\n<\/p>\n
For example, let\u2019s say you\u2019re planning an offsite and get an email from a team member asking for the hotel information so they can book a room. Ask Gemini in Gmail to look it up from a Google Doc that contains all the offsite details with: \u201cwhat is the hotel name and sales manager email listed in @Company Offsite 2024.\u201d Then, you can easily insert the information into your email reply.<\/p>\n
If at first you don\u2019t succeed, try, try again! Refine your prompt and experiment with different approaches, including using synonyms or different keywords, adjusting the level of detail and specificity and testing different prompt lengths. (Based on the team\u2019s research, the most successful prompts average around 21 words, yet people\u2019s initial attempts are significantly shorter \u2014 usually fewer than nine words.) Plus, don\u2019t forget you can ask follow-up questions.<\/p>\n
Vishnu recommends experimenting with using different personas, too. For example, when you\u2019re writing a prompt about training someone, you may want to ask Gemini to act as a colleague and then compare the results against asking Gemini to act as a teacher.<\/p>\n
\u201cWhen you\u2019re happy with the results, take note of what\u2019s working,\u201d Vishnu says. \u201cTry reusing some of that language with future prompts.\u201d<\/p>\n
When development began on Gemini for Workspace tools, the team started a group chat where they shared examples of their prompts and Gemini\u2019s responses with each other.<\/p>\n
\u201cThe chat provided insights into the types of tasks people are using gen AI for, highlighting both its capabilities and limitations,\u201d Vishnu says. \u201cGooglers found success with practical tasks like summarizing itineraries and extracting information from documents.\u201d As we’ve continued to upgrade our models, we’ve also been able to address previous areas of feedback, like how Gemini can contextualize information across multiple sources.<\/p>\n
These are the kinds of insights the team is still gathering, both from users inside Google and from trusted testers. It all helps. As Vishnu puts it, “The more input we get, the more helpful we can make our products.”<\/p>\n<\/div>\n