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

Owned by Mike

Stop chatting. Start doing. Step-by-step AI courses for business owners, from your first prompt to building your own AI system.

14 contributions to AI Automation Society
Allergies suck. Air quality websites are worse. So, I built my own.
I rarely post in AIS. If you know me, I usually post in AIS+ or another community. But I think this one is useful for a lot more people, because tons of us have allergies. If you suffer like I do, there's a prompt toward the end to build your own. TLDR; No site shows everything in the air in one place. So I had Claude research why, then build the thing. 5 data sources, one page, a 6:30am email every morning, and alerts on bad days. About 2 hours from first question to live URL. Screenshot attached. WHY I WANTED IT - I have allergies. Hay fever, whatever you want to call it. And I don't know WHAT I'm allergic to. - To figure that out I need everything in the air on one screen, broken down by plant, next to how I actually feel that day. I couldn't find it. Claude couldn't find it either. So I built it. - Every air site I tried showed part of the picture. One has AQI. Another has pollen, but lumped into "trees" and "grass." Nobody has mold. Almost nobody has Saharan dust or smoke. - Turns out Fredericksburg has no official air monitor at all. The closest one is San Antonio, 66 miles away. So every local AQI number you've ever seen for here is a model, not a measurement. Most sites don't tell you that. - That's why it has a symptom log. I score each day 0-5 (0 = great, 5 = miserable), and it saves that day's pollen, mold and air levels with the score. After a couple of weeks the pattern table should show which ones line up with my bad days. HOW IT WENT (8:21am to live at 10:24am) 1. Research first. 5 agents fanned out: air quality feeds, pollen, mold, dust and smoke, and a survey of every existing dashboard. Verdict: nothing does all of it. IQAir came closest and still has no plant-level pollen, no mold, no dust. 2. Plan. Data sources, cost per month, what's licensed for personal vs commercial use, and how accurate each number actually is. 3. Build. Claude Code wrote it. I reviewed each piece and made the calls. 4. Ship. Live behind a login only I can pass. Morning email wired about 10 minutes later.
Allergies suck.  Air quality websites are worse. So, I built my own.
1 like • 22d
@Debbie Ai Thanks! Yeah, I originally wasn't planning on building anything. I figured just because I can't find an allergy tracker with everything I wanted, didn't mean they don't exist. When Claude couldn't find one either, I didn't have a choice.
1 like • 22d
@Debbie Ai
Aug 14 • 
Wins 🌟
🏆 Weekly Wins Recap | August 8 – August 14
From $10K builds and monthly retainers to first discovery calls, first agents, and warm outreach turning into real opportunities - this week inside AIS+ showed that sometimes the best clients are closer than you think. 🚀 Standout Wins of the Week inside AIS+ 👉 @Mike Thomson signed his first monthly retainer with zero cold outreach - a local restaurant found him through Google and closed at $10K upfront + $3K/month. 👉 @Leon Seguin-denis officially launched his agency by signing his first client for €5.5K setup + €290/month recurring revenue. 👉 @Ameeth B. signed a $3.5K + MRR client and shipped a BI dashboard that automatically consolidates data from 7 Smartsheets every morning. 👉 @Dean Henry reached out warmly to just 2 people about AI automation and both agreed to let him build for their businesses. 👉 @Ryan S. Howard held his first discovery call with a large church ministry and uncovered 4 potential workflows, including one that could save a leader 6-10 hours every week. ⸻ 🎥 Super Win Spotlight | @Karen Widas Karen joined AIS+ expecting useful training. What surprised her most was the community. Someone inside AIS+ helped audit her website, which eventually gave her the confidence to rebuild the entire thing herself using Claude Code - and later build a custom solution for one of her customers. For someone who normally considers herself a “lurker,” she also found herself comfortably posting, asking questions, and helping others. Her biggest takeaway? The right community doesn’t just teach you. It gives you the confidence to build things you didn’t think you could build before. 🎥 Watch Karen’s story 👇 ✨ Sometimes the next opportunity doesn’t come from reaching more people - it comes from becoming more useful to the people already around you.
🏆 Weekly Wins Recap | August 8 – August 14
9 likes • Aug 14
@Matthew Sutherland appreciate you! You inspire me in ways I can’t explain.
✅ PROJECT GLASSWING: ONE-MONTH UPDATE
Source: Anthropic, May 22, 2026 Model: Claude Mythos Preview (unreleased) HEADLINE Finding bugs is no longer the bottleneck. Patching them is. Anthropic and ~50 partners have been using Mythos Preview to hunt vulnerabilities in critical software. After one month, the security ecosystem is struggling to keep up with the volume of valid findings. SCALE OF FINDINGS - 10,000+ high/critical-severity vulnerabilities surfaced across partners in one month - Partners reporting 10x increases in bug-finding rate - Cloudflare: 2,000 bugs (400 high/crit), false-positive rate beating human testers - Mozilla: 271 vulns fixed in Firefox 150, 10x the Firefox 148 run with Opus 4.6 - Industry patch volumes spiking: Palo Alto 5x normal, Microsoft and Oracle accelerating EXTERNAL VALIDATION - UK AI Security Institute: first model to solve both cyber ranges end-to-end - XBOW: "significant step up" over all existing models, unprecedented token-for-token precision - Top performer on ExploitBench and ExploitGym (new academic benchmarks) OPEN-SOURCE SCAN RESULTS - Projects scanned: 1,000+ - Total vulns flagged: 23,019 - Estimated high/critical: 6,202 - Triaged so far: 1,752 - True positive rate: 90.6% - Confirmed high/critical: 62.4% - High/crit disclosed: 530 - Patched: 75 - Public advisories: 65 Notable: wolfSSL certificate forgery exploit (CVE-2026-5194), now patched. Would have let attackers host convincing fake bank/email sites. Maintainers are asking Anthropic to slow disclosures. Capacity is the binding constraint. WHAT'S PUBLIC VS. HELD BACK Mythos-class models are NOT being released. Anthropic says safeguards aren't strong enough. Available now: - Claude Security (public beta, Enterprise) - 2,100 vulns patched in 3 weeks using Opus 4.7 - Cyber Verification Program for legit security pros - Tooling release on request: scanning harness, threat model builder, shared skills - Cisco open-sourced its Foundry Security Spec IMPLICATION FOR DEFENDERS The find-vs-fix gap is the new attack surface. Mythos-class capability will proliferate to other labs soon. Anthropic's advice:
✅ PROJECT GLASSWING: ONE-MONTH UPDATE
4 likes • May 23
@Matthew Sutherland with the AI news scoop! Nice!
🚀New Video: Unlock the Next Evolution of Claude Code with One Plugin
There's one free plugin that's completely changed how I use Claude Code. It's called Superpowers, and it turns Claude Code into a disciplined developer that clarifies, designs, plans, codes, and verifies before shipping anything. In this video I walk through all 14 skills, show real brainstorming demos, and share the results from a 12-run experiment comparing token usage and code quality with and without the plugin installed. SUPERPOWERS
4 likes • Apr 12
Gave this to Claude today, Claude was like “hell yeah, let’s do this”. Ripping through projects since. Thank @Nate Herk !
Mar 27 • 
Wins 🌟
🏆 Weekly Wins Recap | Mar 21 – Mar 27
From AI operating systems and quick client closes to outbound wins and real-world automation impact - this week inside AIS+ showed what happens when builders stop waiting and start shipping. 🚀 Standout Wins of the Week 👉 @Latoya Robinson built her own AI Operating System in one weekend - 7 agents, 15 integrations, and a $1.2M+ pipeline in motion. 👉 @Michael Wacht closed an $8,500 AI project focused on voice, email, and workflow automation. 👉 Michael Elliott built and closed a $1,200 app live during a client call using Claude Code. 👉 @Mike Thomson turned a $60K ad-spend issue into a real-time monitoring system with alerts and auto-protection. 👉 Angel Benavides turned cold outreach into his first discovery call - then booked another the next day. 🎥 Super Win Spotlight | @Latoya Robinson Latoya joined AIS+ ready to commit - not just consume. In just a few months, she has: • Closed a $24,000 client engagement (3 months) • Built systems using Claude Code for real business use cases • Reduced hours of manual work into just a few hours of execution • Started building SaaS systems with real revenue potential Her biggest shift? Going from feeling stretched and overwhelmed → to operating with leverage and speed. Latoya’s journey is proof that when you commit fully and apply what you learn,results follow faster than expected. 🎥 Watch Latoya’s story 👇 ✨ Want to see wins like this every week? Step inside AI Automation Society Plus and start building assets that compound 🚀
🏆 Weekly Wins Recap | Mar 21 – Mar 27
3 likes • Mar 28
@Deleted If you've ever ridden a Triumph Rocket 3, you'd understand :) 2500cc beast.
2 likes • Mar 28
@Deleted As long as you ride, and you have fun, that's all that matters. I have an illness... I NEED lots of torque. The Rocket has more torque than any other motorcycle on the road.
1-10 of 14
Mike Thomson
4
31 points to level up
@mike-thomson-5349
I help business owners get real work out of AI. I host Outside the Chat Box, offer personal coaching, and am available for consultative work.

Active 6h ago
Joined Dec 10, 2025
INTJ
Powered by