Anthropic gives Claude agents live web search through its API
Anthropic released API web search for Claude 3.7 Sonnet and Claude 3.5 models, allowing deployed agents to decide when to search, retrieve current information and return cited answers.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
Model-directed access to current web information expands agent reach and task reliability while adding an external prompt-injection and misuse surface at API scale.
Assessment history
-
R1
Toward 38 · confidence 93
New web-connected agent deployment distinct from the underlying model releases.
12 Aug 2026
Share this page
-
DoomBench assesses “Anthropic gives Claude agents live web search through its API” as evidence moving toward doom, with magnitude 38 and confidence 93 out of 100 in the autonomy and agency category.
-
The DoomBench assessment of “Anthropic gives Claude agents live web search through its API” is based on reporting from Anthropic and records the editorial rationale, source quality, attribution, and revision history.
-
DoomBench summarizes “Anthropic gives Claude agents live web search through its API” as follows: Anthropic released API web search for Claude 3.7 Sonnet and Claude 3.5 models, allowing deployed agents to decide when to search, retrieve...
https://www.doombench.com/news/anthropic-gives-claude-agents-live-web-search-through-its-api-2025-05-07