LLM Agents Interview Questions, issue 7, Mar 1, 2026
The DOM Context Trap
Senior AI Engineer interview at OpenAI, and the interviewer asks:
“You’ve built a web navigation agent using the full accessibility tree (DOM) to maximize contextual awareness. But latency is spiking, and it’s completely failing on complex web apps. What is the hidden architectural bottleneck here, and why is pure-vision grounding the superior production choice?”
Don’t say: “The DOM is too long for the LLM’s context window, so we just need to use a better parsing script or apply RAG to chunk the HTML.”
Feeding the full accessibility tree into an LLM creates a state-space explosion where invisible artifacts dominate attention and latency scales with structural noise, not task complexity.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.