Signups
9
MRR
£0
Stack
Flutter · Node.js · Express
- Current read
Faruq + Amina · Aug 29, 2026
Faruq thesis
Miguelito is a neural assistant that bets on becoming the go-to AI-powered planner by leveraging psychology-based scheduling and natural conversation.
Next moves
- Implement a robust user feedback loop to continuously refine the 'Calm Authority' persona and scheduling algorithm. - This unblocks the thesis by ensuring that Miguelito's unique value proposition (psychology-based scheduling and natural conversation) is constantly improving and resonating with users.
- Develop a comprehensive onboarding experience that introduces users to Miguelito's 'Calm Authority' persona and the benefits of psychology-based scheduling. - This unblocks the thesis by setting the right expectations and guiding users to adopt Miguelito's unique approach to planning and goal setting.
Watch
- Over-reliance on AI for scheduling decisions may lead to user dependency and loss of autonomy. - If users become overly dependent on Miguelito's scheduling decisions, they may lose the ability to make independent choices, undermining the product's value proposition.
Amina visual track · running
Use real product captures first; create hero stills, proof crops, and social/OG variants from Faruq's latest thesis and current-state evidence.
— Why it exists
I built Miguelito because I kept losing the week.
Five apps that didn't talk to each other. A calendar that didn't know about a deadline. A fitness tracker that didn't know I had three client calls before noon. A quarterly goal I'd set in January and forget by March. Every Sunday I'd replan. Every Wednesday the plan would be dead.
The planning wasn't the problem. The execution was. Nothing adapted when the day moved. Nothing actually knew me.
So I built it.
— How it's built
Orchestrator architecture, not a mega-prompt
Central intent classifier dispatches to the right specialist agent. Prevents feature sprawl. Keeps every agent sharp.
Privilege Lock System
Three tiers - Gentle, Standard, Hard - let users enforce their own constraints on themselves. Guardian Mode adds a timed focus pause you can't skip.
Chronotype-aware scheduling
The calendar agent reads whether you're a morning lark or night owl and builds around your actual energy, not convention.
Wearable data is ground truth, not decoration
Stress, sleep, and recovery signals feed real decisions - dropping cognitive load, protecting evenings, reshuffling deep work blocks.
— The lesson
“The orchestrator pattern. Users don't think about which agent they're talking to - they just talk. The routing disappears and that's what makes it feel like one assistant instead of five tools stacked behind a chat window.”