Writing

Field notes on production voice AI, telephony, and building software with agents.

18 articles and field notes

Subscribe via RSS ↗

AI Made Building Faster. We Still Have to Decide What to Build.Small teams can ship more with AI. But unclear requirements still send us back to rebuild. My thoughts on planning, prototypes, and engineering judgment.September 7, 20266 min read

One API, Many Carriers: Designing a Provider-Neutral Telephony LayerProduct code should talk to a capability, not a vendor SDK. Lessons from running Twilio, Vonage and Telnyx behind one interface.September 5, 20266 min read

STIR/SHAKEN, CNAM, and Why Nobody Answers Your AI's CallsYour agent can be flawless and still show up as Spam Likely. What I learned about caller identity and number reputation running outbound voice agents.September 5, 20266 min read

The Real Cost of a Voice Agent MinuteOur infrastructure cost fell from $0.26 to $0.10 per minute. How to meter each component, compare operating costs, and protect conversation quality.September 4, 20265 min read

Answering-Machine Detection Is Turn-Taking's Evil TwinBefore a voice agent can decide when to speak, it has to decide whether anyone is there. Why AMD is hard, and why you cannot test it by calling your own phone.September 3, 20266 min read

Turn-Taking Is the Hardest Problem in Voice AICallers forgive a mediocre answer long before they forgive being interrupted. Notes on endpointing, latency and barge-in from real phone lines.September 2, 20266 min read

Migrating Production Voice Agents from Vapi to LiveKitWe ran dealership voice agents on Vapi and now run them on LiveKit. What we did before the migration so it would not become a rewrite, and what it did to cost.September 1, 20267 min read

Issue Tracking Is Dead. The Ticket Is Just a Receipt.I pulled 18 months of my own commit history to test whether tickets still do anything. Here is what the data shows, including the part that contradicts me.August 9, 20268 min read

What Is the Singularity? Why Sam Altman and Elon Musk Say We Are Already In ItWhat the singularity means, why Altman and Musk argue it has already started, and which parts of that claim survive contact with the evidence.August 3, 202613 min read

Claude Code: The AI Coding Assistant That Lives in Your TerminalWhat Claude Code actually does in a terminal, how it differs from an editor plugin, and where an agent that reads and edits your repo earns its keep.March 17, 20267 min read

Claude Cowork: AI That Actually Does the Work on Your ComputerClaude Cowork runs real work on your machine rather than suggesting it. What that changes, where it holds up, and the tasks worth handing over first.March 17, 20268 min read

Twilio A2P 10DLC: Brands, Campaigns, Costs, Throughput, and ComplianceA comprehensive guide to Twilio’s A2P 10DLC system, including Brand and Campaign types, associated costs, throughput limits, and compliance requirements.August 15, 202541 min read

The Real Bottleneck in Software Development Isn’t Writing CodeTyping was never the slow part. Where the time actually goes in shipping software, and why writing code faster moves the needle less than you would hope.August 10, 20254 min read

Your Docs Have a Second Reader Now, and It Does Not ScrollPractical ways to make documentation readable by agents: llms.txt, plain-markdown endpoints, stable URLs, answer-first pages, and doc servers. With what I could verify and what I could not.June 16, 20257 min read

Everything I Ship Is a Wrapper. The Model Was Never the Product.What a product built on someone else's model actually has to own: the workflow, the integrations, the evaluation harness, and the failures the provider will never see.May 17, 20257 min read

The Next.js Naming Conventions I Actually FollowI audited twelve of my own Next.js repos before writing this down. Here are the naming rules that survived the audit, the two places my repos disagree with each other, and the rules the framework decides for you.May 16, 202512 min read

Formatting Belongs to Tools, Not Code ReviewsOne formatter per language, pinned to a version, enforced at save, commit and CI. The rules I apply across my JavaScript, TypeScript and Python repos, and why I stopped tuning the options.May 15, 20255 min read

I Stopped Prompting and Started Specifying: How I Work With Coding AgentsThe practices that decide whether a coding agent helps or costs you time: context budgets, spec-first delegation, parallel runs, verification gates, and knowing when to stop prompting.February 23, 20257 min read