> ab ovo — from the very beginning_
Miguel · Software Architect · Lima, Perú
Software architecture for AI‑native delivery.
I design backend systems and supervise autonomous AI agent teams as the domain expert who validates what they build at each step.
Ask Abovo
Answers from this portfolio, with sources
What has Miguel built with LLMs?
Two lab projects stand out: claude-lab, a Python harness on the Anthropic Messages API with a budget‑enforcing client, and Accesible por diseño, a multi‑agent WCAG 2.2 audit pipeline over axe‑core and Playwright.
Launching soon — this is a preview of how answers will look.
- AI‑native deliveryDomain expert supervising autonomous agent teams
- CertifiedSoftware Architecture · MBSE
- LecturerHigher‑education teaching
- Standards expertNational software competency standards
AI experiments, in the open
Working code, design notes and what each experiment cost to run.
- A1
Ask Abovo
In progressRetrieval‑augmented assistant over this site’s case studies, CV and posts. Serverless proxy, rate‑limited, answers cite their sources.
- A2
claude-lab
In progressSix sessions from a first Messages API call to multi‑agent orchestration, in Python, behind a MeteredClient that enforces a budget.
- A3
Accesible por diseño
ResearchWCAG 2.2 benchmark of public‑sector portals following WCAG‑EM, using axe‑core, Playwright and a multi‑agent review pipeline.
Essays and tutorials
Starting from first principles
Abovo comes from the Latin ab ovo — “from the egg”: telling a story from its true beginning, without skipped steps. It is how I approach architecture: understand the problem from its origin, then design only what is essential.
- Now
- Software Architect & Domain Expert · AI‑native delivery
- Previously
- Consulting, telecom and global IT services
- Teaching
- University and institute lecturer
- Standards
- Independent expert, national software competency standards