I ran into a couple of issues with n8n - maybe someone here can help .. 1) when I set a trigger from google sheet for a row being updated - how can I get the previous value of the fields in the row ? 2) is there a way to connect MCPs to AI agent nodes ? For example- - I want to use Figma Mcp with an AI agent node to generate user stories automatically..

Our agency is currently taking off fast, and we need to get some dev help on ASAP. We have projects that are closed and ready to be taken on right away, and a bunch more coming in as we speak. Us: https://atomautomation.ai https://www.linkedin.com/in/joel-mcwilliam-119a5231b/ https://www.linkedin.com/in/johannes-laukart/ # Opportunity/Structure: - Project based at first ($6-15k projects rn, trending upwards fast), negotiable rev share - Likely transition into full-time if you’re good. Happy to pay a premium for A players. - We’re growing very fast, so there’s opportunity to take on more responsibilities as we expand the team. - We’re also likely going to build out a software platform over time, as we grow into the biggest AI company in the space; equity talk is not off the table. We’re both young (20 and 23), hungry guys, and building a lean and mean team to scale to 6mil usd next year together. Then we look onwards to the big Bs and total market domination. We’ve made great connections in the space that are going to pay off massively and are currently in talks with the executive team of the biggest licensing company in the space in Australia, executives of a 500 staff firm, and more. We’re extremely hyped for what’s to come and now need some killers to join us on the journey. # Project Details The solutions we build are mainly around handling meeting transcripts, generating, and extracting from compliance documents (Fact Finds, File Notes, Records of Advice, etc) and integrating with the client’s CRM and file storage (usually Sharepoint) to pull context and push updates, creating action items, etc. Importantly, our clients are handling sensitive financial and personal data, so you’ll be working with Australian financial data security/compliance requirements. # Requirements - be sharp, HUNGRY, move FAST and hate mediocrity. - can work independently to finish projects from design to deployment - be on top of production best practices for LLM projects, and using AI in your own workflows. - Experienced working in Azure (Functions, Logic Apps is good) - Python, JS/TS

I’m looking to harness the collective smarts of our Data Alchemy community. Who is interested in taking on the challenge of evolving a Large Language Model to process queries with the insight and depth of an expert? ## The problem with current LLMs The more you integrate LLMs in your workflows, the clearer their shortcomings become. Let’s say you request a business plan for “an AI-driven e-commerce site”. It will jump straight into a carbon-copy template business buzzwords – Problem Definition, Unique Value Proposition, Early Adopters – without context or insights. Why doesn’t the LLM pause and wonder: what does “AI-driven” mean to you? What stage of your business story are you in? It's the nuance, the back-and-forth of understanding that's missing—direct prompts often lead to a one-way street of uninspired affirmations. In my talks with business people, a recurring theme is their need for an LLM that doesn’t churn out cookie-cutter answers, but crafts them with the considered questions of an expert analyst. Wouldn’t it be great if we were the ones to offer more useful LLMs to our customers? ## A new mental model In May of this year, academics proposed a mental model where the AI imagines a team of experts discussing the problem, each representing a different point of view. They propose their ideas step by step to the group, up until the point that they realize they are wrong, which is when they leave: “3 experts are discussing the question with a panel discussion, trying to solve it step by step, and make sure the result is correct and avoid penalty.” What is it about this prompt that triggers AIs into more productive thinking patterns? This 'panel' construct reshapes the pattern, emphasizing critical engagement over rote response. Instead of locking onto the most expected answer, the AI is coaxed into a more layered and intricate mode of thinking. But does it do so structurally, for the rest of the conversation?

https://github.com/NirDiamant/Prompt_Engineering

I see that hallucination is on of the major issues that everybody comes across using Gen AI. A human oversight is needed to no befall this but are there ways to mitigate this?