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.
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.
Managed Agents Adds Scheduled Deploys, a Vault, and Session Webhooks — Deciding What Leaves My Cron Setup
Scheduled deploys, vault credentials, and session-thread webhooks just landed in Claude Managed Agents. How I triaged my self-hosted cron jobs: what moves, what stays, and why idempotency decides.
An Anti-Corruption Layer for Claude API Models — Keeping Generation Changes Out of Your Business Logic
Hard-coding model strings into business logic means production breaks quietly every time a generation is retired. Here is an anti-corruption layer that separates logical roles from physical model IDs, with working TypeScript and Python, migration costs, and the judgment calls behind it.
Diagnosing invalid_request_error When You Pass an Image URL to the Claude API
When the Claude API rejects an image you passed via `source.type: url`, the root cause almost always lives in one of four buckets: scheme, MIME, size, or reachability. Here is the diagnostic order I use in production.
Splitting Claude API prompt cache into 5m and 1h tiers — separate TTLs cut cost and stabilize ops
Anthropic's cache_control supports two TTLs: 5 minutes and 1 hour. Splitting them into a two-tier layout — 1h for static system/tools, 5m for variable few-shot — meaningfully changed both my costs and my on-call life. Here's the design with the numbers I observed.
Designing Graceful Degradation for the Claude API — A Four-Tier Fallback Architecture That Keeps AI Features Quietly Alive
Once Claude API features hit real production traffic, model-level fallback alone stops being enough. This article walks through an SLI-driven four-tier degradation design, with Python and TypeScript code, SLO burn-rate alerting, and the operational trade-offs an indie developer actually runs into.
Absorbing the Claude API "Tool Result Submitted" Error in a Retry Layer: A Small Conversation-History Repair
How I absorbed the Claude API "Tool result could not be submitted because the previous turn was not a tool use" error inside a small retry layer, with the diagnosis order I followed after it hit a production batch.
Adding Priority and Fairness to a Claude API Job Queue — Backpressure Patterns from a 50M-Download Indie App
A practical design for adding three-tier priority queues and Deficit Round Robin fairness to a Claude API worker. Drawn from running review-automation pipelines across an indie app catalog with 50M cumulative downloads, with full Python code and production metrics from a year of operation.
Allocating the 200K Context Window in Claude API — Budgeting System, Tools, Memory, and History in Production
Treat Claude API's 200K context as a budget rather than an open shelf. A TypeScript-backed allocation architecture that carves system, tools, memory, history, and headroom into explicit envelopes — built and tuned in a wallpaper app earning real ad revenue.
Forecasting Claude API token costs with ±10% accuracy from the first three days
A practical EWMA + seasonality decomposition model that forecasts month-end Claude API costs from only the first three days of token usage, with three-tier automated guardrails for prompt caching, model routing, and rate limiting.
What metadata.user_id in the Claude API Is Actually For — Designing the Abuse-Detection vs. Privacy Trade-off
The metadata.user_id field in the Messages API exists to sharpen abuse detection, but sending raw email addresses creates a privacy problem. Here is the HMAC-based stable pseudo-ID pattern I use, plus a clear set of rules for when to send it and when not to.