Spent an afternoon this week chasing down why a client's order dashboard took around 2.5s to load.
Turned out the page was firing 300+ database queries. Classic N+1 problem. Every order in the loop was making its own separate trip to the DB just to grab the customer and product.
One line fixed it. select_related() tells Django to pull the related rows in a single JOIN instead of querying them one at a time.
312 queries down to 3. Page load went from 2.4s to 0.08s.
The annoying part is this never shows up on small datasets in dev. It only bites you in production once the table grows. So now I always check the query count in Django Debug Toolbar before shipping any list view.
AI-Integrated Digital Platform & Web Solutions (yakusapas.ai.id)
Engineered and deployed the web infrastructure for yakusapas.ai.id, focusing on modern digital services, automated processes, and clean, scalable software architecture.
Core Architectural Highlights:
Next-Gen Web Architecture: Built with high-performance frameworks delivering sub-second response times, secure endpoints, and responsive mobile-first layouts.
Intelligent Automation & Logic Workflows: Designed modular backend pipelines capable of integrating AI endpoints, data processing services, and automated digital tasks.
Intuitive User Interface: Minimalist dashboard and navigation tailored for rapid user onboarding and friction-free service exploration.
Data Integrity & Security: Built-in safeguards including input sanitization, rate-limiting, and hardened environment configs for production reliability.
Live operations dashboard for a payment engine: design and build
A real-time dashboard I designed and built for a payment system, so a team can see at a glance that no payment is lost or paid twice, even while things go wrong.
Design highlights
A “promises” scoreboard: three big rings (Lost, Sent twice, Stuck) that stay green at 0
A one-click, 90-second demo that plays a story on the live system: the network gets flaky, a worker crashes mid-payment, the network goes down, the team fixes it, and the day ends balanced
A life story for every payment: click any payment to see each retry, who handled it and why
Live charts and a control room to break the network on purpose and watch the system recover
End-of-day reconciliation in one click, checked against the payment network’s own records
Not a mock-up: it’s connected to a working payment engine I also built (Python, FastAPI, PostgreSQL, Redis), so every number on screen is real.
Built with: HTML, CSS and JavaScript, no framework.