his AWS team leverages MCP servers and Amazon Q to speed design, boost onboarding, and solve problems faster, while Danny highlights enterprise-level use cases like multilingual documentation.

- They discuss whether developers should build agents, the risks of security gaps, and how frameworks like DSPy could make optimized, lightweight agents a new competitive edge.

Chapters

0:00 MCP servers: security reality check

0:33 Modern Web Podcast intro

0:55 Guest: Wes Ecklan (AWS ProServe)

2:02 Job hunt & interview mistakes

5:05 Danny’s THRIVE framework

7:39 Researching values & STAR stories

11:12 Sponsor + quality & discipline in applications

13:04 100 Days of Code in the AI era

18:03 Using AI at work (MCP + Amazon Q)

23:13 Hackathons & making time to innovate

25:06 MCPs in practice: adoption & security

36:00 Agents: when they help vs. hype — close & links

Wes Eklund on Linkedin: https://www.linkedin.com/in/weseklund/

Rob Ocel on Linkedin: https://www.linkedin.com/in/robocel/

Danny Thompson on Linkedin: https://www.linkedin.com/in/dthompsondev/

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/

This Dot Labs Bluesky: https://bsky.app/profile/thisdotlabs.bsky.social

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