Claude Agent SDK Credit Pool: A Plain Guide to the June 15 Change
On June 15 Anthropic split Agent SDK billing into a separate monthly pool. Plain guide to what changed, what breaks, and how to keep your tools running.
Topic
Building production AI agents with the Claude Agent SDK in Python and TypeScript. Articles in this section cover tool use, memory, subagents, prompt caching, batch processing, the credit pool billing model, cost tracking, and the differences between the Agent SDK, LangChain, and the Vercel AI SDK. The goal of each guide is to get you from a working hello-world agent to a service you can ship and bill for, without skipping the boring parts (auth, retries, observability, evals).
On June 15 Anthropic split Agent SDK billing into a separate monthly pool. Plain guide to what changed, what breaks, and how to keep your tools running.
How to measure what your Claude Agent SDK workload really costs before the June 15, 2026 credit change, with code, caveats, and a sizing decision.
Microsoft released RAMPART on May 20, 2026, a pytest-native safety testing framework for AI agents. Here is how to apply it to your Claude agents today.
A practical side by side look at the Claude Agent SDK and Vercel AI SDK 6 for production AI agents in 2026, with code, defaults, and a clear pick.
Build your first Claude Managed Agent step by step: agent, environment, session, streaming events, rate limits, and the production gotchas no one mentions.
What Claude Mythos is, who got access through Project Glasswing, the zero-days it has already found, and what its arrival means for security teams in 2026.
A calm side by side look at the Claude Agent SDK and LangChain for production AI agents, written by someone who has shipped both.
Learn what agentic RAG is, how it differs from traditional RAG, and how to build one with the Claude Agent SDK and pgvector. Step by step, with full code.
A side by side look at Claude Opus 4.7 and GPT-5 in 2026, with notes on coding, reasoning, long context, vision, agent work, speed, and price.