Reserving Priority Capacity for User Traffic with service_tier
If you pay for Priority Tier but your user-facing responses still slow down at peak, the culprit is often your own background jobs eating the priority pool. Here is how to read service_tier, prove the contention, and isolate background work.
Putting Cloudflare AI Gateway in Front of Claude Made the Numbers I Needed Disappear — Field Notes on Instrumentation
After putting Cloudflare AI Gateway in front of Claude API, here is where I actually got stung — cost attribution, semantic-cache false hits, fallback quietly lowering quality, and budgets that don't really stop anything — with the code I used to fix each.
When Your Claude × Playwright Browser Agent Fails While Reporting Success — Verifying Actions and Catching UI Drift
A vision-driven Claude + Playwright browser agent fails quietly: it reports success while nothing actually changed. Here is how to stop trusting self-reports, verify each action against the goal, and detect UI drift before it breaks you.
When Your Claude API Response Cache Returns Stale Answers and Near-Miss Wrong Ones — Field Notes on Freshness and False-Hit Suppression
A Claude API response cache improves latency and cost immediately, but the problems that hurt in production are not average hit rate — they are stale hits and semantic false hits. Here is the key design, freshness management, false-hit suppression, and observability that keep a cache honest.
When Claude API Extracts the Wrong Value With Full Confidence — Designing the Verification Layer
When you extract invoices or contracts with Claude API, the scariest failure isn't an exception — it's plausible-but-wrong JSON. Here is how I build a verification layer that catches silent extraction errors with schema checks, arithmetic reconciliation, and dual-extraction agreement, in TypeScript.
Making the Numbers Add Up in a Multi-Tenant Claude API SaaS — Field Notes on Isolation and Cost Attribution
The first thing that breaks when you make a Claude API SaaS multi-tenant is the month-end reconciliation. Here are field notes on a single metering chokepoint, atomic counters, reconciling against Anthropic's bill, and proving tenant isolation with adversarial tests — with production TypeScript.
Keep a Decision Rationale Ledger for Autonomous Agents — So You Can Explain 'Why' Later
When an autonomous agent takes hard-to-reverse actions like a production deploy or a bulk delete, capture the chosen option, rejected alternatives, and assumptions in a structured ledger. Includes structured output, an append-only log, and tiering by impact.
PII Masking for Claude API Lives or Dies on the Ledger — Restore, Encrypt, Measure
The hard part of masking PII before Claude API isn't detection — it's operating the token ledger you restore from. Encrypted storage, multi-instance sharing, and a daily leak-rate loop, with working code.
Centralizing the anthropic-beta Header So a Retired Beta Won't Kill Your Batch
Scattered anthropic-beta headers turn a beta retirement or GA graduation into a 400 that takes down an entire batch. A small capability registry, a startup preflight, and tiered fallback keep your pipeline running across feature generations.
When a Long-Running Agent's Context Quietly Decays — Budgeting and Compaction
An agent that runs all night gets sloppier by morning. The cause is dilution from accumulated context. Here is how to treat context as a budget, measure its decay, and keep it healthy with compaction — with working code and field notes.
When a Model Disappears Without Warning: A State Machine for Retirement, Withdrawal, and Overload
A model can become unusable in hours for reasons that have nothing to do with a technical outage. This guide models three distinct flavors of 'unavailable'—retirement, withdrawal, and transient overload—as one availability state machine, with a router that keeps automated pipelines running. Working TypeScript and Python included.
Before Per-PR CI Burns Through Your Monthly Credits: A Three-Layer Guard for Claude Code GitHub Actions
From June 15, Claude Code GitHub Actions bills against non-rolling monthly credits. Run a review on every PR and you can drain the month in the first week. Here is a three-layer guard — when to run, how heavy one run can get, and making spend visible — with working workflows.