DAILY NEWS

Stay Ahead, Stay Informed – Every Day

Advertisement
TECH & AI
From an Idea to a Hackathon: Lessons from Organizing Build with AI Makerere
jackminion 0



After months of planning, countless emails, sponsor outreach, community workshops, and late nights, we successfully hosted the Build with AI Makerere Hackathon in partnership with Google Build with AI and Major League Hacking (MLH).

The event brought together student developers from universities across Uganda to build AI-powered solutions addressing real-world challenges using Gemini, Google AI Studio, and Google Cloud.

Along the way, I learned invaluable lessons about:

Building partnerships and securing sponsorships
Planning and organizing a hackathon from scratch
Leading a growing developer community
Navigating unexpected challenges
💡 Creating an environment where students could innovate and learn

This experience reminded me that community leadership isn’t about having everything figured out—it’s about learning, adapting, and bringing people together around a shared vision.

I’ve written a detailed reflection covering the journey, the challenges, the impact, and the lessons I’ll carry into future events.

👉 Read the full story here: build-with-ai-makerere-hackathon

I’d love to hear your thoughts or learn about your own experiences organizing community events!

BuildWithAI GoogleAI GDG @mlhacks Hackathon DeveloperCommunity ArtificialIntelligence OpenSource CommunityBuilding Leadership



Source link

TECH & AI
hack with Hyd 2.0 – DEV Community
jackminion 0



Support bots that forget every conversation aren’t support bots. They’re expensive FAQ pages.I built SupportMind to fix that — a customer support agent that actually remembers.The architecture is two layers:Memory (Hindsight): After every interaction, the agent stores structured context in a vector namespace per user. Next session, it recalls semantically — “payment problem” retrieves “Visa charge failing” even if the words don’t match.Routing (cascadeflow): Not every query needs GPT-4. Password resets go to Groq’s free tier. Complex billing disputes escalate. Every decision is logged with model, cost, latency, and reason.The delta that matters:Session 1: “Can you tell me your card details and the error you’re seeing?”Session 3 (same user, same issue): “I see you’ve had recurring issues with your Visa ending in 4242. Last time, clearing billing cache fixed it — want to try that first?”Same infrastructure. Completely different agent.On a typical support workload: ~80% simple queries handled by the cheap model. Cost per query dropped from ~$0.012 to ~$0.002.The part I didn’t expect: routing and memory compound. When Hindsight shows a user has had the same issue four times, cascadeflow automatically classifies their next message as complex — even without explicit signals. That fell out of the architecture. 👇https://lnkd.in/gn8NwP6Z

hashtag#AIAgents hashtag#AgentMemory hashtag#Hindsight hashtag#cascadeflow hashtag#LLM hashtag#AI



Source link