Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: Anthropic
Porting a Chat Loop From OpenAI to Claude in Python: One Page of Changes
Move a stateless message loop to Anthropic's Messages API: the top-level system parameter, required max_tokens, content blocks and strict role alternation.
4 min readStructured System Prompts for Rust AI Agents: Layers, Caching, Drift Checks
Build a layered system prompt for a Rust agent: identity, instructions, output rules, examples and fresh context, plus a cache boundary and a fingerprint for CI.
12 min readManaged Agents Compared: Anthropic, LangGraph and Google ADK
Who runs the sandbox, credentials and traces? A comparison of Anthropic Managed Agents, LangGraph and Google ADK with pricing, failure modes and a quick decision guide.
19 min readCut Repeated Prompt Costs by 90% With One Line of Prompt Caching
Turn on automatic prompt caching with a single field, verify hits in the usage block, and avoid the prefix mistakes and minimum-length traps that silently erase savings.
4 min readPrompt Engineering and Structured Output in .NET: OpenAI, Azure, Anthropic, Gemini
OpenAI, Azure OpenAI, Anthropic or Gemini for .NET: residency, SDKs, pricing, structured output with JSON Schema, prompt engineering and a thin IChatClient.
11 min readPhlox-GW: Open-Source LLM Gateway with Budgets, Guardrails, and HA
Phlox-GW is an open-source LLM gateway you self-host: budgets and chargebacks, rate limits, PII guardrails, audit logs, OpenAI and Anthropic endpoints, HA.
11 min readStatistical Text Watermarks vs C2PA Credentials in Claude Output
Learn how Claude's SynthID-based text watermark and C2PA file credentials work, what detectors can prove, and how to judge any tool claiming to remove them.
10 min readWhat AI Safety Warnings From Ex-Anthropic Researchers Mean for Developers
This article breaks down why researcher warnings about AI risk matter for everyday developers, and how agent autonomy and alignment gaps should shape practical safety habits.
16 min readWhy AI Access, Not Capability, Is Your Real Dependency Risk
This article examines recent export-control incidents with Claude and GPT-5.6 to argue that access to AI models is a volatile variable independent of raw capability.
11 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.