Lola

Lola

Lola is the founder of Lunch Pail Labs. She enjoys discussing product, app marketplaces, and running a business. Feel free to connect with her on Twitter or LinkedIn.

Your instructions are probably a mess. Mine were too. XML fixed it.

Your instructions are probably a mess. Mine were too. XML fixed it.

Most AI agents break because their instructions are too long, too vague, or too human. I used to write like that too — until I switched to XML and finally got the control I needed.

The Software Leader's Guide to Xero

The Software Leader's Guide to Xero

Xero is a cloud-based accounting platform built for small businesses, offering real-time financial management and a powerful ecosystem of connected apps. With a robust API and global reach, Xero empowers developers to build tools that simplify business and scale effortlessly.

The Software Leader's Guide to RapidAPI

The Software Leader's Guide to RapidAPI

RapidAPI empowers software leaders to scale faster by turning services into APIs and connecting with millions of developers worldwide. Its powerful platform simplifies API development, publishing, and monetization.

Stop the 5867 Design Syncs. Show a Prototype Instead

Stop the 5867 Design Syncs. Show a Prototype Instead

Tired of endless design syncs and slow approvals? Use prototypes and AI tools to align faster, cut feedback loops, and move projects forward—without the back-and-forth.

AI at the Point of Work — How Browser-Based Assistants Unlock 10x Output

AI at the Point of Work — How Browser-Based Assistants Unlock 10x Output

Most AI tools sit outside the flow of work. PailFlow brings AI into the browser, where real work happens. Here's what makes that so effective—and how it changed the way I build.

Why too many AI model choices are costing you customers (and what to do instead)

Why too many AI model choices are costing you customers (and what to do instead)

Not all AI models are the same. Some prioritize speed, others cost, and some excel at reasoning or summarization. If your users have different needs, letting them choose their model can improve their experience—but too much choice can add confusion. Here’s when to offer AI model selection and when to keep things simple.