7 min read
Execution Is Cheap Now — Evals Are the Job
I routed my whole workday through Claude — email, Slack, research, tickets. The throughput gain was the boring part. The interesting part is what's left for me to do.
#ai
17 posts
5 min read
Chatting About Stablecoins, LINE Pay, and the B2B Era
A casual LINE debate over whether restaurants need stablecoin payments turns into a bigger question: is this an era where B2C startups get flattened by giants?
9 min read
Confessions of a Silicon Valley PM: AI Lab Secrets, Rest-and-Vest Hangovers, and the Myth of the Mentor
A conversation with a Silicon Valley product manager — the traffic-light framework for PM decisions, whether to validate a side project with interviews or a POC, the real inside story on DeepMind, Anthropic, OpenAI and Meta, and how hard it is to find a mentor in Silicon Valley.
10 min read
A Walk With Cursor's Ian Huang: Coding Agents, Startups, and Remembering to Document the Process
Notes from a walk with Cursor's Ian Huang in San Francisco: coding agents, product validation and startups, then personal brand, education, philosophy, and how to build the life you actually want.
7 min read
Hugging Face vs. GitHub: What ML Engineers Actually Use
Hugging Face solves a different problem than GitHub. How ML engineers use both platforms, and why models and datasets live on Hugging Face.
9 min read
Claude Code, LangGraph & n8n: The GTM Engineering Stack
See how Claude Code, LangGraph, and n8n split GTM engineering work — operator harness, reasoning engine, and automation glue — with real workflow examples.
5 min read
How a Teen Chatbot App Became Hugging Face, the GitHub of AI
Hugging Face started as a chatbot for teenagers. Here's the week it pivoted to open-source AI infrastructure — and what that pivot teaches builders.
9 min read
LangChain vs. Claude Code for GTM Engineering: What to Use When
Clay's GTM engineering stack shows the difference between production agent frameworks like LangGraph and operator harnesses like Claude Code or Codex.
5 min read
What Is GTM Engineering? (And Why It's Not Just RevOps With AI)
GTM engineering turned go-to-market from a series of manual handoffs into a system you build. A look at what the role actually does, how it differs from RevOps, and why ~100 job listings for it now open every month.
3 min read
Linear, Jira, and the Case Against Product Management Tools
Paying for Linear or Jira might be one of the worst investments a company makes. A first-principles look at why PM tools exist, and what replaces them once AI can render the interface.
6 min read
What Is DESIGN.md, and Why I'm Watching It Closely
DESIGN.md is Google's open file format for handing your entire design system to an AI coding agent — like a CLAUDE.md, but for design. Here's what's in it, what Atlassian found when they stress-tested it, and why it's a near-perfect fit for a small site like this one.
11 min read
Why Big Companies Are Building Their Own Coding Agents
Ramp built Inspect, Stripe built Minions, Block built goose. Cursor and Claude Code exist and are excellent — so why are these companies rolling their own? The answer is context, integration, and ownership, and it says something about where the moat in AI engineering actually sits.
12 min read
When Your Best Hire Asks for a Compute Budget
Notes from an interview with Perplexity's Dmitry Shevelenko — why every knowledge worker is becoming an executive, what Perplexity learned watching CEOs out-adopt their own employees, and why agentic checkout is overhyped.
6 min read
Coffee With David Zeng: Sell the Shovels, Charge for the Service
Notes from a coffee chat with David Zeng, co-founder of Beacons AI — on cancelling AI subscriptions, why the boring jobs are the ones worth paying for, and what 'Service as a Software' really means.
8 min read
MCP, Skills, and Workflows: Three Ways to Put Claude to Work
A plain-English guide to the three features that decide what an AI agent can do — MCP (access), Skills (a toolbox it chooses from), and Workflows (a strict assembly line) — with the analogy that finally made them click for me.
7 min read
Stop Treating AI as a Tool — It's a Digital Employee That Needs Onboarding
Notes from the Crossroads podcast on Forward-Deployed Engineers (FDEs), why most enterprise AI projects fail, and the shift from selling slide decks to shipping working agents.
7 min read
When AI Builds Itself: Reading Anthropic's Recursive Self-Improvement Essay
Anthropic says 80% of its own code is now written by Claude. I read their recursive self-improvement essay, checked the numbers, and separated what they actually claimed from the doom-spin around it.