Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More

Memberships

Data and Ai Automations

283 members • Free

14 contributions to Data and Ai Automations
December Challenge - Get Your First n8n Customer (day 5)
It's time to lock in & land your first Customer on Upwork 2026 is coming soon & I want YOU to have a big win to end off the year. So here is the goal, I want 3 people in this group to get their first n8n/data/ai customers. Everyday we post a comment in this post the number of jobs applied to, any interviews, and things you learn along the way. While I have taken a break from Upwork, I will also be applying as well... No excuses. @Alex Rodriguez @Rudolf Van Loggerenberg @Danny Glosser The Challenge will run through 12/20/25, Need some help with how to navigate Upwork we have a mini course on YouTube: https://www.youtube.com/watch?v=SGQ7mdt_EeM&list=PLcQVY5V2UY4L8_RvrhvgJsjnClE0BxxML
0 likes • 1d
@David Kyle Focus on one or the other. Are you US based? That might change the focus
0 likes • 18h
Day 4. Two applications and one response. Okay deal probably 1k a week.
RAG for accurate retrieval?
What is the best practice for setting up your data to make sure it’s embedded properly for RAG vector so that the AI agent can really retrieve it correctly and accurately? I see a lot of YouTube videos with guys doing this, but it’s obviously for show over simplified, and the quality of retrieval has to be poor or average at best. What are the real best practices in terms of doing this? For example, should you build your knowledge source in a Google sheet that’s one for one matching the vector table structure in Supabase? With metadata for …? Or Use markdown in doc? Predetermine chunk size and edit knowledge source to match desired chunk size instead of relying on “random” chunking? How do you set your raw data up to get the most accurate retrieval from AI agent? (Let’s assume n8n Q&A AI chat agent with Supabase vector and 1,000 rows of unique data from online course material.) Thanks!!
0 likes • 5d
I would focus more on your retrieval recall than anything else. If you can't retrieve the correct information, you're never going to get the correct answer. For your different questions on format and steps: Every use case is going to be a bit different, and you'll spend most of your time optimizing those variables (data structure, metadata quality, chunk size). I'd really focus on being able to evaluate quality as quickly as possible so you can iterate as fast as possible
0 likes • 3d
@Timothy Roberts are you expecting it to just "work" out of the box? Entire companies are built around designing these for different workflows. There is no one stop solution for every RAG pipeline because the data structure changes, queries change, chunk sizes change etc. Its easier to design the system you believe is best and put evaluation tooling in place so you can test it and iterate. I'd start simple and iterate based on results and issues like: - My retrieval recall is low - The context has the correct info but answers are wrong - My metadata does not help
Upwork is as competitive as ever
I applied to a few jobs today for the first time in probably 5 months or so. Upwork is the most competitive its ever been. I started applying in 2021 and it was easy and cheap to get roles. Now there are these non-negotiables if you want good jobs: - Boosting proposals to the top. Its expensive, but you pay to play. If you aren't willing to spend money to apply, you are going to get lost - Exact case studies or whitepapers for what the customer is looking for - 100% job success score, good earnings, good reviews - Volume of distribution - Fast time to apply
0 likes • 4d
that was quick
November Group MVPs
Let's celebrate our first full month of having a Skool Group! The group is ranked #284 in Tech and I think we can crack the top 200 relatively soon! This month we also hosted our first ever group lock in/work calls. Big congrats to the following 5 members for being at the top of the leaderboards 1. @Ryan Steggerda 2. @Alfred Alonso 3. @Greg Drysdale 4. @Rudolf Van Loggerenberg 5. @Alex Rodriguez I want to reward the top contributors each month, Ryan won a free 1:1 call this week where we will discuss Ai, Python, and more. Alfred landed a freelance gig as well just by taking action and being on a call. In December I want to help @Rudolf Van Loggerenberg & @Alex Rodriguez land their first Paying n8n customers. The challenge this month will be posted later today. Let's crush December. Anything you guys want to see in the server? Post it below
0 likes • 4d
Im so deep in the grind I read MVP as "Minimum Viable Product" and was confused.
AI Automation and Data Science Tools/Mentality
With how fast a tools are evolving and changing, such as the intrduction of agents, it creates a necessity in changing ones mindset. Instead of trying to plan out each step individualy, manually learning/looking up code syntax, and other tasks. It is better to let agents and LLM's so this for you to speed up productivity and skill. This does not mean you can ignore hard skills, but allows you to better allocate time and energy. Comment below some tips and personal stories in how you have slowly changed your mindset and work style to fit these changes!
1 like • 5d
I think its just so new that most people don't have a concrete flow for these things yet. You still need the skills related to the task. I see a million pull requests a week that have vibe coded junk that affects other parts of the codebase that it shouldn't because the developer does not have the skills (or is lazy) to validate the changes and the affects those changes have. The coding tools write code incredibly focused on solving your problem, with minimum considerations for other parts of the codebase uses those items. You see it mostly in complex or asynchronous codebases, as those require deeper knowledge about the way the system is used.
1-10 of 14
Matt Payne
3
44points to level up
@matt-payne-3363
Group Owner | Ai expert here to help you get more per hour

Active 18h ago
Joined Nov 10, 2025
Powered by