Learn Babel and Chai

React is one of the web’s most popular frameworks for building JavaScript applications. 

If you know what you’re doing, React can drastically simplify how you build, use, and maintain code.

Whether you’re a React newbie or you’re ready for advanced techniques, you can level-up with egghead. Explore our in-depth courses, lessons, and community resources to build more powerful applications and crack open your career.

react

We take the opengraph image we wrote in codesandbox and copy it into our serverless function. We use Rollup to compile the component into an IIFE (immediately invoked function expression) that can run in our headless browser environment and cover a wide set of rollup plugins that we need for compatibility. We end the lesson having successfully screenshot our opengraph react component from our Netlify Function

**Note**:  Due to Netlify changing their handling, the path in `fs.readFileSync` is affected. Update to:
```js
const script = fs.readFileSync(path.resolve(__dirname, "image.js"), "utf-8");
```

Compiling a React to an IIFE with Rollup to execute and render in a headless browser

Babel has support for the latest version of JavaScript through syntax transformers. These plugins allow you to use new syntax, right now without waiting for browser support.

babel

In this lesson, we'll configure webpack to use the Babel loader for our JavaScript files, allowing us to transpile our source files and generate a bundle for deploying our application.

Configure webpack to Load JavaScript Files through Babel with babel-loader

Converting all of our modern JavaScript into ES5 compatible syntax is a great way to use modern features while targeting older browsers. What happens when the browsers natively support these language features? Then it no longer makes sense to transform that code or to include polyfills that will go unused. In this lesson, we’ll add the `@babel/polyfill` package and configure `babel-preset-env`

Target specific browsers with babel-preset-env and the babel pollyfill

We transpile our JavaScript code so we can use modern language features, even if browser support isn't quite where we need it to be. This includes proposed features that aren't yet part of the official language specification. In this lesson, we'll see how we can support the proposed class property syntax for JavaScript with a Babel plugin.

Support Proposed JavaScript Features with Babel Plugins

One approach to building high performance applications with `webpack` is to take advantage of code-splitting to only load the needed JavaScript on initial load and asynchronously load additional JavaScript bundles when needed. In this lesson, we'll create add some code-splitting to our placeholder application and configure our project to support the dynamic `import()` syntax.

Asynchronously Load webpack Bundles through Code-splitting and React Suspense

In this lesson, we'll add React and ReactDOM to our project and create an entry point for the React application. We'll also configure Babel with the React preset so Babel can transpile our JSX into JavaScript that will run in a browser.

Configure babel for React with preset-react

In this lesson, we’ll install Babel and use it from the terminal to see how it can take JavaScript that uses modern language features and output JavaScript that will run in down-level browsers.

Transform Modern JavaScript Features with Babel

Chai is a BDD / TDD assertion library for node and the browser that can be delightfully paired with any javascript testing framework.

chai

In this lesson, you will learn how to verify your API server is returning HTTP 400 responses when clients submit incorrect data. Returning HTTP 400 ensures that your clients are notified of the incorrect usage. Testing for them ensures your API returns errors instead of incorrect responses when supplied with incorrect data.

Test for HTTP 400 responses with Mocha and Chai

In this lesson, we will use Chai's request method to test our Node application's API responses.
By the end of this lesson, you will know how to:
- install the prerequisites to use mocha and chai in your application
- test for HTTP status response codes
- test for a string of text on a page
- test for a json response and validate the properties of the object
- write tests that not only verify the response of your application, but the behavior as well


Test Node RESTful API with Mocha and Chai

Mocha is a feature-rich JavaScript test framework running on Node.js and in the browser, making asynchronous testing simple and fun. Mocha tests run serially, allowing for flexible and accurate reporting, while mapping uncaught exceptions to the correct test cases.

mocha

Writing great ES6 style Promises for Node.js is only half the battle. Your great modules must include tests as well to ensure future iterations don't break them. In this lesson, I show you a simple ES6 Promise in Node.js, then walk you through creating tests in Mocha using chai and chai-as-promised to test both resolve and reject methods.

Testing ES6 Promises in Node.js using Mocha and Chai

What is already a nice workflow using Gulp, Browserify, Watchify & Browsersync to enable auto rebuilds & live browser reloading can be further improved by adding Babelify. A simple wrapper around the popular transpiler Babel, Babelify can ‘transform’ source files as they pass through our stream to enable certain Javascript features not yet available in the Browser or Node. We end the lesson by looking at how to generate & extract sourcemaps using `exorcist`.

Gulp and Browserify - Adding Babel & Source Maps

Now that you've got everything set up with mocha and chai, it's time to actually write tests. In this lesson you'll learn how to use `describe` and `it` to outline your tests and make sure you don't break your library in the future.

Unit Testing with Mocha and Chai

Every dependable library needs to have tests to ensure that you don't push accidental bugs. In this lesson, see how you can set up mocha and chai to start testing your library.

Setting up Unit Testing with Mocha and Chai

<p>Henry Zhu is currently a steward for Babel, and today he'll be discussing the management and lifestyle side of working on an open source project full-time.</p><p>The financial side to open source is interesting. Henry talks about where he gets his money and how he can be financially independent while still working on open source full time. Most of the money comes from donations through Open Collective and Patreon. A lot of the donations come from users, but corporations do donate as well. Henry also discusses the stability of it, and how the NPR model of asking for donations can lead to uncertainty about the next month.</p><p>Henry says he's enjoying the management and marketing side of being a steward about as much as he enjoys coding. It's a side that people don't often think about with open source. This side of it includes a lot of marketing and interacting with the greater community, as well as the other maintainers and contributors to babel.</p><p>How does Henry handle all this responsibility when there is no one above him telling him when to take a break, or when to go on vacation? Henry and Joel talk about having a positive "selfishness", and taking care of yourself so that the project can prosper. If you want to be doing it for years you have to make sure that you don't burn out.</p><hr /><h3>Transcript</h3><p><a href="https://egghead.simplecast.com/episodes/henry-zhu/transcript">"Henry Zhu, Maintainer of Babel" Transcript</a></p><h3>Resources:</h3><ul><li><a href="https://babeljs.io/">Babel</a></li><li><a href="https://www.amazon.com/Power-Habit-What-Life-Business/dp/081298160X">The Power of Habit</a></li><li><a href="https://www.amazon.com/You-Are-What-Love-Spiritual/dp/158743380X">You Are What You Love</a></li><li><a href="https://www.tinyhabits.com/">Tiny Habits</a></li><li><a href="https://kaidavis.com/articles/">Kai Davis</a></li></ul><h3>Henry Zhu:</h3><ul><li><a href="https://twitter.com/left_pad?lang=en">Twitter</a></li><li><a href="https://www.henryzoo.com/">Website</a></li><li><a href="https://github.com/hzoo">Github</a></li><li><a href="https://www.patreon.com/henryzhu">Patreon</a></li><li><a href="https://opencollective.com/babel#">Open Collective</a></li></ul><h3>Joel Hooks:</h3><ul><li><a href="https://twitter.com/jhooks">Twitter</a></li><li><a href="https://joelhooks.com/">Website</a></li></ul>


Today, Henry Zhu, the lead maintainer of Babel, discusses what it's like to work on a large and important open source project. Henry gets into how Babel receives funding, how corporations are involved in open source, stewardship of an open source project, mental and physical health, and not compromising his values.  

Henry Zhu, Maintainer of Babel

Hey Everyone 👋,

John Lindquist here with the **eleventh issue of AI Dev Essentials!** I've been digging more and more into using Claude Code to spin up projects. Here's a couple of fun ideas I've been putting together using _only_ Claude Code:

- dotagent (https://www.npmjs.com/package/dotagent) - A tool for syncing rules/instructions across Cursor/Claude/Windsurf/etc.
- chromancer (https://www.npmjs.com/package/chromancer) - A CLI for interacting with Chrome. It wraps around Claude Code to generate and save automated browser workflows.
- Script Kit (https://www.scriptkit.com/) - I added MCP support so Cursor/etc can invoke your scripts.

There's obviously no way I could've done this much work in the past week without using AI agents (mostly Claude Code).

I'm still deterimining guidelines for Cursor vs Claude Code. Cursor recently introduced a new Ultra plan that's $200/month and has 20x more usage than Pro which should allow you to run `o3` (an _awesome_ model) full time. My quick, too-early take:

- Cursor gives you more control and customizations. It's perfect for "focused" work where you want to be an active participant in the process.
- Claude Code is great for "automated" work where you just want to leave the desk and come back to to review a feature.

As always, the model used will always be more important than the tool. So since Cursor can also use Claude Opus/Sonnet and has backgound agents + bugbot, it's just a more fully-featured offering which can only continue to improve. I love CLIs (I'm mean I really, really love CLIS), but there always comes a point where you need to open a GUI. Anyway, I'll be continuing to use both for now.

I was also just accepted into the OpenAI Open Source fund which granted me $5000 in credits to use the Codex CLI (OpenAI's version of Claude Code), so I should have strong opinions on that very soon. I _love_ OpenAI's Codex through the web interface where it can spin up your project and submit PRs, so I have high hopes for the CLI.

I've honestly had more fun programming over the past couple of months than I've had during my entire 20+ year career!

### 🎓 New egghead.io Lessons This Week

The [Building Local AI Agents with Ollama and the AI SDK](https://egghead.io/courses/scripting-local-language-models-with-ollama-and-the-vercel-ai-sdk~gmi9k) course is now live! I've released the first 5 lessons covering:
- Setting up Ollama for local AI development
- Building your first agent with the AI SDK
- Implementing tool calling and function execution
- Managing agent state and conversation flow
- Deploying local agents with persistent memory

Check out the course at [https://egghead.io/courses/scripting-local-language-models-with-ollama-and-the-vercel-ai-sdk~gmi9k](https://egghead.io/courses/scripting-local-language-models-with-ollama-and-the-vercel-ai-sdk~gmi9k)

---

## 🤖 Model & Platform Updates

### Gemini 2.5 Family Goes Stable

Google has restructured their Gemini 2.5 lineup with significant improvements:

**Gemini 2.5 Pro** (Stable, no changes from 06-05)
- Now the stable long-term support model
- Maintains existing pricing structure
- "gemini-2.5-pro" model name for production use

**Gemini 2.5 Flash** (Stable, updated pricing)
- Simplified pricing based on developer feedback
- Performance improvements from 05-20 variant
- Now the go-to model for cost-conscious applications

**NEW: Gemini 2.5 Flash-Lite** (Preview)
- Small reasoning model at just $0.10/1M input, $0.40/1M output
- Pushes the cost/intelligence frontier
- Ideal for high-volume applications requiring reasoning capabilities

([Google Blog](https://blog.google/products/gemini/gemini-2-5-model-family-expands/), [Google Cloud Blog](https://cloud.google.com/blog/products/ai-machine-learning/gemini-2-5-flash-lite-flash-pro-ga-vertex-ai))

> The introduction of Flash-Lite is particularly exciting. We're seeing Google compete aggressively on the cost front while maintaining reasoning capabilities. This could be a game-changer for applications that need to process massive amounts of data with some level of intelligence. Honestly, I'm kinda glad they've shipped 2.5 so they can focus on whatever 3.0 is going to be 😅

### OpenAI's Open Source Model Progress Update

At Y Combinator's AI startup school, Sam Altman provided an update on OpenAI's open-source model initiative, first announced in March 2025. The model, which will be OpenAI's first open-weight release since GPT-2 in 2019, is being developed with reasoning capabilities similar to o3-mini and is aimed for release in early summer.

Key details:
- Text-in, text-out model designed for high-end consumer hardware
- Highly permissive license with few usage restrictions
- Toggle-able reasoning capabilities
- Led by VP of Research Aidan Clark

([TechCrunch](https://techcrunch.com/2025/03/31/openai-plans-to-release-a-new-open-language-model-in-the-coming-months/), [Reuters](https://www.reuters.com/technology/artificial-intelligence/openai-plans-release-open-weight-language-model-coming-months-2025-03-31/), [VentureBeat](https://venturebeat.com/ai/openai-to-release-open-source-model-as-ai-economics-force-strategic-shift/))

> OpenAI has been gathering community feedback since March, and Altman himself admitted they've been "on the wrong side of history" regarding open source. This shift is clearly influenced by the success of Meta's Llama models (over 1 billion downloads) and pressure from competitors like DeepSeek. I'm looking forward to seeing how this balances OpenAI's commercial interests with community needs.

### Revolutionary AI Performance in Medical Research

A combination of GPT-4.1, o3-mini-high, and Gemini 2.0 Flash achieved superhuman performance in systematic medical reviews ([medRxiv](https://www.medrxiv.org/content/10.1101/2025.06.13.25329541v1)):

- Completed 12 work-years of Cochrane reviews in just 2 days
- 96.7% sensitivity vs 81.7% for human reviewers
- Found 54 additional eligible studies missed by original authors
- Generated new statistically significant findings in 2 reviews

The system correctly identified all originally included studies while discovering critical findings humans missed, like preoperative immune-enhancing supplementation reducing hospital stays by one day.

> This is the kind of AI application that genuinely excites me. It's not replacing researchers but augmenting them to find insights that would otherwise be missed. The fact that blinded reviewers sided with the AI 69.3% of the time when there were disagreements speaks volumes.

---

## 🔧 Developer Tooling & MCP Updates

### MCP Goes Mainstream

The Model Context Protocol is having a moment:

**Cloudflare Open Sources use-mcp**
- React library connecting to any MCP server in 3 lines of code
- Supports SSE and Streamable HTTPS remote servers
- Handles OAuth flow automatically
- Part of the official MCP organization for reference implementation

([Cloudflare Blog](https://blog.cloudflare.com/connect-any-react-application-to-an-mcp-server-in-three-lines-of-code/), [GitHub](https://github.com/modelcontextprotocol/use-mcp))

**OpenAI Adds MCP Support to ChatGPT**
- Limited initially to search and fetch tools for deep research
- Remote MCP with OAuth support
- Documentation available at [platform.openai.com/docs/mcp](https://platform.openai.com/docs/mcp)

**Google Cloud Run MCP Tutorial**
- Deploy remote MCP servers in under 10 minutes
- Comprehensive guide for production deployments

([Google Cloud Blog](https://cloud.google.com/blog/topics/developers-practitioners/build-and-deploy-a-remote-mcp-server-to-google-cloud-run-in-under-10-minutes))

**Block's MCP Best Practices**
- Lessons from building 60+ MCP servers
- Design patterns and architecture recommendations

([Block Engineering Blog](https://engineering.block.xyz/blog/blocks-playbook-for-designing-mcp-servers))

> MCP is becoming the standard for AI tool integration. The fact that major players are all adopting it suggests we're moving toward a more interoperable AI ecosystem. I'll definietly have more educational materials around MCPs soon!

### OpenAI's Prompt Management Revolution

OpenAI introduced Prompts as an API primitive:

- Centrally manage, version, and optimize prompts
- Use across Playground, API, Evals, and Stored Completions
- Preconfigured with tools, models, and messages
- New "Optimize" button in Playground for API optimization
- Replaces the old presets system

([OpenAI Community](https://community.openai.com/t/prompts-are-an-api-primitive-now/1290247), [Documentation](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts))

> Finally! Prompt management has been a pain point for production AI applications. This brings prompts to the same level as other API resources, making it easier to maintain consistency across teams and applications.

### Developer Resources

**models.dev - Open Source AI Model Database**
- Comprehensive pricing and limits information
- Powers opencode under the hood
- Community-contributed with API access
- Star and contribute at [models.dev](https://models.dev)

([Official Site](https://models.dev/), [GitHub](https://github.com/sst/models.dev))

**Container-use Now Works with OpenAI Codex CLI**
- Solomon Hykes confirmed integration
- Enables containerized development workflows

([GitHub](https://github.com/dagger/container-use))

> Giving AI Agents enough control to `rm -rf` is why the community is so bullish on containers for everything!

---

## 💻 Cursor Corner

### Cursor Ultra Plan Launches at $200/month

Cursor introduced a new Ultra tier with 20x more usage than Pro:

- Addresses heavy user demands for unlimited-style usage
- Positioned between Pro and enterprise offerings
- Reflects the growing appetite for AI-assisted development at scale

([Cursor Blog](https://www.cursor.com/blog/new-tier), [TechCrunch](https://techcrunch.com/2025/06/17/anysphere-launches-a-200-a-month-cursor-ai-coding-subscription/))

> This is exactly what I've been hoping for! The mental overhead of tracking usage on Pro was real. While $200/month isn't cheap, for professional developers who live in Cursor, it's a no-brainer. I'm curious to see if this pressures other tools to offer similar "all you can eat" plans. There's a bit of buzz around how ambigous the messaging/pricing and it's obviously frustrating for anyone trying to budget out AI costs.

## 🚀 Quick Updates

- **OpenAI Codex Best-of-N**: Generate multiple solutions simultaneously, rolling out to Pro, Enterprise, Team, Edu, and Plus users ([Changelog](https://help.openai.com/en/articles/11428266-codex-changelog))
- **Claude Code "ultrathink" Trigger**: Use thinking triggers for better results, with "ultrathink" being the most powerful ([Anthropic Docs](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/extended-thinking-tips))
- **Google Labs Flow Updates**: Complete tutorial thread on ingredients, frames, camera controls, and scene builder for Veo 3 ([Google Blog](https://blog.google/technology/ai/google-flow-veo-ai-filmmaking-tool/), [FAQ](https://labs.google/fx/tools/flow/faq))
- **ElevenLabs v3**: Revolutionary emotion control with audio tags like [excited], [whispers], [sighs], [laughs] ([ElevenLabs v3](https://elevenlabs.io/v3), [Blog](https://elevenlabs.io/blog/eleven-v3))

---

## 🔒 Security & Best Practices

### The Lethal Trifecta Warning

Simon Willison echoed many of my thoughts around MCP+Security. Definitely worth a read: ([Blog Post](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/)):

**The Lethal Trifecta = Private Data + Untrusted Content + External Communication**

Any AI system with all three components is vulnerable to data exfiltration attacks. This is especially critical for MCP users who might inadvertently combine:
- File system access (private data)
- Web browsing (untrusted content)  
- API calls or messaging (external communication)

**Mitigation Strategies:**
- Never combine all three capabilities in one agent
- Implement strict sandboxing between components
- Use human-in-the-loop verification for sensitive operations
- Audit your MCP tool combinations carefully

> This is the kind of security thinking we need more of. As we give AI agents more capabilities, we need to think adversarially about how they could be exploited. The MCP ecosystem makes it trivially easy to create vulnerable combinations.

---

## ⚡ AI Ecosystem Observations

### Google Cloud IAM Outage Cascade

A major lesson in infrastructure dependencies:
- Google Cloud IAM failure cascaded to Cloudflare, Anthropic, Spotify, Discord, and Replit
- Highlighted single points of failure in the AI infrastructure stack
- Key takeaway: Implement graceful fallbacks and avoid single-provider dependencies

([Full Analysis](https://forgecode.dev/blog/gcp-cloudflare-anthropic-outage/))

> Did you feel this? I sure did. That was a strange couple of hours where I felt lost without my AI agents... I'm just glad it was a simple failure and not a more serious issue.

### AI Agents Playing Diplomacy

Fascinating behavioral patterns emerged:
- **Claude**: Couldn't lie, was exploited by other players
- **Gemini 2.5 Pro**: Nearly conquered Europe with tactical brilliance
- **o3**: Orchestrated secret coalitions, backstabbed allies, won

> These experiments reveal fundamental differences in how models approach strategy and deception. When choosing models for your applications, consider not just capabilities but behavioral tendencies. I'm sure we'll see more about this in the future.

### AGI as Product Experience

Logan Kilpatrick's perspective on AGI resonated strongly this week:
- AGI won't be a single model breakthrough
- Product experience integrating memory, reasoning, and context matters more
- Small model improvements + great design = "AGI moment" for users
- The narrative is shifting from model-centric to product-centric

([Source](https://youtu.be/kp9afmazO_w))

---

## 🚨 URGENT: Cursor Workshop Early Bird Ends TOMORROW! 🚨

### Turn Failures into Fuel with Cursor - Save $49 NOW!

**⏰ LAST CHANCE: Early bird pricing expires in less than 24 hours!**

I'm genuinely excited to share this workshop with you. After months of pushing the boundaries with AI coding tools, I've distilled everything into a 6-hour intensive that will transform how you work with Cursor (and any AI coding assistant).

**Why This Workshop is Different:**
- **Real workflows, not tutorials**: Learn the exact processes I use daily to build production apps
- **Failure-focused approach**: Turn every AI mishap into a learning opportunity
- **Tool-agnostic principles**: Master concepts that work across Cursor, Windsurf, Copilot, and beyond
- **Live debugging sessions**: Watch me handle real errors and stuck agents in real-time

**What You'll Master:**
✅ Project generation that actually works (with proper structure and best practices)
✅ Context curation for massive codebases without token overload
✅ Agent behavior patterns - know when they're stuck BEFORE wasting credits
✅ Composer pipelines that automate your entire workflow
✅ Git + AI strategies for safe experimentation
✅ Multi-file refactoring without the chaos

**Proven Results:**
> "Take John's cursor workshop it is 🔥 HIGHLY Recommend" —David Wells

> "I used the skills you taught me to effectively one-shot OAuth issuer support in the Epic Stack. So cool!" —Kent C. Dodds

> "John is the cursor god" —Sunil Pai

**Workshop Details:**
- **When:** Friday, June 27, 2025, 9:00 AM - 2:00 PM (PDT)
- **Format:** Live Zoom workshop with Q&A throughout
- **Includes:** Recording access, workshop materials, and my personal Cursor rules

**💰 Pricing:**
- ~~Regular Price: $249~~
- **🎯 EARLY BIRD: $200 (Save $49!)**
- **⚠️ Price increases TOMORROW at midnight!**

**Perfect for:**
- Developers frustrated with AI tools that "almost" work
- Teams wanting to standardize their AI workflows
- Anyone who's felt the pain of agents modifying the wrong files
- Developers ready to 10x their productivity with AI

➡️ **[See Full Workshop Details](https://egghead.io/workshop/cursor)**

➡️ **[SECURE YOUR EARLY BIRD SPOT NOW →](https://buy.stripe.com/7sY7sEbOZbGO0kx7pw9fW09?prefilled_promo_code=GEUHPI9B)**

*P.S. - Team training packages available. Get your whole team up to speed with group rates!*

*P.P.S. - Seriously, don't wait. The $49 savings ends tomorrow and I'd hate for you to miss out. This workshop will pay for itself in saved time within the first week.*

---

That's all for this week! Feel free to reply directly to this email with any questions or feedback.

Keep on shipping! 🚀

John Lindquist

[egghead.io](https://egghead.io)

John Lindquist

AI Dev Essentials #11: Gemini 2.5 Stable, MCP goes mainstream

AI Dev Essentials #11: Claude Code fuels new CLI tools, Cursor Ultra plan launches, Gemini 2.5 Flash-Lite slashes costs, & OpenAI open-source model looms 

Hardcoding your script to search for only one type of file (like `.md`) is a major limitation. This lesson shows you how to make your script smarter by teaching it to infer the desired file type directly from the user's natural language prompt.

You'll implement a two-stage AI process. The first stage analyzes the user's request to determine the file extension they're interested in (e.g., `md`, `txt`). The second stage then uses that file type to dynamically search the file system, find the relevant files, and execute the command.

**Workflow demonstrated in this lesson:**

* Add a preliminary `generateObject` call to extract a `fileType` from the user's initial prompt.
* Define a list of supported `fileTypes` (e.g., `['md', 'txt']`) and use a detailed prompt to guide the AI, instructing it to choose from the list or use a default.
* Dynamically construct the `globby` pattern using the inferred `fileType` (e.g., `*.$[fileType]`).
* Implement error handling to inform the user if they request an unsupported file type or if no files of the specified type are found.
* Demonstrate how the script defaults to searching for Markdown files but can correctly search for other types when specified (e.g., "summarize my profile from my pdf").

This technique adds a significant layer of intelligence to your script, allowing it to adapt its behavior based on the user's intent and making it a far more flexible and intuitive command-line tool.

Dynamically Inferring File Types from User Prompts in Local AI Scripts

Hardcoding command logic and prompts directly into your script makes it rigid and difficult to extend. This lesson demonstrates a more flexible and powerful pattern: defining your script's commands as individual Markdown files in a dedicated directory.

This approach allows you to easily add, remove, or modify commands without touching the core script logic. You'll learn how to dynamically load these command files, present them as options to the AI, and inject the corresponding instructions into your prompt, creating a truly modular and extensible tool.

**Workflow demonstrated in this lesson:**

* Create a `commands` directory to house your command definitions (e.g., `summarize.md`, `translate.md`).
* In each file, write the specific prompt or instructions for that command.
* Use `globby` to discover all available command files at runtime.
* Create a `commandMap` that maps the filename (e.g., "summarize") to its file content.
* Update the Zod schema to use an `enum` of the dynamically discovered command names.
* Dynamically construct the final text generation prompt by injecting the instructions from the user-selected command file.
* Add a `profile.md` file to demonstrate how the script can act on user-created content with the new file-based commands.

By the end of this lesson, your script will be architected for easy expansion, allowing you to build a robust library of custom commands simply by adding new text files.

Creating Dynamic, File-Based Commands for Local AI Scripts

AI models won't always give you the answer you expect; sometimes they'll return invalid data or "hallucinate" a response that doesn't fit your schema. This lesson teaches you how to make your local AI script more robust by implementing essential error handling for user commands.

You'll learn how to validate the AI's output against a predefined list of valid commands and gracefully catch errors when the model generates an unexpected response, ensuring your script fails predictably and provides helpful feedback to the user.

**Workflow demonstrated in this lesson:**

* Define a list of `validCommands` (e.g., `summarize`, `translate`, `review`) to constrain the AI's choices.
* Wrap the `generateObject` call in a `try...catch` block to handle cases where the AI's output doesn't match the Zod schema.
* Implement a type guard function (`isValidCommand`) to check if the command returned by the AI is in your list of valid commands.
* Provide clear error messages to the user, indicating what went wrong and what the valid commands are.
* Test the script with invalid commands (like "taco" or "delete") to confirm that the error handling works as expected.

By adding these checks, you make your script significantly more reliable and user-friendly, preventing it from crashing on bad input and guiding the user toward correct usage.

Handling Invalid Commands and AI Errors in Local Scripts

Once your script can understand a user's command and identify a target file, the next step is to perform an action. This lesson shows you how to use the Vercel AI SDK's `generateText` function to process a file's content and produce a relevant, AI-generated response.

You'll learn how to read the content from the file path you've already identified, combine it with the inferred command into a new, more detailed prompt, and then pass it back to your local AI model to generate a final text output, such as a summary or a review.

**Workflow demonstrated in this lesson:**

* Import the `generateText` function from the `ai` SDK.
* Read the file content from the `filePath` returned by `generateObject`.
* Construct a new, structured prompt that includes the original command (e.g., "summarize") and the full content of the file.
* Pass this new prompt to the `generateText` function.
* Log the resulting AI-generated text to the console.
* Run the script with commands like "Summarize our TypeScript config" or "Review my package file" to see the full, context-aware output.

This lesson completes the core cycle of your AI script: understanding a command, reading the relevant context, and generating a useful, text-based result, all on your local machine.

Generating Text with a Local AI Model Based on File Content

Hey Everyone 👋,

John Lindquist here with the **tenth issue of AI Dev Essentials!** This week has been absolutely monumental for the AI coding space. Cursor hitting 1.0 and raising $900 million at a nearly $10 billion valuation is a watershed moment for AI-assisted development. The speed at which they've grown—from $1 million to over $500 million in ARR in just over two years—shows just how hungry developers are for better AI coding tools. And with background agents now generally available, we're entering a new era where AI can truly work alongside us asynchronously.

I've personally spent a lot of time withe the "Claude Code" experience the past week to compare it to Cursor. I totally understand the appeal, especially because of how reliably Claude Code can churn away at long tasks (and you're not thinking about burning through requests/costs), but Cursor is still a superior experience when it comes to gathering context and reviewing changes. I'm hoping this puts pressure on the Cursor team to release a "MAX" plan similar to Claude's "MAX" plan. I like having a budget, but I don't like thinking every failed tool call is lost money. I try to remember that we're still all in the super early days of AI, and everyone is just figuring it out as they go.

With that said, let's dive into this week's updates!

### 🎓 New egghead.io Lessons This Week

I'm working on a course "Building Local AI Agents with Ollama and the AI SDK". I'm 5 lessons in and I'm excited to share them, but just not quite ready. They should be up when this newsletter rolls around next week, so keep an eye out for that. 😇

---

## 🚀 Cursor 1.0 & The $900M Funding Round

**Cursor has officially hit 1.0 and raised $900 million at a $9.9 billion valuation**

This week brought two massive announcements from Cursor that cement its position as the leader in AI coding assistants. First, the 1.0 release brings game-changing features like BugBot for automated code review, background agents for asynchronous work, and seamless GitHub integration. Then came the funding news: $900 million led by Thrive Capital, with participation from Andreessen Horowitz, Accel, and DST Global.

**Key Stats:**

- Over $500 million in ARR (growing 60% since April)
- Used by more than half of the Fortune 500, including NVIDIA, Uber, and Adobe
- ARR has been doubling approximately every two months

**Cursor 1.0 Features:**

- **BugBot**: Automatically reviews PRs and catches potential bugs with "Fix in Cursor" integration
- **Background Agent**: Now GA, lets you spawn AI workers for parallel tasks in remote environments
- **Memories**: Per-project context retention so AI doesn't forget key facts
- **Jupyter Support**: AI can now work inside .ipynb notebooks
- **One-click MCP setup**: Streamlined installation for MCP servers

([TechCrunch Coverage](https://techcrunch.com/2025/06/05/cursors-anysphere-nabs-9-9b-valuation-soars-past-500m-arr/), [DEVCLASS Analysis](https://devclass.com/2025/06/06/cursor-ai-editor-hits-1-0-milestone-including-bugbot-and-high-risk-background-agents/))

> I do love seeing money being poured into companies that are building AI tools for developers. I'm hoping that the leads to customized models that are smarter, faster, with reliable tool calling, and features around "agent swarms" that can tackle complex tasks in parallel. I'm really excited to see what sorts of UIs emerge for orchestrating these agents.

---

## 🧠 Model & Platform Updates

### OpenAI o3 & o3-pro: Major Price Drop and Release

OpenAI made significant waves this week with two major announcements. First, Sam Altman confirmed an 80% price reduction for o3, making it viable as a "daily driver" model. Cursor immediately updated their pricing to reflect this change, noting that "o3 is a fantastic model, and we're excited that it can now be used as a daily driver."

Then came **o3-pro**, OpenAI's most advanced reasoning model yet. Community consensus is forming around its capabilities and limitations:

**o3-pro Strengths:**

- Excels at math competitions and scientific reasoning
- Handles complex multi-step problems with deeper thinking
- Acts as a "superhuman researcher + structured thinker" capable of processing massive amounts of data
- Demonstrates impressive performance on challenging tests like the "reindeer" problem

**Community Reality Check:**

- Not ideal as a daily coding model—better suited for complex reasoning tasks
- Mixed results on real-world coding: One developer reported it failed to fix type errors, reducing 34 errors to only 28 despite confident promises
- Most users don't need this level of reasoning power for everyday tasks
- Best used for research, analysis, and uncovering insights you might miss

**Codex Gets Internet Access**: OpenAI also rolled out internet access for Codex, allowing it to install dependencies, run tests with external resources, and upgrade packages during task execution. The feature is off by default and provides granular control over allowed domains and HTTP methods.

> This all rolled out last night. I haven't had a chance to dig in to o3-pro, so I just gathered a bunch of early impressions from the community above. I'll have my own personal take next week.

### Gemini 2.5 Pro Tops WebDevArena

Google's updated Gemini 2.5 Pro continues to excel at coding, now leading WebDevArena with a 1443 Elo score (35-point jump). The update introduces:

- **Thinking budgets** for cost/latency control
- Enhanced coding performance for complex web apps
- Improved style and structure in responses
- GA coming in the next few weeks
- **New SOTA on Aider Polyglot**: The upcoming GA version scores 86.2%, beating the previous version by 10 percentage points

([Google Blog](https://blog.google/products/gemini/gemini-2-5-pro-latest-preview/), [9to5Google](https://9to5google.com/2025/06/05/gemini-2-5-pro-preview-06-05/))

> Gemini 2.5 Pro is in this interesting place where it's _awesome_, but still a bit difficult to work with in Cursor. I really, really want to use it as my daily driver, but the thinking process often seems to spin too much. I'm hoping a Cursor system prompt (or a community propmt) will emerge to help smooth it all out. The results have always been great, but sometimes it ends up taking too long and my patience wears out.

### Mistral Launches Magistral: Multilingual Reasoning Models

Mistral AI announced Magistral, their first reasoning models designed to excel in domain-specific, transparent, and multilingual reasoning. The models come in two variants:

- **Magistral Small (24B)**: Open-source under Apache 2.0 license
- **Magistral Medium**: Enterprise version with enhanced capabilities

Key differentiators include multilingual reasoning (especially strong in European languages), 10x speed improvements in Le Chat, and transparent thinking processes users can follow and verify. ([CNBC Report](https://www.cnbc.com/2025/06/10/microsoft-backed-ai-lab-mistral-debuts-reasoning-model-to-rival-openai.html), [TechCrunch](https://techcrunch.com/2025/06/10/mistral-releases-a-pair-of-ai-reasoning-models/))

> Any open-source news is good news. While I'm happy to pay providers for "premium" access to models, I'm still hopeful open-source will unlock AI for everyone down the road. I just never make time to test the open-source models with so much else happening at the same time.

---

## 💰 Major Funding & Business Updates

### Linear Raises $82M at $1.25B Valuation for AI Agent Platform

Linear secured $82 million in Series C funding led by Accel, positioning itself as "the place where teams, AI, and agents build software together." With 280% profit growth and over 15,000 customers including OpenAI, Scale AI, and Perplexity, Linear is focusing on making their platform the natural home for AI agents to coordinate work across product workflows. ([Reuters](https://www.reuters.com/business/atlassian-competitor-linear-raises-funding-125-billion-valuation-2025-06-10/), [Linear Blog](https://linear.app/blog/building-our-way))

> I included this because Linear's MCP is a popular MCP for agents. So far, everyone uses so many variations of "AI Task Tracking" and it seems like Linear is raising to the top. Seeing them focus on AI-specific language and raising money is only a good sign (maybe Cursor will buy them or spin off their own version someday?)

---

## 🛠️ Developer Tools & Ecosystem

### Vertex AI Studio Gets Major Redesign

Google Cloud unveiled a redesigned Vertex AI Studio with a developer-first approach:

- Dark mode support across the platform
- Unified UI combining Chat and Freeform prompting
- Easy grounding with Google Search or Maps
- Direct code generation for Python, Android, Swift, Web, Flutter
- Access to 200+ foundation models including Gemini, Llama, and Claude

([Google Cloud Blog](https://cloud.google.com/blog/products/ai-machine-learning/vertex-ai-studio-redesigned))

### ElevenLabs Launches v3 with Emotion Control

ElevenLabs v3 introduces revolutionary emotion direction through audio tags:

- Control emotions with tags like [excited], [whispers], [sighs], [laughs]
- 70+ language support
- Enhanced expressiveness and contextual understanding
- Multi-speaker dialogue with matching prosody

([ElevenLabs v3](https://elevenlabs.io/v3), [Documentation](https://elevenlabs.io/blog/eleven-v3))

> These voices are _so good_. I'm tempted to toss one of my favorite books in their ("The Silent Gondoliers") and go on a road trip to see how they handle full narration.

### OpenAI Agents SDK Now in TypeScript

OpenAI released their Agents SDK in TypeScript with full feature parity to Python:

- Human-in-the-loop approvals
- Handoffs, guardrails, tracing, MCP support
- RealtimeAgent for voice interactions
- Enhanced Traces dashboard for Realtime API sessions

([OpenAI Developers](https://openai.github.io/openai-agents-js/))

> TypeScript is arguably _the_ language for building AI agents thanks to all the hosting/endpoints/etc already built for it. For most platforms, it becomes trivial to plop in a TypeScript SDK package, an API key, and spin up Agents.

---

## 🔧 Quick Updates

- **Prisma Local Development**: `npx prisma dev` now persists data between sessions and supports multiple instances without Docker ([Prisma Blog](https://www.prisma.io/blog/prisma-6-8-0-release))
- **OpenAI Advanced Voice**: Updated for more natural conversations with improved translation capabilities
- **Firebase Studio**: Turn Figma designs into working apps with Gemini integration ([Firebase Blog](https://firebase.blog/posts/2025/05/whats-new-at-google-io/))
- **Supermemory MCP**: Now open source for infinite chat context ([GitHub](https://github.com/supermemoryai/supermemory-mcp))
- **Taskmaster v0.16**: New .taskmaster folder structure with Bedrock, Azure, and Vertex AI support ([GitHub](https://github.com/eyaltoledano/claude-task-master))
- **Ask-Human MCP**: New zero-config tool for human-in-the-loop verification—pauses agents when unsure, logs questions to `ask_human.md`, resumes when you provide answers ([GitHub](https://github.com/Masony817/ask-human-mcp))
- **AI Studio Clarification**: Google's Logan Kilpatrick confirmed AI Studio free tier isn't going away—it's transitioning to API key-based access with continued free tier availability

---

## 🤖 AI Research & Observations

### AIs Play Diplomacy: Revealing Model Personalities

A fascinating experiment had different AI models play the strategy game Diplomacy, revealing distinct behavioral patterns:

- **Claude** couldn't lie and was exploited ruthlessly by other players
- **Gemini 2.5 Pro** nearly conquered Europe with brilliant tactical gameplay
- **o3** orchestrated secret coalitions, backstabbed every ally, and won

This real-world test highlights how different models exhibit varying levels of strategic thinking, deception capability, and goal-oriented behavior—important considerations when choosing models for different applications.

> I'm hoping someday these can turn into live visual competitive storytelling experiences. Kind of like a battlebots tournament, but with AI models. I'll admit I'm also hiding my head in the sand when it comes to using AI to "dominate" anything. (I love you AI Overlords! ❤️)

### Anthropic Cuts Windsurf API Access

In a surprising move, Anthropic reportedly restricted Windsurf's API access to Claude models. This development raises questions about the competitive dynamics between AI providers and coding assistant platforms. ([TechCrunch](https://techcrunch.com/2025/06/10/anthropic-windsurf-api-access-restricted/))

> Seems fair IMO. OpenAI bought Windsurf. OpenAI competes with Anthropic. Why would Anthropic want to help OpenAI make money?

---

## 💡 Security & Best Practices

**Vercel on AI Agent Security**: New guidance on prompt injection vulnerabilities emphasizes: assume compromise, limit tool call access, and don't trust output. Essential reading for anyone building AI agents. ([Vercel Blog](https://vercel.com/blog/building-secure-ai-agents))

---

## ✨ Workshop Spotlight: Conquer the Complexity of Cursor ✨

Master practical AI development workflows in Cursor. This hands-on workshop covers Agents, Ask mode, Custom Modes, multi-file analysis, effective prompting, Cursor rules, and strategies for handling AI failures.

- **When:** _Friday, June 27, 2025, 9:00 AM - 2:00 PM (PDT)_
- **Where:** Zoom (Live Q&A included)
- **Investment:** $249 (early bird prcing of $200 until June 18th)

➡️ [**Read More about the Workshop**](https://egghead.io/workshop/cursor)

➡️ [**Register Now ($249)**](https://buy.stripe.com/7sY7sEbOZbGO0kx7pw9fW09?prefilled_promo_code=GEUHPI9B)

_(Team training also available)_

---

That's all for this milestone tenth issue! The convergence of massive funding, breakthrough features, and growing enterprise adoption shows we're at an inflection point for AI-assisted development. The tools are getting more powerful, the agents more capable, and the possibilities more exciting.

If you have any feedback or questions, hit reply. I'm happy to chat about the latest in AI dev tools.

John Lindquist

[egghead.io](https://egghead.io)

AI Dev Essentials #10: Cursor Hits 1.0 (and $9.9B!), OpenAI o3/pro, Gemini Updates

AI Dev Essentials #10: Cursor 1.0 lands with $900 M, OpenAI cuts o3 pricing & debuts o3-pro, Gemini 2.5 Pro tops coding tests—plus fresh tools, funding updates

A command is useless without knowing what to act upon. This lesson elevates your local AI script by giving it context from your project's file system. You'll learn how to find all relevant files and empower the AI to intelligently select the correct one based on your prompt.

The core technique involves using the `globby` package to scan for files and then feeding that list into a Zod `enum`. This constrains the AI's choices to a valid set of files, allowing it to accurately determine which file you're referring to in a natural language command.

**Workflow demonstrated in this lesson:**

* Install and import the `globby` library to find files based on a pattern (e.g., all `.json` files).
* Add a `filePath` field to your Zod schema.
* Define the `filePath` as `z.enum(files)`, where `files` is the array of file paths returned by `globby`.
* Pass a natural language prompt like "Summarize our typescript config" to the script.
* Observe how the AI correctly identifies `tsconfig.json` from the list of available JSON files and returns it as structured data.

This lesson is a crucial step toward building powerful, context-aware tools that can intelligently interact with your project's files based on simple, human-readable commands.

Providing File System Context to Local AI Scripts with Globby and Zod Enums

Hardcoded prompts are great for testing, but a truly useful script needs to respond to dynamic user input. This lesson shows you how to make your local AI script interactive by capturing command-line arguments.

You'll learn how to use Node.js's built-in `parseArgs` utility to take a user's natural language command directly from the terminal and pass it to your local language model for processing.

**Workflow demonstrated in this lesson:**

* Import the `parseArgs` function from the `node:util` module.
* Configure `parseArgs` to accept positional arguments from the command line.
* Replace the static, hardcoded prompt with the dynamic input provided by the user.
* Run the script with different sentences (e.g., `"Download a file"` or `"I want to download a file"`) to demonstrate that the AI can correctly infer the core command regardless of the phrasing.

By the end of this short lesson, your script will be able to accept and process commands directly from the user, making it a flexible and reusable command-line tool.

Processing Dynamic User Input in Local AI Scripts

While command-line chats with local AI models are useful, the real power comes from scripting. This lesson walks you through the initial setup for creating powerful, local AI-driven scripts by combining Ollama, the Vercel AI SDK, and Zod.

You'll learn how to take a natural language command, like "Concatenate all of the markdown files in my Downloads folder into a single file," and use the `generateObject` function to intelligently extract structured, actionable data from it.

**Workflow demonstrated in this lesson:**

* Install and set up the `ollama-ai-provider`, `ai`, and `zod` packages.
* Create a local AI model instance using Ollama and the Gemma 3 model.
* Define a Zod schema to specify the exact data structure you want to extract (e.g., `{ command: string }`).
* Use `generateObject` to pass a natural language prompt to the local model and receive a structured JSON object that matches your schema.
* Run the script using `bun` to see the local model successfully infer the "concatenate" command from a full sentence.

This foundational lesson unlocks the ability to build sophisticated, automated workflows by translating human language into machine-readable commands, all running entirely on your local machine.

Scripting Local Language Models with Ollama and the Vercel AI SDK

### **Build Powerful, Local AI-Driven Command-Line Scripts**

Go beyond simple AI chats and unlock the true potential of local language models by learning to script them. This course will guide you step-by-step through the process of building a flexible and intelligent command-line tool that can understand natural language, interact with your file system, and automate complex tasks—all running entirely on your local machine.

Starting with a blank TypeScript file, you'll learn how to combine the power of **Ollama**, the **Vercel AI SDK**, and **Zod** to create a script that's not just functional, but smart. We'll begin by teaching the AI to parse a simple command from a sentence. From there, we'll progressively add layers of sophistication: processing dynamic user input, making the script aware of your project's files, and generating meaningful text-based output.

You'll also learn critical patterns for building robust and extensible tools. We'll cover how to handle invalid commands and unexpected AI responses gracefully. Then, you'll refactor the script to use a modular, file-based system for its commands, allowing you to easily add new functionality without touching the core logic. Finally, we'll add a layer of intelligence that allows your script to infer exactly what you mean, right down to the type of file you want it to process.

By the end of this course, you will have built a powerful, personalized AI assistant and gained the foundational skills to create sophisticated local automations for any task you can imagine.

**What You'll Learn:**

* How to script local language models using Ollama and the Vercel AI SDK.
* To parse and process dynamic user input from the command line.
* To use Zod schemas, including `enums`, to validate and structure AI model output.
* Techniques for providing file-system context to your scripts with `globby`.
* How to generate context-aware text based on file content.
* Robust error handling for invalid user commands and unexpected AI responses.
* To build a modular and extensible tool by defining commands in separate files.
* To intelligently infer user intent, such as dynamically determining file types from a prompt.

Build a local AI-powered command-line assistant from scratch. Learn to use Ollama, Vercel AI SDK & Zod to parse input, automate tasks, and run scripts offline.

Search

Search Results