<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Iterosys Engineering Blog</title><description>Production engineering notes from Iterosys — LLM orchestration, billing systems, async pipelines, Bangla NLP, and the architecture behind real AI products.</description><link>https://iterosys.com/</link><language>en-us</language><item><title>LangGraph credit metering: how to charge users correctly for AI tool usage</title><link>https://iterosys.com/blog/langgraph-credit-metering/</link><guid isPermaLink="true">https://iterosys.com/blog/langgraph-credit-metering/</guid><description>Billing AI agents at the request boundary overcharges users for failures and can&apos;t price a multi-tool turn. Here&apos;s how to meter inside each LangGraph ToolNode, with three strategies keyed to each tool&apos;s cost and shape.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate><category>LangGraph</category><category>AI/ML Engineering</category><category>Architecture</category><author>Iterosys Engineering</author></item></channel></rss>