The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
🚀🧫 INTRODUCING ALOKO AI TEACHER! 📚🤖
All thanks to God for making this possible! 🙏❤️
I’m excited to introduce Aloko AI Teacher, an AI-powered study platform designed to help HND Microbiology students study smarter.
✅ Study courses across the curriculum
✅ Ask AI questions and get explanations
✅ Generate scientific diagrams
✅ Access practice questions and past-question materials
✅ Learn practical concepts with AI-generated lessons
My goal is to make learning more accessible and help students prepare better for their examinations. 🎓🔬
This is just the beginning! More improvements are coming. 🚀
🔗 Try it here: [https://aloko-ai-teacher-mqdlth7qlgffyfxexyznoq.streamlit.app/ ]
Click the link and explore it for yourself! 😂🔥
#AlokoAI #Microbiology #ArtificialIntelligence #EdTech #StudentLearning
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
I finally updated my personal website, and you can actually "dye" your own canvas on it! 🎨
I've been experimenting with how to bring something physical into a digital space. The idea came from my growing interest in natural dyes and traditional textile-making, which I've been exploring a lot lately.
I designed and built the whole experience in one day using Figma, Claude and Netlify. It's been pretty exciting to see how AI makes ideas that once felt technically out of reach something I can now experiment with and build on my own.
I'm also open to fractional creative director roles, so if you know a team building something meaningful, I'd love to connect!
Come play with it, and please let me know if you find any bugs 🐛
mya-nguyen.com
dyeing your own canvas on a personal site is such a nice idea. most portfolios just sit there, this one lets you play
I built Tests Wise: paste a URL, get a test plan and watch AI run the tests live.
Most small teams ship without a written test plan. Not because they don't care because writing one takes a day nobody has. And running it takes another.
Tests Wise does both:
Paste your site's URL (works with sites behind a login).
AI agents explore up to 8 pages in a real browser and figure out what each one does.
You get prioritized test scenarios steps, expected results, priority as an Excel your QA team or client can use right away. In English or Spanish.
Then an AI agent executes those scenarios live in a real browser, driven through Playwright MCP, and reports what passed, what failed and why, with a screenshot of each step.
Everything is automated software: no scripts, no selectors, no CI to wire up.
Under the hood: FastAPI + PostgreSQL, Redis/RQ workers, Playwright for the crawl, Claude for scenario design and for driving the browser via Playwright MCP, LangGraph for the pipeline. Deterministic exploration, LLM only where it adds value — a full run on an 8-page site costs a few cents.
It's free to try, no card needed: https://app.tests-wise.com/
Demo below 👇 I'd love to hear which site you'd throw at it first.
A screenshot per step is a smart touch, makes failures easy to show a client. How long does a full run take for 8 pages?
Building MLOpsLab has taught me something interesting:
Most workflow problems aren't caused by missing automation.
They're caused by missing visibility.
A form gets submitted.
A webhook fires.
An API responds.
Everyone assumes the process worked.
Then days later someone discovers a missing lead, duplicate record, failed sync, or unexplained gap.
Lately I've been spending time building and testing workflow reliability scenarios around:
• Intake validation
• Duplicate event handling
• Failure detection
• API and database integrations
I'm documenting what works, what fails, and where assumptions break.
If you've ever spent hours tracking down a workflow issue that "should have worked", I'd be interested in hearing what the failure looked like.
#automation #n8n #api #workflow #supabase #buildinpublic
The hardest one to catch is the green run that did nothing. An API returns 200 with an empty list, every later step runs on zero items, and nothing errors. A cheap guard: count items in and items written at the end of the run, and alert when they differ. Are you testing that case in MLOpsLab, or mostly hard failures?