Daniel Landi

Self-Correcting AI Teaching Activity Generator

Sun, 27 Sep 2026 00:00:00 +0000

A web app built in 48 hours for the IBM Bob 2.0 Hackathon that generates hands-on, teacher-editable classroom activities for any resource level — with a second AI pass that audits its own output against six quality checks before the teacher sees it.

The C code factory: local first, cloud only when needed

Sun, 11 Oct 2026 00:00:00 +0000

A 7B model on a laptop with no GPU solved 20 of 41 C tasks under the 42 Norm; a cloud cascade solved all 41 for USD 1.01. Method, results, and the six mistakes I caught along the way.

uLLAMA: A Minimal C Runtime for Local LLM Inference

Tue, 29 Sep 2026 00:00:00 +0000

A small C wrapper around llama.cpp that loads GGUF models and runs an interactive session with live tokens-per-second reporting — built to fit an 8 GB, CPU-only laptop and written under the 42 Norm.

Typed Decisions vs. Prose: A Support-Ticket Triage Demo

Mon, 28 Sep 2026 00:00:00 +0000

A live, side-by-side demo of two ways an AI model can triage support tickets — fast typed decisions versus slower generated prose — built against a published model contract and localized for Brazilian Portuguese.

What 25 Years of Telecom Ops Taught Me About Cloud Infrastructure

Fri, 25 Sep 2026 00:00:00 +0000

The instincts don’t change when the hardware does — they just get renamed.

Digital Resilience: Failover-Resilient Serverless Architecture

Tue, 01 Sep 2026 00:00:00 +0000

A high-availability AWS architecture with dual-origin failover, built and live-tested for the EDN Hackathon Future Builders (Case B: Digital Resilience).

Gems & Landi: AWS Cloud Labs Documentation Series

Sun, 23 Aug 2026 00:00:00 +0000

An ongoing, self-published documentation standard for hands-on AWS labs — networking, security, and serverless — written with more depth than the official docs.

Systems Programming at 42 São Paulo

Fri, 21 Aug 2026 00:00:00 +0000

Reimplementing the C standard library, building a line-by-line file reader with static memory, and co-developing a stack-sorting algorithm — the foundations most cloud engineers skip.

About

Mon, 01 Jan 0001 00:00:00 +0000

I spent 25 years keeping mission-critical systems alive — carrier-grade wireless networks, signaling infrastructure, prepaid databases running on Solaris and HP-UX, across telecom deployments in six countries. The discipline that comes from that world — SLA management, ITIL, eTOM, the assumption that failure is not hypothetical — is the foundation everything else here is built on.

I’m now retooling deliberately into AI development and modern software engineering, on cloud-native foundations. That means: