Notion Unveils AI Agents: A Game-Changer for Productivity and Task Automation

Notion launches agents for data analysis and task automation | TechCrunch

At the "Make with Notion" event on Thursday, the company announced the launch of its first AI agent. The agent will draw on all a user's notion pages and database as context, automatically generating notes and analysis for meetings, competitor evaluation reports, and feedback landing pages. The productivity platform said that the agent can create pages and databases, or update them with new data, properties, or views. Users can also trigger Notion agents from outside platforms that are linked to the service. For instance, you can ask Notion agent to create a bug tracking dashboard from various sources, including Slack, email, and Google Drive. The newly announced Agent builds on Notion AI, a pre-existing feature which could search or summarize content. But the new agent is able to tackle more complex multi-step tasks, using the powers of agentic AI. The company said that the current version of agent can perform a task that runs up to 20 minutes across hundreds of pages. Users can set up a "profile" page for the agent to instruct it to follow directions on referencing sources, style of output, and where to update tasks and final results. You'll also be able to ask the agent to "remember" key points as people use them. Those memories will be stored on the profile page, and users can edit them there. In demo videos, the company gave examples of agents that could provide feedback for landing pages and update them, create a restaurant tracker, create an analysis from meeting notes, and prepare a competition analysis report. At the moment, you have to trigger these actions manually. But Notion said that the ability to create customized agents that work on a schedule or triggers is coming soon. The company will also release a template library for agents so you can pick ready-made prompts that might suit your task. Over the last two years, Notion has released a calendar app, a Gmail client, a meeting notetaker, and an enterprise search to get information from different sources. These are features that gave the company enough contextual building blocks to create automations. Other enterprise knowledge and productivity platforms, including Salesforce, Fireflies, Read AI have launched their own agents to extract and update information.

Notion's new AI Agents will basically do your job for you

Notion has entered the agent era of its AI evolution with the launch of the Notion Agent on Thursday. The announcement forms the bulk of the Notion 3.0 roll out available to all users. The company calls the new product a "teammate and Notion super user" that "can do everything a human can do in Notion." While Notion users previously constructed pages and databases manually, now the agent builds both for them. Agents can also search for information beyond the Notion workspace and across connected tools such as Slack and the internet. The agents can form a plan and act on it, doing up to "20 minutes of autonomous work at a time across hundreds of pages at once," according to the company press release. The agents can also "remember" the user's preferred way of working, such as which content to reference and where to file it. These "memories" are stored in the user's profile that can be edited later. Each user's agent can be personalized under multiple profiles with different behaviors for now, but fully automated and customized agents will be rolled out in the future. Notion's use cases for AI agents include generating and editing email campaigns, collecting and analyzing feedback collected across multiple platforms into a single report, and turning meeting notes into emails and proposals. The company's cofounder Akshay Kothari teased the launch of agents in August and September with videos of him prompting the agent to create a tracker of the cafes he has visited and a database of movies to watch based on scores from the website Rotten Tomatoes.

Notion's 3.0 Update Wants to Help You With Project Management

Notion just launched Notion 3.0, which the company is calling the biggest update ever for its popular productivity app. This update will let Notion work with you to make better notes and give you an agent to help you create better spaces. The main new feature is the inclusion of customizable AI Agents, which can perform a wide range of tasks on your behalf. These aren't just your run-of-the-mill AI chatbots that give you simple suggestions. According to Notion co-founder Akshay Kothari, these agents can handle "real work" because they understand your workspace and can actually take action. Apparently, this AI is meant to handle your busy work. To Notion, this is like having follow-ups to write, a project plan being due, and digging through old documents and messages to find one specific detail from last week. This is the kind of stuff that Notion 3.0 is designed to handle for you, like an assistant would. According to the company, the idea behind Notion has always been about combining different tools in one place. Notion 1.0 gave us a collaborative canvas for docs and knowledge, and then Notion 2.0 added databases and integrations. Now, with 3.0, Notion has taught its AI to use all these building blocks to get real work done. Previously, Notion AI was only good for quick answers or editing a single page. But now, your Agent can do up to 20 minutes of autonomous work across hundreds of pages at once. Some examples given were the user telling their Agent to "compile customer feedback from Slack, Notion, and email into actionable insights." The Agent will then research across all your connected tools, pull out the important findings, create a structured database, and even notify you when it's done. It can also turn meeting notes into a polished proposal with updated task trackers and follow-up messages. You can also have it keep your knowledge base up-to-date. One thing I liked is that in the case of important details changing, you can just tell your Agent to spot the gaps and update everything for you. Not everyone has an office job where they do all of that, but the 3.0 release was made with personal use in mind as well. For example, a Notion co-founder uses his Agent to keep track of movies to watch and even built him a "CafeOS" to track his love of coffee. Notion has already worked with the community to create a library of examples and a video playlist to show off how the Agent handles different workflows. Personalizing an agent sounds like what Gemini Gems and custom GPTs from ChatGPT are. You give your Agent a page with specific instructions on how it should behave, and that page acts as a memory bank. So you can tell it how to handle your tasks, format its responses, and what information to use before it starts working. The more you use it, the more personalized it gets. Since you can edit these instructions anytime, you can refine how your Agent works for you. Notion didn't mention whether this would come to free users or paid subscribers. If you look at the company's plans, it shows that AI features are only available on the $20 a month Business Plan. However, you can snag a limited trial of Notion's AI features that give you 20 free responses on the free plan. Notion See at Notion Expand Collapse Source: Notion

Notion's new AI agents can research, write, and run your team's workflows

The collaborative productivity application Notion is getting a boost in AI power. Instead of simply answering questions and offering basic assistance, a built-in AI tool called Notion Agent will now be able to conduct research, draft detailed documents, and set up or update custom Notion databases on demand. "Essentially, it can do everything that humans can do inside Notion," says Notion cofounder and COO Akshay Kothari. In a demo for Fast Company, Kothari showed how Notion Agent could pull user feedback on a new product from multiple sources, generating a well-cited report with recommendations for future updates. It could also create a database of articles from a news site. The software can handle operations like assigning tasks to team members at the start of a new project or updating a company knowledge base with new information.