London · AV / Audio / Automation

Santiago Hoyos

I design and build systems across AV, audio software and intelligent automation.

View selected work Explore the AI work

51.5072° N
0.1276° W

My work ranges from integrated rooms and acoustic coordination to C++ audio tools and private AI workflows. In each project, I make the system, its constraints and its outputs clear.

How I build with AI

I build the workflows around the model: what it can read, who does the work, how we check it and where I make the decision.

AI-built, human-directed

AI Orchestrator

A personal AI workspace connecting scoped specialists, source-linked memory, Python checks and human decisions.

  1. 01 Define the outcome Human direction
    Input
    A request, a real constraint and a desired result.
    Output
    A bounded brief with a checkable finish.

    This websiteExpand this portfolio's AI projects while keeping the existing brand and private sources separate.

    I decide the objective and what the system may change.

  2. 02 Bound the context Coordinator
    Input
    The brief and the sources permitted for this task.
    Output
    A small assignment for the right specialist.

    This websiteUse the public project copy, approved visual system and existing Astro code.

    A relevant source does not grant permission to share it.

  3. 03 Do the work Scoped specialist
    Input
    The assignment, relevant evidence and allowed tools.
    Output
    A draft, analysis or implementation for checking.

    This websiteAI agents produce the project text, Astro components and calculated graph on this page.

    A specialist's recommendation is advice, not approval.

  4. 04 Check the result Code and review
    Input
    The result and the task's acceptance conditions.
    Output
    Evidence of what passed, failed or remains unknown.

    This websiteThe production build and automated browser checks pass. Visual review remains a separate check.

    A successful command does not prove the whole task worked.

  5. 05 Decide what ships Human review
    Input
    The checked result, its limitations and proposed action.
    Output
    Accept, revise or hold at the relevant release boundary.

    This websiteKeep the update local for my visual review before publishing it.

    Checks do not replace creative judgement or release permission.

Conceptual workflow, not a live execution trace. Open a stage to inspect the hand-off.

Under the hood

Separate agents do the work. Source-linked memory carries decisions forward. JEV helps with narrow judgements. I connect these parts and keep their permissions distinct.

Multi-agent setup

Personal working system

A coordinator delegates bounded work to separate specialist profiles, then checks the returned evidence.

Agent memory

Working prototype / expanding coverage

Source-linked recall, age-based relevance and corrections that preserve history.

JEV judgements

On-demand advisory tools

Structured choices, scores and yes/no questions support evaluation and routing. Code and people retain control.

Knowledge maps

Owner-only navigation tool

Follow relationships back to the source instead of treating a graph as the answer.

This website

AI-built, human-directed

A real application of the workflow, from creative brief to code and browser checks.

Explore the AI system

Selected work

Three systems,
built at different scales

Mews Cinema room render
Mews Cinema · Room render

Integrated AV
Physical system

Mews Cinema

A concealed residential cinema coordinated across AV, acoustics, joinery and lighting control.

Mews Cinema · Room plan · equipment and speaker positions within the joinery
Room plan · equipment and speaker positions within the joineryOpen full drawing
Mews Cinema · Sightline study · drawing annotations: 10° front row, 4° rear row
Sightline study · drawing annotations: 10° front row, 4° rear rowOpen full drawing

Decision / evidence

ConstraintHidden speakers and screen set-out within bespoke joinery DecisionCoordinate the joinery, acoustic build-ups and screen placement CheckEquipment layout, viewing angles, acoustic details, rack and controls

Audio software
Signal processing

OSHAEQ

A six-band parametric equaliser built in C++ and JUCE, with a real-time FFT spectrum analyser.

View case study
OSHAEQ equaliser interface
OSHAEQ · Plugin interface

Making system behaviour visible

Four-band computed response study. A build-time calculation, separate from the six-band plugin above.

Frequency response of a four-band parametric equaliser, computed from RBJ Cookbook peaking biquad filters: 80 Hz +3.5 dB Q 0.9, 450 Hz -4.5 dB Q 1.4, 2.4 kHz +5 dB Q 1.1, 9.5 kHz -3 dB Q 0.8.
+dB4 bands · 20 Hz to 20 kHz
80 Hz +3.5 dB
450 Hz -4.5 dB
2.4 kHz +5 dB
9.5 kHz -3 dB

Practice

One method across
different systems

I work with rooms, signal paths, data models and automation. The medium changes. I start by understanding the structure and its constraints, then build a result that can be checked.

About

I am based in London. My background includes AV systems design, acoustic consultancy and an MSc in Audio & Music Technology from the University of York, including spatial-audio research with Sony Interactive Entertainment.

About Santiago →

Start a
conversation

I welcome professional conversations and selective collaborations in AV, audio software and intelligent systems.