Ahsan Iqbal: writinghttps://ahsan-iqbal.dev/writing/Articles on agent harnesses and AI infrastructure.enHow a tool call works, and one turn of the loophttps://ahsan-iqbal.dev/writing/deep-agents-tool-calls-and-the-loop/https://ahsan-iqbal.dev/writing/deep-agents-tool-calls-and-the-loop/Sat, 14 Nov 2026 09:00:00 +0600Tool calling from first principles. What the model actually returns, how LangChain turns it into a graph, and the six middleware hooks every Deep Agents feature plugs into.Your first deep agent, and the prompt it really seeshttps://ahsan-iqbal.dev/writing/deep-agents-first-agent/https://ahsan-iqbal.dev/writing/deep-agents-first-agent/Fri, 13 Nov 2026 09:00:00 +0600Install Deep Agents, run a first agent, read its files back, stream subagents and pause for approval. Then every create_deep_agent() argument, and how the system prompt is assembled layer by layer.What Deep Agents is, and where it came fromhttps://ahsan-iqbal.dev/writing/deep-agents-what-it-is/https://ahsan-iqbal.dev/writing/deep-agents-what-it-is/Thu, 12 Nov 2026 09:00:00 +0600LangChain's Deep Agents is a harness, not a runtime. Where it sits in the stack, what it adds over a plain agent loop, and the four ideas it started from.