AI's hunger for context is making search a critical but expensive component. As illustrated by Turbo Puffer's origin, a single recommendation feature using vector embeddings can cost tens of thousands per month, forcing companies to find cheaper solutions to make AI features economically viable at scale.

Unlike humans who type 2-3 words, LLMs generate long, sentence-like queries (e.g., eight words or more) to gather comprehensive context. This shift in user behavior from human to AI requires search engines to be optimized for these detailed, descriptive inputs.

The new multi-agent architecture in Opus 4.6, while powerful, dramatically increases token consumption. Each agent runs its own process, multiplying token usage for a single prompt. This is a savvy business strategy, as the model's most advanced feature is also its most lucrative for Anthropic.

AI agents, unlike humans, need complete and exhaustive information (thousands of results) and use complex, controllable queries. A search engine built for human keyword simplicity and limited results will fail to serve them effectively.

The growth of LLM context windows has stalled not primarily due to technical barriers, but because multi-million token requests can cost users several dollars per query, leading to low demand. The industry is shifting focus to "smart context" techniques like compaction and retrieval to provide relevant information without the prohibitive cost of massive context.

Don't pass the full, token-heavy output of every tool call back into an agent's message history. Instead, save the raw data to an external system (like a file system or agent state) and only provide the agent with a summary or pointer.

When an AI assistant performs a task like web research, it consumes a large amount of context. Instructing it to use a sub-agent offloads this work, keeping the main chat session lean and focused by only returning the final result, dramatically conserving your context window.

Unlike chatbots that rely solely on their training data, Google's AI acts as a live researcher. For a single user query, the model executes a 'query fanout'—running multiple, targeted background searches to gather, synthesize, and cite fresh information from across the web in real-time.

The simple "tool calling in a loop" model for agents is deceptive. Without managing context, token-heavy tool calls quickly accumulate, leading to high costs ($1-2 per run), hitting context limits, and performance degradation known as "context rot."