Google Colab, a Google cloud tool for coding, data science and AI, gets a new “AI agent AI” tool, Agent Data Science Agent to help COLAB users quickly clean data, visualize trends and get information about their data files.
For the first time announced at the Google Developer Conference at the beginning of last year, the data agent was originally launched as a separate project. However, Google decided to integrate it into Colar to help users access the agent directly from the co -founder’s notebook, said Kathy Korevec, Google Labs, in an interview.
Data Science Agent is available free of charge from this week in what -coil, although COLAB limits free users to relatively low love for calculation. Google offers a number of COLAB paid plans with higher limits starting at $ 9.99.
Data Science Agent is the primary beloved with data scientists and AI use boxes, but the agent can also help find the API anomalies, analyze customer data and write SQL code. All users have to make their data and ask the agent on the question.
Data Science Agent uses the AI Google Gemini 2.0 AI family on the backend, along with “thinking tools” to help with engineering and data cleaning. Korevec said TechCrunch that Google is constantly improving agents and using techniques included learning amplification and integrating user design to increase science agent.
Data Science Agent currently supports only CSV, JSON or .txt files below 1 GB. It can analyze about 120,000 tokens in one challenge that will cost more than 480,000 words.
Korevec said that data about data science can come to other devotic applications and services in the future.
“We scratch the surface of what people can do here,” she said. “Because it’s an agent, we can integrate it into many different tools and I don’t need it to force people who are ashamed of the code to go to Corab.”