Doubao Search opens to developers with API and MCP hooks for agents
量子位 · wechat · 2026-07-28
Doubao Search is being spun out of the Doubao app and exposed to enterprises and developers through APIs, MCP, and Skills. The article argues that for agents, search is no longer just about finding links: it has to return structured, usable fields such as source type, authority level, publication time, summaries, and Markdown excerpts.
The post walks through several agent tests: recent Kimi K3 open-weight news, EV industry research, and AI coding tool updates. In each case, the agent could use the search output directly to verify facts, judge source reliability, and extract specific conclusions without re-reading full web pages. The write-up also cites benchmark lifts on SimpleQA, FreshQA, BrowseComp-ZH, and Xbench-2505, positioning search as a core layer in agent workflows.
More from coding & agent
- Why company AI agents go stale: adoption needs in-house knowledge, not just better agents — EdenEmarco177 · 2026-10-16
- Cheng Lou open-sources Handwired: hand-written weights turn code into training-free neural nets — dotey · 2026-10-16
- Building a portable context vault in Notion so every AI agent knows you from day one — ivanhzhao · 2026-10-16
- Lovable apps can now talk to customers on WhatsApp with inbox, reminders and templates — AlexandrePesant · 2026-10-16
- FDE-Gym benchmark: best agent fully solves only 14 of 95 real customer-delivery tasks — dair_ai · 2026-10-16
- Deep Research API showdown: OpenAI, Perplexity, Parallel, Tavily, Gemini, Valyu compared — bar_raiser333 · 2026-10-16