SandRise
Ep 640 Research Paper 1:10 w/ Pippa & Tyler

You.com: Web Search APIs for AI Agents

The hosts discuss You.com's web search APIs for AI agents, focusing on its performance, features, and potential applications.

AgentsDev ToolsYou ComOpenAIDuckduckgoRetrieval Augmented GenerationTool Use And Function CallingAgentic LoopsContext WindowResearch Paper
Read the source → Plain-text transcript →
Embed this episode

Paste this on any site — the player is a self-contained iframe with no cookies or trackers. 

<iframe src="https://sandrise.io/exploring-next/embed/640"
  width="100%" height="180" style="max-width:640px;border:0;border-radius:12px;overflow:hidden"
  title="Exploring Next — Episode 640 audio player"
  loading="lazy" allow="autoplay" referrerpolicy="strict-origin-when-cross-origin"></iframe>
Embed & API docs →
Script Llama 4 Scout Voice Inworld TTS 2

Transcript

Tyler You.com's central claim is that their web search APIs can provide structured, LLM-ready results at 300ms p99 latency, which is 2X faster than competitors. They serve 10M+ daily queries at 99.99% uptime.

Pippa That's impressive. The Search API returns structured JSON that's ready to feed directly into LLM context windows. It also supports livecrawl for full page content inline with results.

Tyler The Research API is particularly compelling because it handles multi-step reasoning that would otherwise require agents to orchestrate multiple search-read-synthesize loops themselves. It's #1 on the DeepSearchQA benchmark.

Pippa I'm intrigued by the potential applications. For instance, enabling AI agents to search for current information, verify facts, and stay up to date. It could also augment retrieval pipelines with live web results.

Tyler The company claims to be SOC2 certified with zero data retention and DPA-ready compliance. It's trusted by major companies like DuckDuckGo, Amazon, and OpenAI.