hi guys, I want to create a solution that automate this process: - take every LLM output of a client for 1-4 different queries - compare the previous vs last output semantically to see if changed the output (especially if there's no mention about legal cases) - send notification to the client only if the output chaged I've already automatized the gathering of the data which go into a google sheet (one sheet fot gemini and one for chatgpt) the problem is how compare the texts. I'm trying with the AI agent with the google sheets as tools but it retrieves the wrong dates and only compare outputs randomly even if i described in detail in the prompts how it should compare. I don't know how to get reliable comparisons. Should I store the output in a vector DB to get more consistent results and if so how? Should I use an ai agent or create an AI workflow? How would you approach it? ps: it would be cool to highlight significant differences too

I have an if logic that basically give me an http request if asked for, if not it gives me an empty string. I want then in the google sheet column assigned to receive this data to have the http request if requested or empty value if not. I tried with merge but i can't seem to let it work out. How would you do it??

I'm trying to get 4 different queries' response from gpt-40 and append them on a google sheet, with each output in a different assigned column (but same row). The problem is that: when I run the workflow it's unreliable. some times only the first http request goes, sometimes two, but never all 4 together in order. even if I run them one by one manually, I'm still not able to get each http request output to their assigned column. I only get the same output repeated 2,3,4 times across the columns. How can i solve this problem??

I’m trying to get new model response which has the the web search tool method POST https://api.openai.com/v1/responses I’ve set up the header auth with: Name Authorization Value Bearer my-API but it keep on giving me error of authentication: Error code 401 Full message { "error": { "message": "Missing bearer or basic authentication in header", "type": "invalid_request_error", "param": null, "code": null } } these are my body parameters: { "model": "gpt-4o", "tools": [ { "type": "web_search_preview", "user_location": { "type": "approximate", "country": "IT" } } ], "input": "chi è {{ $json.chatInput }}?" } and this are my headers: [ { "name": "Content-Type", "value": "application/json" } ] Do you have some suggestion on how to fix it? Ps: I can retrieve the response using python and openAI library so the problem is on n8n part

For a deeper discussion on building AI Agents at scale, let's chat here. Over the past six months, I’ve been building AI agents, automating workflows, and running an AI automation agency—all without a traditional programming background. In this video, I break down the biggest lessons I’ve learned, the mistakes I made, and what I’d do differently if I were starting over today. Whether you're a beginner looking to get into AI automation or a business owner curious about leveraging AI agents, this video will give you a real-world perspective on what it takes.