A Two-Stage Pre-Publish Gate for User-Facing AI Text in Consumer Apps
Design a two-stage pre-publish gate for short AI-generated text you ship to end users: a deterministic rule layer plus a Claude classifier, with fail-closed handling, generation-time vetting, and a cost model. Full implementation code included.
When Extended Thinking Flattened My Accuracy but Doubled the Bill — Field Notes on Measuring the Marginal Utility of Thinking Tokens
You pinned budget_tokens high 'to be safe,' accuracy barely moved, and the bill kept climbing. These field notes show how to ledger real thinking-token usage by p50/p95/hit-rate and measure how much accuracy each extra 1,000 thinking tokens actually buys.
Using Claude's Reflect Monthly Review to Tune a Solo Dev Rhythm
How to read Claude's new Reflect monthly review as a planning tool for the month ahead rather than a report card, grounded in the day-to-day rhythm of solo development.
A Long Non-Streaming Response Was Billed Twice Past the 10-Minute Wall: Redesigning the SDK's Default Timeout and Retries
The Anthropic SDK's default 10-minute timeout and two automatic retries can silently re-run a long non-streaming response and bill you twice. Here is how the trap works, and how to close it with streaming, explicit timeout/max_retries, and a small local ledger — with measured before/after numbers.
When Instructions Fade in Long Conversations: Measuring Adherence and Pulling It Back
System-prompt instructions quietly lose their grip as a conversation grows. This piece turns that drift into a number you can track, then fixes it with prompt structure and mid-conversation re-anchoring, backed by runnable code and measured results.
Claude in Chrome Went GA and I Stopped Babysitting the Tab — Where Background Notifications and Handoff Actually Help
Claude in Chrome's general availability adds background notifications, draft handoff, and better failover. As someone who hands browser work to it daily in solo development, here's what to notify on, what to leave running, and the settings I actually changed.
Drop Your Static Claude API Keys: Moving CI and Production to Keyless Auth with Workload Identity Federation
Workload Identity Federation is now generally available on the Claude Platform. This guide walks through replacing long-lived sk-ant- keys with short-lived OIDC tokens, including keyless GitHub Actions auth, the migration steps, and token refresh design.
Putting a Ceiling on the pause_turn Loop: Running Long Server Tools Safely Unattended
A production design for continuing pause_turn safely in unattended runs, where long server tools like web_search and code execution are involved. Covers branching all four stop_reason values in one loop, capping continuations and wall-clock time, and accumulating usage across paused segments.
Connecting Managed Agents to Services You Don't Want to Expose: MCP Tunnel Design
How to connect Claude Managed Agents to an internal MCP server that is never exposed to the public internet. We cover the MCP tunnel, self-hosted sandboxes, authorization boundaries, and graceful degradation when things break.
Where the human still has to press the button — lessons from delegating ad ops to Cowork
From actually delegating repetitive ad operations — AdMob bidding-partner sign-ups and floor tuning — to Cowork, here is the boundary I found between what AI can fully own and the single moves a human still has to make by hand.
Catching Claude Quality Regressions With an Eval Harness
I tweaked a prompt by one line and, for a different set of inputs, the output quietly got worse. Here is the eval harness I built to protect Claude's production quality across every prompt change and model update, with full implementation code and real operating numbers.
Adding Three AdMob Mediation Partners With Claude — What I Learned Updating 4 iOS Apps at Once
A hands-on account of adding Unity Ads, Liftoff, and InMobi to 4 iOS apps simultaneously. Covers W-8BEN tax form submission, ATT prompt ordering, and AppLovin MAX waterfall setup — all with Claude as my documentation navigator.