Field Trials
Take the tools outside and see what breaks — agents become products, and products can be raced.
Twelve months after we hand-rolled a tool-calling loop, coding agents are a product category with fifteen entrants — so we raced them. The June report puts 15 agents head-to-head; feature development goes phone-only with Jules, Codex, and Cursor; Microsoft Build signals the platform bet on protocols — MCP, A2A, NLWeb; Gemini gets reassessed; and "Don't be passive-aggressive with your agents" notices that tone is an operational parameter. The trial results all point one direction: raw model capability is table stakes, workflow fit and harness decide the winner. That finding runs the rest of the run.
The Quarterly Retrospective
We took the tools outside. Fifteen coding agents ran the same gauntlet in the June report, a working PWA got built entirely from a phone, and Microsoft Build made the industry's bet explicit: protocols — MCP, A2A, NLWeb — are the prize, not just bigger models.
The shootouts kept teaching one lesson: capability is table stakes and workflow fit decides. Two essays aged the best — On Demos and Demons, on the gap between the stage and the bench, and Don't Be Passive-Aggressive, which turned out to be operations advice, not etiquette.
June 2025 Coding Agent Report
A comprehensive analysis of 15 leading AI coding agents in 2025. We break down the strengths, weaknesses, and surprises from top tools, with clear winners for pros, tinkerers, and casual users alike.
Thoughts on gemini
Despite popular narratives about Google lagging in AI, their Gemini models reveal engineering excellence that's hard to ignore when you strip away the conservative product decisions and UI polish. From the lightweight yet powerful Gemma 3 to the multimodal capabilities of Gemini 2.5, Google's models demonstrate a level of speed, precision, and fundamental understanding that suggests they're not playing catch-up—they're just being cautious.
Don't be passive aggressive with your agents
Treat your coding agents as adaptable collaborators—communicate clearly, value efficiency over endurance, match tools to your workflow, skip unnecessary formality, rethink technical debt, and document your development rules for best results.
Use Cursor in Slack
Learn how to integrate Cursor with Slack for seamless code review and collaboration, including setup tips and workflow enhancements.
Content Finder
Ever had a movie stuck on the tip of your tongue or wanted more like your family's favorite? Explore how AI-powered content discovery can help you make your next pick.
Geolocation Prompt
This post introduces a prompt for high-precision, image-based geolocation analysis, guiding AI to deduce where a photo was taken using expertise in visual, cultural, and environmental cues. The prompt provides a step-by-step framework for analyzing images and generating confident, reasoned location guesses—even suggesting what extra information would help if uncertain.
Iterating designs with Chat GPT 4o
Discover how to leverage Chrome's hidden command palette and ChatGPT to transform your website screenshots into sophisticated wireframes. Learn a clever workflow that combines Chrome's full-page screenshot capability with ChatGPT's AI-powered design suggestions to create professional 16:9 ratio mockups for your next project.
Use the llm cli for quick prototyping
Transform your workflow with a command-line tool that brings AI capabilities directly to your terminal, no complex setup required. See how to parse websites, analyze transcripts, and extract meaningful data using the llm CLI with popular models like Gemini and Claude.
Lift and shift
Master the art of learning from existing projects by using this structured approach to extracting and documenting requirements and insights. With simple command-line tools and clear documentation practices, you'll be able to turn any existing implementation into a wealth of reusable knowledge.
Feature Development on the go
What happens when you challenge Google Jules, OpenAI Codex, and Cursor to build a PWA—using just your phone? Find out which agent delivered.
Report from Microsoft Build 2025
Microsoft is betting big on an open, agent-powered web—where protocols like MCP, A2A, and NLWeb redefine how AI and services interact. The real opportunity in AI isn’t just smarter models, but the “capability overhang” waiting to be unlocked by better reasoning and open standards.
Geo-affordance
Imagine having Sherlock Holmes’ legendary eye for detail—AI now makes that possible for all of us. Is this AI changing us? It will alter our expectations and the risks of everyday digital life.
On Demos and Demons
June 2025 Coding Agent Report
15 AI coding tools tested — strengths, weaknesses, and recommendations.