🧠 Built with AI: TrendScout- Agent build on MSFT Foundry | 888 Day 6
- Cindy Adem
- May 21
- 2 min read
Click play to see it in action:
Summary
TrendScout is a no-code AI agent that analyzes qualitative customer feedback and summarizes it into actionable insights for product teams. It was built well under 8 hours using Microsoft’s brand-new Foundry Agent Service.
My Role:
Product Designer & Builder
Prompt Architect
QA (aka "Does this even work?”)
The Challenge
Microsoft announced Foundry Agents during #Build2025. Dev-first UI. Experimental.
As a non-dev PM, I challenged myself: Can I use this raw tech to build a real solution that saves product teams hours?
Solution
I built TrendScout: An agent that reads customer feedback (think: Zendesk tickets, app reviews, bug logs) and answers questions like:
“What are users complaining about?” “What do people love most?” “Summarize top feature requests.”
Tools Used
Microsoft Foundry Agent Service (AI orchestration)
GPT-4 (prompting + data generation)
ChatGPT (assistant + debugger)
Figma (UX sketches)
Loom / ScreenRec (video capture)
🧪 Process Breakdown
Key Features
Natural Language Feedback Analysis
Trend Detection
Sentiment Summary
Follow-up Q&A
What Makes It Different
I didn’t write a single line of code.
Built using a just-released AI platform.
It solves a real PM pain point
Done in <8 hours
What I Learned
AI doesn’t eliminate product thinking — it amplifies it
Prompt design = the new UX
Tools are moving fast — but UI/UX must catch up
I can ship real AI tools without waiting for dev time
What’s (potentially) next
Turn TrendScout into a white-labeled agent for solo founders & PMs
Create a web UI wrapper (aka a friendly frontend for normal humans)
Test with real data from local businesses
🔥 What is 888?
8 Hours. 8 Days. 8 Products. A personal challenge to build 8 functional AI-powered tools in 8 consecutive days; dedicating just ~8 hours to each build.
This is not about perfection - it’s about speed, creativity, and clarity of product thinking.
Every project is an exploration: solving real problems, testing ideas fast, and documenting the build process openly.
📌 How to Follow the Flow
Each day, I’ll share:
A short demo video
A concise build recap post (on LinkedIn & Twitter)
A full write-up in comments or blog (with lessons, tech stack, and what worked/didn’t)
And once ready, a live link to the deployed product (or prototype status if not yet deployed)
Give me your email and I'll send you daily updates or connect with me on socials to stay updated daily.
Comments