Hey Nate, hey awesome other guys, I love what you do! 2 months or so I switched over from make, where I coded self-improving, self-extending, user-centric multi-step-bots, but this took like forever and hundreds of modules. With n8n this is just so much easier. What I try to create since a while is a similar assistant to your 2.0, but with Microsoft instead of Gmail. It's getting better after I found out that credentials were taken wrongly first, but now I face other issues. What is core here? Even within email, there are so many possible tasks I want the assistant all to be able to combine effectively and efficiently. Commands like "can you please summarize the communication with xyz", "are there important mails in my mailbox", "can you please draft a response to xyz including abc", etc. should be doable. Initially with Telegram, later I'd love to install yor 11Labs integration <3 The above I programmed with make like: 1) understand the final goal of my task, 2) adapt it based on the knowledge about me (vector or knowledge database), 3) search API for final step in self-created API-overview, 4) feedback if there is no final API / create a "project" if there is one, 5) iteratively approach the goal with the bvest fitting API in the list to get closer to the goal, 6) if there is no API helping further: 6a try to reserch API-calls, try one out and integrate it in the API list if it works, or 6b ask the user if there is none. 7) asynchron at nights: review missing skills based on the user demands and try to find some with "more complex methods" (such as combining purposely created hallucinations with vector based hallucination on API-vactor base only, response/feedback of user, trying ou and proactively using disclosures. You can imagine what a code monster this was at n8n, considering I built this all for several systems, incl. lots of MS integration such as Outlook, Tasks, Onedrive, but also other services I use. With n8n I find myself having a harder time. Of course, the "fromAI" function is so massively helpful, bevor this was a nightmare (since I tried to do all this without any additional AI usage to have faster responses), also the AI agent modules make it a lot easier. But when I e.g. try to adapt your 2.0 assistant and need the agent to structure its approach more, I get errors.

Subject: Enhanced Prompting Flow for Personal Assistant with @AI Integration Hi, I watched your video on Personal Assistant, and I’m excited about the new one on prompting—definitely going to check it out! I had a few thoughts regarding the integration of @AI and best practices for prompting within the Personal Assistant flow. Would you be able to share the updated flow with @AI included and offer insights on refining prompting strategies? Here are a few specific ideas I thought might enhance functionality: 1. **Email Responses**: Tailor responses to mirror the sender's tone, automatically setting the appropriate salutation and greeting. Integrating a vector database for contextual analysis could pull in relevant information from prior emails to enrich responses. 2. **Calendar Events**: Using a vector database could also help provide background when setting up agenda items. Once a user ID is retrieved, contacts (from Gmail or another source) could be queried to find additional context about attendees or previous interactions, allowing for a more contextually rich prompt. 3. **Personal Data Trust**: A major added value would be allowing users to trust the assistant with specific, personal information tied to their ID. For example, users could add licenses, passwords, or other private information, enabling the assistant to remember and provide context-based responses, much like the personalized responses we see with ChatGPT’s latest updates. This could vastly improve prompt relevance and response accuracy. 4. **Grounding the AI (Similar to Microsoft Copilot)**: Before responding to any prompt, the assistant could consult a vector database for user-specific details (e.g., Jan is a male of [age], tech-savvy, etc.). By grounding each interaction in the user’s data, responses can be much more precise and personalized. Would love to hear your thoughts on these ideas and any recommendations you have for refining the prompting flow! Kind regards, Jan

The Ultimate n8n Starter Kit is a complete roadmap for learning n8n, guiding you from basic workflow automation to advanced AI integrations. It breaks down key concepts like nodes, data transformations, and third-party integrations, while providing practical examples and extensive resources to answer your questions as your skills progress. Whether you're just starting or looking to level up, this kit equips you to build powerful automations with confidence.

Hey all! My buddy Cole Medin (you probably know him from YouTube) is hosting an AI Agent Hackathon and the registration just opened! You can find out more information and register here. This is a super cool event that takes place throughout the month of January, so get in there and start building!