Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
12 contributions to AI Automation Society
Building a desk dashboard with an AI tutor, not an AI autocomplete
I've been building a small dashboard on a Raspberry Pi 4B that sits on my desk as a second screen, currently showing local weather (plus a meta touch: it tracks my own Claude Code usage too). Flask serves the page, and two collectors run independently on systemd timers. The app never touches an external API directly, it just reads whatever the collectors last wrote, so a dropped Wi-Fi connection means stale data instead of a blank screen. Before writing any code, I used the WAT framework from our earlier lessons to build a claude.md file for the project: environment, tools, architecture, and a running list of gotchas I'd already hit once. That shared context is what made the AI collaboration work. What helped wasn't Claude writing code for me, it was Claude explaining why one architecture beats another before I touched a line, like why timestamps belong in UTC or why paths need to be anchored to the script instead of relative. Small steps, an explanation before each change, verify it actually worked. Closer to a patient TA than a code generator. Discussion question: Weather's just the start. Calendar, unread email count, Pi health stats, and stock positions are all on the list next. If you were adding a data source to this dashboard, what would you pick, and what's one design decision (like the "stale over blank" tradeoff) you'd have to make for it to fail gracefully?
2 likes • Aug 31
@Gaurav Saxena solid suggestion.
1 like • Aug 31
@Egil Andersson I wouldn't want to hide it, but I would like to give it some sort of conditional highlight if the data is too stale, is what I'm thinking.
Most Valuable Skill (MVS)
Let’s steal some good ideas from each other. What’s the most valuable agent skill you’ve built so far or found on the interwebs? Share the use case, what triggers it, and what tools it connects to.
5 likes • Aug 20
@Jason Elam - This one is up first to steal from me.
1 like • Aug 21
@Sakshi Gahlawat Completely agree. There’s a lot of value in first getting really clear on what we’re actually solving for and understanding the current process end to end. Once you know the inputs, decisions, bottlenecks, and desired outcome, it becomes much easier to determine where automation or AI can genuinely help. The tools will keep changing, but that ability to understand and structure the problem is much more durable. Good software-selling teams are solving fo the same issue ( I know it's a completely different topic but relatable)
My Experience As the Director of Marketing for ClickFlow Automation 🤙
At the beginning of the summer I was hired as the director of marketing for an automation SaaS startup called ClickFlow Automation. Here are the biggest takeaways from my first 6 weeks with this position: - We grew the community by 92% from 6 members to 72. - Organic networking is a very strong, under appreciated outreach strategy. - Consistency is key. It’s corny but it’s true. - Day to day results aren’t predictable. Week to week results are. - Make connections with the genuine intention of providing value for free instead of just making a sale. - Commit long-term and love the game.
2 likes • Aug 19
Love this post. Great lessons here, especially only six weeks in.
I need your help naming this!
We've been putting a lot of work into Glaido. We want to make it undeniably better than Wispr Flow. Think of it as the voice layer that can actually take action and connect to all of your tools, rather than just transcribing text. Now we're stuck on the name. Four options on the table: And if you haven't checked out Glaido, get a FREE month HERE
Poll
481 members have voted
3 likes • Aug 19
Solid suggestion.
1 like • Aug 19
@Eduardo Beltran hahaha, fair!
Badly need your suggestion guys.
Hey, I have been a product designer for the last 5 years and have been developing marketing sites via low code. But with the wave of the AI era, I am getting confused about how I should evolve with AI. I am designing and developing 4x faster compared to my previous stack, but I believe it is going to be a very basic skill in the coming years. What services should I add, or what decision-making skill should I learn for future moves? Please help me with your valuable futuristic insights.
2 likes • Aug 13
Completely agree with @Chiranjeevi K . I think this is where the future of tech is heading. AI will continue to make it easier and faster to build websites, applications, automations, and workflows. But that also means the real differentiator becomes understanding what problem is actually worth solving and what outcome the customer is trying to achieve. After a decade in tech sales, one thing I’ve consistently seen is that the best partners don’t just show up with a solution and try to apply the same hammer to every problem. They take the time to understand the business, the customer, the process, and the outcome, then determine where technology can create the most value. That’s why skills like product design, discovery, workflow design, and business process optimization become even more valuable in an AI-driven world. The technology will keep changing. The ability to connect technology to meaningful business and customer outcomes is what will continue to separate great partners from everyone else. Hence, we are all here. The genie's out of the bottle already. Now take your skills and adapt.
1-10 of 12
Alejandro Muniz
4
39 points to level up
@alejandro-muniz-6119
looking to learn Ai and help other learn to automate their businesses.

Active 7d ago
Joined Jul 9, 2026
20466
Powered by