Google upgrades Colab with an AI agent tool

Google’s cloud-based notebook equipment for coding, data science and AI is gaining a new “AI agent” equipment, data science agent, so that the collab users help to clear data, visualize trends and get insight in their uploaded data sets.

Was first announced at Google’s I/O developer conference earlier last year, the Data Science Agent was initially launched as it Standelone projectThe However, Google has decided to integrate it with Kalab to help you access the agent directly from a collab notebook, Kathy Korevek, director of Google Labs in an interview.

Data Science Agent is available for free in Kolab like this week, although the Kalab free users limit the relatively low amounts of computing. Google provides a variety of paid collab plans with a higher limit, starting from $ 9.99.

Data Science Agent is basically the use of data scientists and AIs, but the agent can help find the inconsistencies of API, analyze customer data and write SQL code. All users have to do is upload their data and ask the agent a question.

Data Science Agent Features use Google’s Gemi 2.0 AI Model Family on the back -end with “logic” equipment to help engineering and data cleaning work. Korevec told TechCrunch that Google was constantly improving the agent and used strategies with user advice as well as consulting user to enhance the effectiveness of data science agent.

Data Science Agent currently supports only 1GB size CSV, JSN, or .txt files. It can analyze about 120,000 tokens in a single prompt, which works at about 480,000 words.

Koreevec said that the data science agent may come to the Additional Div-Focused Google Apps and Services in the future.

“We have to tease the surface of what we can do here,” he said. “Since this is an agent, we can integrate it with a single bunch of different tools and I certainly don’t want to force shy people to see the code to go to Kolab.”