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: Claude
Why AI Agents Burn Budget Without Finishing, and How to Stop Them
Learn why tool-calling agents keep looping when "done" is undefined, where the token spend goes, and which stop conditions beat simply raising step or budget caps.
1533 wordsRead articleCalling Claude, GPT and Gemini Through OpenAI-Compatible Endpoints
See what the Anthropic and Gemini OpenAI-compatible layers support, where they silently drop features, and when routing all three through one gateway makes sense.
1812 wordsRead article30 Practical Claude Prompting Techniques from Real Daily Use
A field-tested breakdown of 30 Claude prompting techniques, organized by what they actually accomplish, from clear instructions to full prompt systems.
2982 wordsRead articleFugu Ultra: How an AI Orchestrator Model Challenges GPT and Claude
Explains how Sakana AI's Fugu Ultra v2 routes tasks across specialist models instead of one giant LLM, and how it stacks up on benchmarks, pricing, and transparency.
2320 wordsRead articleComparing Frontier AI Agents: Astra, Flash, Fable, and Mythos
A breakdown of how the latest GPT, Gemini, and Claude model releases perform on real agentic tasks like coding, browsing, and tool use, not just benchmarks.
2160 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.