Skip to main content
The Changelog

A new direction for AI developer tooling (Friends)

89 min episode · 2 min read
·

Episode

89 min

Read time

2 min

Topics

Productivity, Leadership, Artificial Intelligence

AI-Generated Summary

Key Takeaways

  • Local-First Architecture: Tidewave runs on localhost rather than remote servers, accessing your actual browser session and development environment. This allows the agent to use existing authentication, database connections, and framework configurations without separate MCP setup or credential management.
  • Browser-Based Verification: The agent executes JavaScript directly on the page to test implementations, automatically scrolling to validate autoplay features and running database queries to confirm data persistence. This creates a verification loop where agents test their own work before declaring completion.
  • Context Pruning Strategy: When context windows fill, Tidewave prunes tool outputs from early conversation stages rather than summarizing everything. This preserves recent context accuracy while extending conversation length, allowing developers to have meta-conversations with the agent about available tools and capabilities.
  • Framework Integration Over MCPs: Instead of installing multiple MCP servers for database access, GitHub integration, or documentation, Tidewave leverages existing framework capabilities. The agent uses code execution within the web application context, accessing documentation bundled with exact dependency versions rather than potentially outdated remote sources.
  • Productivity Through Specialization: Developers gain measurable productivity by identifying specific use cases where agents excel versus fail. Valim avoids using agents for Elixir type system work but successfully uses them to translate features between frameworks, skipping redundant tests and mocks while maintaining quality through proper verification loops.

What It Covers

Jose Valim discusses Tidewave, a local coding agent for full-stack web applications that runs in the browser alongside your development environment, integrating tightly with Phoenix, Rails, and other frameworks for real-time verification and testing.

Key Questions Answered

  • Local-First Architecture: Tidewave runs on localhost rather than remote servers, accessing your actual browser session and development environment. This allows the agent to use existing authentication, database connections, and framework configurations without separate MCP setup or credential management.
  • Browser-Based Verification: The agent executes JavaScript directly on the page to test implementations, automatically scrolling to validate autoplay features and running database queries to confirm data persistence. This creates a verification loop where agents test their own work before declaring completion.
  • Context Pruning Strategy: When context windows fill, Tidewave prunes tool outputs from early conversation stages rather than summarizing everything. This preserves recent context accuracy while extending conversation length, allowing developers to have meta-conversations with the agent about available tools and capabilities.
  • Framework Integration Over MCPs: Instead of installing multiple MCP servers for database access, GitHub integration, or documentation, Tidewave leverages existing framework capabilities. The agent uses code execution within the web application context, accessing documentation bundled with exact dependency versions rather than potentially outdated remote sources.
  • Productivity Through Specialization: Developers gain measurable productivity by identifying specific use cases where agents excel versus fail. Valim avoids using agents for Elixir type system work but successfully uses them to translate features between frameworks, skipping redundant tests and mocks while maintaining quality through proper verification loops.

Notable Moment

Valim demonstrates how developers can trick coding agents by asking hypothetical questions about nonexistent tools. The agent imagines the tool exists, attempts to invoke it, then crashes when discovering the tool is fictional—revealing fundamental limitations in current agent reasoning capabilities.

Know someone who'd find this useful?

Episode Transcript

It's changelog and friends, a weekly talk show about MCP hot takes. Thanks as always to our partners at fly.io, the public cloud built for developers who ship. We love Fly. You might too. Learn more about it at fly.io. Okay. Let's talk. What's up, friends? I'm here with Kyle Galbraith, cofounder and CEO of Deepo. Deepo is the only build platform looking to make your builds as fast as possible. But, Kyle, this is an issue because GitHub Actions is the number one CI provider out there, but not everyone's a fan. Explain that. I think when you're thinking about GitHub Actions, it's really quite jarring how you can have such a wildly popular CI provider, and yet it's lacking some of the basic functionality or tools that you need to actually be able to debug your builds or deployments. And so back in June, we essentially took a stab at that problem in particular with Depo's GitHub Action Runners. What we've observed over time is effectively GitHub Actions, when it comes to, like, actually debugging a build, is pretty much useless. The job logs in GitHub Actions UI is pretty much where your dreams go to die. Like, they're collapsed by default. They have no resource metrics. When jobs fail, you're essentially left playing detective, like, clicking each little drop down on each step in your job to figure out, like, okay, where did this actually go wrong? And so what we set out to do with our own GitHub Actions observability is essentially we built a real observability solution around GitHub Actions. Okay. So how does it work? All of the logs by default for a a job that runs on a depot GitHub Action runner, they're uncollapsed. You can search them. You can detect if there's been out of memory errors. You can see all of the resource contention that was happening on the runner. So you can see your CPU metrics, your memory metrics, not just at the top level runner level, but all the way down to the individual processes running on the machine. And so for us, this is our take on the first step forward of actually building a real observability solution around GitHub actions so that developers have real debugging tools to figure out what's going on in their builds. Okay, Fran. You can learn more at depot.dev. Get a free trial, test it out, instantly make your builds faster. So cool. Again, depot.dev. I got, like, the news. Like, I got the update in the podcast that there was, like, an oxide event, and you were there. Was that was that a thing? Like, how often do you do that where you go, like, to the place? Yeah. This was this was a first for us, I guess. Because that's like an internal conference for their company. And honestly, we are not internal to their company. So that's a first for us. But, you know, we've hit it off with …

Get the full transcript (16,105 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all The Changelog transcripts →

You just read a 3-minute summary of a 86-minute episode.

Get The Changelog summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • SPONSORS: Depot
  • SPONSORS: Fabi
  • Tidewave runs in the browser alongside your development environment, integrating tightly with Phoenix, Rails, and other frameworks for real-time verification and testing.
  • Instead of installing multiple MCP servers for database access, GitHub integration, or documentation, Tidewave leverages existing framework capabilities.
  • Tidewave runs in the browser alongside your development environment, integrating tightly with Phoenix, Rails, and other frameworks for real-time verification and testing.
  • Jose Valim discusses Tidewave, a local coding agent for full-stack web applications that runs in the browser alongside your development environment, integrating tightly with Phoenix, Rails, and other frameworks for real-time verification and testing.
  • SPONSORS: Miro

company

More from The Changelog

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best Cybersecurity Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into The Changelog.

Every Monday, we deliver AI summaries of the latest episodes from The Changelog and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime