Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
How to Audit Your Job for AI Risk in 10 Days: The TCLD Framework Explained
Tag every calendar item and work output over 10 business days into Theater, Commodity, On-the-Line, or Durable. Here's the full method.
Better Model vs. Better Harness — Which One Actually Moves Your Agent's Benchmark Score?
The same model shows up to 6x performance variation based solely on harness design. Here's the data on where to invest first.
How to Build a Brand Identity File for Your AI Agent: The Interview Method
Stop writing identity files from scratch. Use the AI interview method to create a user.md and brand context file that gives your agent consistent outputs.
How to Build a Voice Agent with 11 Labs and Cal.com Booking Using Claude Code: 45-Minute Walkthrough
No API docs, no dashboard configuration. Claude Code reads the 11 Labs docs autonomously and builds a working voice booking agent in under an hour.
Claude + Blender MCP: What It Can Do, What It Can't, and When to Use It
Claude's Blender MCP connector is impressive but limited. Here's an honest look at its real-world performance, limitations, and best use cases.
Claude Code Found the UTC Timezone Bug in a Cal.com Tool Call by Reading the Conversation Transcript
The Cal.com tool was querying availability in UTC instead of local time. Claude found the bug by reading the transcript — without being told where to look.
Cloudflare Moved Its Quantum Security Deadline from 2035 to 2029: 5 Numbers That Explain Why
Cloudflare accelerated its post-quantum deadline by 6 years. Here are the five specific research numbers that forced the change.
Codex agents.md vs. Claude Code CLAUDE.md — Which Project Context System Actually Works Better?
Both Codex and Claude Code use a markdown file to anchor project context. Here's how agents.md and CLAUDE.md differ and when each approach wins.
Codex Automations Silently Default to GPT-5.2 — Here's How to Fix the Hidden Model Setting
Codex automations quietly use GPT-5.2 instead of GPT-5.5 by default. This hidden setting caused a 40-minute automation to stall. Here's the fix.
How to Use Skill Systems in Codex: Chaining Skills Into Scheduled Automations
Individual skills save time. Skill systems save your week. Learn how to chain Codex skills into scheduled pipelines that run without your supervision.
Why Consumer AI Agents Still Feel Disappointing: 5 Rungs They Haven't Climbed Yet
The ladder of trust — from read-only to fully autonomous — explains exactly where every consumer agent product is stuck and what it would take to move up.
What Is Context Inheritance in Claude Code? How to Manage Multi-Client Projects
Claude Code's context inheritance lets parent folders pass shared methodology to client subfolders. Learn how to structure multi-client AI agent projects.
How to Deploy an AI-Built Dashboard to Vercel Using Claude Code or Codex
Go from local AI-generated app to live URL in minutes. Learn how to push your Claude Code or Codex project to GitHub and deploy it on Vercel for free.
Durable Work vs. Commodity Work — How to Position Yourself on the Right Side of AI Automation
The legibility paradox: make your work too visible and it becomes automatable. Too hidden and it gets cut. Here's how to thread the needle.
Ezra Klein's Counterintuitive Argument: Mass AI Unemployment Would Actually Be Easier to Handle Than What's Coming
Klein argues 80M displaced workers would force policy action — but 8M targeted ones get ignored like the China trade shock. Here's why that matters.
GitHub Is Planning for 30x More Repos — The Infrastructure Signals That Proactive Agents Are Almost Here
GitHub is preparing for 30x repo growth from agent activity. Stripe's agent-driven signups are exponential. Here's what the infrastructure data reveals.
How to Set Up Google Pomelli for Branded Social Content in Under 30 Minutes
Skip manual brand DNA entry. Screenshot the template, run it through Gemini, paste back in. Here's the full Pomelli setup workflow with the AI shortcut.
Google Pomelli Video Animation Only Works in 9:16 — The Hidden Format Requirement Most Users Miss
The animate button in Pomelli only appears after switching to 9:16 story format. Animated text is also unreliable. Here's the workaround for both issues.
Google Pomelli vs. Manual Product Photography — When AI-Generated Photoshoots Are Good Enough
Pomelli's studio, ingredient, in-use, and contextual templates auto-select by product type. Here's an honest look at output quality vs. real photography.
Google's Quantum Attack Estimate vs. Caltech's: Which Timeline Should You Actually Plan Around?
Google says under 500K physical qubits in minutes. Caltech says 26K qubits in days. The numbers differ — here's how to read both for planning purposes.
GPQA vs. Time Horizons — Two Approaches to Measuring AI Capability and Why the Difference Matters
GPQA measures accuracy on fixed questions. Time Horizons measures task duration. The GPQA creator explains why both approaches have blind spots.
GPT 5.5 vs Claude Opus 4.7 for Agentic Coding: Real-World Differences
GPT 5.5 and Claude Opus 4.7 power different coding agents. Compare their strengths, token efficiency, and best use cases for agentic development work.
Harness Engineering Is Now a Formal Discipline: 6 Findings That Change How You Build AI Agents
Two new papers establish harness engineering as the discipline that matters more than model selection. Here's what the research shows.
Higgsfield MCP vs. CLI for Claude Code Agents — Why the CLI Is Significantly Cheaper for Agentic Workflows
The Higgsfield MCP exposes every tool simultaneously — expensive for agents. The CLI is purpose-built for agentic use and significantly cheaper.