I tested @OpenAI's GPT-6 Astra with @ExaAILabs, @KeenableAI, @p0, @ValyuOfficial and its built-in web search on 26 LiveBrowseComp questions. Exa matched Astra’s built-in web search on accuracy (11/26) at roughly 1/3 the estimated cost. It also finished faster. Keenable finished 1 behind (10/26). Native search made 513 tool calls versus Exa’s 650, but logged 56.5M input tokens versus 12.1M, including cached tokens. After accounting for cache pricing and search charges, estimated cost per question was $3.84 with native search versus $1.26 with Exa. results + methodology:

Before Keenable SELECT, this would have been somebody’s PhD-level sentiment analysis. Today, after our Hacker News announcement, several people sent me this link from the thread. @paulg, they noticed a red trend:

Many of our customers use agents with web search to build and enrich internal structured databases. And then run SQL to build reports and do analytics over them. We decided to simplify the process and enable agents to SELECT over the whole Internet as it is a structured database. Your Claude, ChatGPT, and any agent can access it today. Try Keenable SELECT and share your thoughts. It is free for now.

1. Pandas are cool. 2. And Lightpandas are extremely cool for your agents. We are the early users. This is the browser how it should work for AI era. And this is cool to be the default web search for @lightpanda_io agents.

Introducing V4 Styles! Recraft already nails one good image. But V4 Styles is built for scaling. Give it one reference image and it holds that style exactly, across everything you generate next. The link's in the comments ↓

Today we are announcing @KeenableAI, an AI-native index of the best human knowledge we have, starting with the open web. AI seems to know just about everything until you ask it about something you know deeply. The answer isn’t wrong, but it's just very average. We started Keenable to fix this problem: every model and every agent should be able to query, reason over, and continuously learn from the living web. Backed by a $26M Seed from @Accel and @conviction. Built by the team that took on Google at Yandex Search, with researchers and engineers from Amazon AGI, X, and Perplexity. The Web Search API and Web Query Language for AI are live now. Together they make the web queryable at AI scale. Both are free until end of September. Seven days of benchmarks, stories, and launches ahead. Let your agents search.