Peru.N
Peru NCase studies & notes

I design cloud & AI systems built for security, clarity, and real-world use.

I design secure, scalable software systems and turn complex cloud or AI workflows into products that feel clear, usable, and trustworthy.

Explore case studies Read the notes
Recent architecture work: AI PDF reader system diagram
AI PDF Reader — Architecture

Name

Peru N

Focus

Architecture · Cloud · Security

Contact

Email

Featured repo

Agentic IaC Reviewer

§ What I do

Three practices, one systems mindset

I work end-to-end — from target architecture to delivery to the threat model that keeps it standing.

01

Local-first AI

Product · AI
AI PDF Reader combines retrieval, local models, desktop packaging, and product UX.
02

Platform & reliability

Cloud
Kubernetes and IaC tooling — from infrastructure security review to incident-reliability intelligence.
03

Security design

Security
Threat models, trust boundaries, and secure delivery decisions are part of the project story.
§ Featured work

Case studies in systems thinking & secure design

Projects with architecture visuals, security analysis, and implementation outcomes — not just screenshots.

GraphRAG Incident-Intelligence Copilot architecture diagram
/ 01Architecture
Product · AI2026-07-05

GraphRAG Incident-Intelligence Copilot

Fused knowledge-graph structure with vector similarity so incident diagnosis is driven by evidence, not by a plausible-sounding guess.

Built an on-call copilot that fuses a service dependency graph with semantic search over past incidents, then has an LLM synthesize a grounded root-cause diagnosis and blast radius from ranked evidence.

AI SystemsPlatform EngineeringReliabilityKnowledge Graphs
  • Combined graph structure and historical precedent so root-cause candidates are both reachable and evidenced, not just semantically similar.
  • Reached a 1.0 hit-rate@3 and 0.944 MRR with hybrid retrieval versus 0.778 and 0.569 for graph-only in an ablation over chaos-injected incidents.
  • Turned incident labelling from an argument into a fact by generating ground truth through controlled fault injection.
View case studyRepository
Agentic Kubernetes IaC Security Reviewer architecture diagram
/ 02Architecture
Security2026-06-23

Agentic Kubernetes IaC Security Reviewer

Combined deterministic security scanning with bounded agent remediation to make infrastructure findings easier to trust and act on.

Built an agent-assisted CLI that turns Kubernetes, Terraform, and Dockerfile scanner output into prioritized security reviews, control-backed explanations, and safely staged remediation artifacts.

Security EngineeringPlatform EngineeringDevSecOpsAI Products
  • Turned raw infrastructure scan output into a prioritized review workflow engineers can act on faster.
  • Added control-backed explanations that make findings easier to defend in platform and security discussions.
  • Reduced remediation risk by staging generated fixes outside the source tree with bounded retry logic.
View case studyRepository
AI PDF Reader architecture diagram
/ 03Architecture
Product · AI2026-04-17

AI PDF Reader

A private, local-first document AI product with grounded retrieval, desktop packaging, and strong UX.

Built a local-first AI PDF Reader that lets users upload documents, retrieve grounded answers, generate study guides, and run as both a web app and offline desktop experience.

AI EngineeringSoftware ArchitectureLocal-First AISecurity Engineering
  • Delivered a product that can run in browser mode or as a desktop app for Windows and macOS.
  • Combined PDF parsing, chunking, embeddings, retrieval, and local LLM answers into one polished workflow.
  • Improved privacy posture by supporting local GGUF models and offline packaging for sensitive document use cases.
View case studyRepository
§ Blog

Writing on architecture, delivery & security

Short pieces on platform design, technical decisions, and implementation patterns from recent work.

AI Systems/2026-07-05/6 min

Grounding Incident Diagnosis With a GraphRAG Copilot

This project pairs a service dependency graph with semantic search so an on-call copilot can name a likely root cause and its blast radius from evidence, not from a plausible-sounding guess.

AI SystemsPlatform EngineeringReliability
Read note
Security Architecture/2026-06-23/6 min

What This Agentic IaC Security Reviewer Says About My Architecture Style

This project shows how I turn noisy infrastructure security findings into an explainable, remediation-focused workflow by combining proven scanners with bounded agent reasoning.

Security ArchitecturePlatform EngineeringAI Products
Read note
AI Product Engineering/2026-04-17/7 min

Building AI PDF Reader as a Real Product, Not Just an AI Demo

The difference between an AI demo and an AI product is everything around the model: UX, retrieval quality, runtime setup, packaging, trust, and documentation.

AI EngineeringProduct ThinkingTechnical Leadership
Read note
Software Architecture/2026-04-17/6 min

Architecture Lessons from AI PDF Reader

AI PDF Reader brings together product architecture, privacy, retrieval quality, and delivery discipline in one local-first system.

Architecture ReviewsSoftware ArchitectureAI Products
Read note
Security Engineering/2026-04-17/6 min

Threat Modeling a Local-First AI Desktop App

Local-first AI products feel safer by default, but they still need careful threat modeling around files, models, prompts, packaging, and desktop boundaries.

Threat ModelingDesktop SecurityLocal AI
Read note

§ Get in touch

Let's build something solid together.

Open to architecture, cloud, and security engineering conversations. The links below are the fastest way through.

GitHubLinkedInEmailFeatured repo