Skip to content
Alex Novara

Alex NovaraExperience

Software engineer building reliable web platforms and practical AI tools

11 years of professional experience

PDF updated

  1. Leads the platform team of a fictional digital publisher: the reading app, the editorial tools and, since 2024, the AI features of both.

    • Own the architecture of the reading platform and its editorial back office
    • Introduce retrieval-based search and summaries with an evaluation suite
    • Mentor four engineers and run the weekly design review
    • TypeScript
    • Next.js
    • PostgreSQL
    • pgvector
    • Python
    • LangGraph
    1. Reading assistant

      March 1st, 2024 – present

      Answers readers' questions from the fictional publisher's own archive, with sources.

      • Python
      • LangGraph
      • pgvector
      • PostgreSQL
    2. Editorial workbench

      June 1st, 2022 – September 30th, 2023

      One back office for planning, editing and publishing the fictional publisher's stories.

      • TypeScript
      • Next.js
      • PostgreSQL
    3. Headline tester

      February 1st, 2023 – May 31st, 2023

      A small tool that compares headline variants on a share of the fictional readership.

      Problem

      Headline choices were made by gut feeling.

      Solution

      Added variant assignment at the edge and a daily report.

      Result

      Editors test two headlines a day on average.

      • TypeScript
      • Redis

    Lumen Press website

    “Alex wrote the test questions before writing the assistant. That is why we trusted it with our archive.”

    An illustrated placeholder avatar of the fictional Mira Example.
    Mira Example, Editor-in-chief, Lumen Press (fictional)
  2. A fictional one-person studio for architecture reviews and small AI prototypes for local businesses.

    • Review web architectures
    • Prototype assistants over company documents
    • TypeScript
    • Python
    • Model Context Protocol
    • Docker
    1. Document assistant prototype

      September 1st, 2024 – November 30th, 2024

      A prototype assistant that answers staff questions from a fictional firm's handbooks.

      Problem

      Staff of a small accounting firm asked the same handbook questions every week.

      Solution

      Built a prototype exposing the handbooks to an assistant through an MCP server, with a short evaluation set.

      Result

      The firm kept the prototype for internal use.

      • Python
      • Model Context Protocol
      • Docker
    2. Architecture review kit

      June 1st, 2020 – present

      A repeatable checklist and report template for reviewing small web platforms.

      Problem

      Each review started from a blank page.

      Solution

      Collected the questions of earlier reviews into a checklist and a report template.

      Result

      A review takes two days instead of five.

      • TypeScript

    Quill Studio website

    “Four weeks later our staff stopped asking the same handbook questions.”

    Dana Placeholder, Managing partner of a fictional accounting firm
  3. Co-maintains a fictional open-source catalogue for small community libraries.

    • TypeScript
    • React
    • Playwright
    1. Community catalogue

      March 1st, 2018 – present

      An open-source catalogue for fictional community libraries.

      Problem

      Small libraries kept their catalogue in spreadsheets.

      Solution

      Maintains the React front end and its Playwright suite.

      Result

      Used by a dozen fictional libraries.

      • TypeScript
      • React
      • Playwright

Independent R&D

Unreleased research and experiments, apart from the career above. Each says how far it went.

  1. Citation checker

    BuiltImplemented and working

    Built: a second model pass that refuses answers whose citations do not support them.

    • Grounded answers
    • Self-checking
    • Refusal on missing evidence
  2. Chunking benchmark

    TestedTried hands-on

    Tested: three chunking strategies compared on the same fictional question set.

    • Chunk size
    • Overlap
    • Retrieval recall
  3. Tool permission model

    DesignedUnimplemented design, planned or architected only

    Designed: a permission model for agents that act through tools, with read and write scopes.

    • Least privilege
    • Human approval
    • Audit trail
  4. Evaluation dashboard

    BuiltImplemented and working

    Built: a small dashboard that tracks evaluation scores across prompt and model changes.

    • Regression tracking
    • Pass thresholds

Technologies

Core

  • TypeScript
  • Node.js
  • React
  • Next.js
  • PostgreSQL
  • PHP

AI engineering focus

A current specialisation, not years of core expertise.

  • Python
  • LangGraph
  • pgvector
  • Model Context Protocol

Education

  1. Informatics, master's degree

    Harbour City University

    September 1st, 2013 – June 30th, 2015School

    A fictional programme; thesis on scheduling freight routes.

  2. Applied informatics, bachelor's degree

    Harbour City University

    September 1st, 2010 – June 30th, 2013School

  3. Cloud solutions architect

    Example Cloud Academy

    May 14th, 2021Certification

  4. Evaluating language-model applications

    Example Online School

    January 8th, 2024 – March 1st, 2024Course

  5. First agent in production

    February 1st, 2025Milestone

    The fictional reading assistant reached its first test group.