# Nicolay Camacho

URL: https://nicolaycamacho.com
Summary: Full-stack engineer building trading infrastructure, internal platforms, and product tooling where reliability, operational clarity, and structured workflows matter.
Professional focus: Trading infrastructure, AI products, Developer tooling, Full-stack engineering
Current work context: Currently building trader-facing systems in a production crypto market-making environment, alongside open-source tooling for governed AI-assisted engineering.
Professional interests: I am interested in serious technical conversations around production systems, AI engineering, fintech infrastructure, developer tooling, and high-ownership software work. I’m interested in full-stack and applied AI engineering roles.
Location: Ghent, Belgium
Core skills: TypeScript, React / Next.js, Node.js, Python, FastAPI, Flask, PostgreSQL, Docker, AI tooling, LLM systems

This Markdown document is the machine-readable discovery entrypoint for this portfolio.
It describes public, read-only information and interfaces; it is not a developer account portal.

## When to use this site
Use these resources to understand Nicolay Camacho's professional background, evaluate relevant project experience, retrieve source-grounded public profile facts, or find the documented contact routes.
Use the HTML pages for human-readable context, the JSON endpoints for structured retrieval, OpenAPI for HTTP API discovery, and MCP for read-only tool calls.
Do not infer unstated data, employment claims, availability, or capabilities beyond these public resources.

## Core pages
- [Homepage](https://nicolaycamacho.com)
- [About](https://nicolaycamacho.com/about)
- [Projects](https://nicolaycamacho.com/projects)
- [Contact](https://nicolaycamacho.com/contact)
- [Developer documentation](https://nicolaycamacho.com/developers)
- [Privacy](https://nicolaycamacho.com/privacy)

## Machine-readable endpoints
- [ARD ai-catalog.json](https://nicolaycamacho.com/.well-known/ai-catalog.json)
- [OpenAPI](https://nicolaycamacho.com/openapi.json)
- [MCP server card](https://nicolaycamacho.com/mcp/server-card)
- [MCP registry manifest](https://nicolaycamacho.com/server.json)
- [agent.json](https://nicolaycamacho.com/agent.json)
- [llms.txt](https://nicolaycamacho.com/llms.txt)
- [Profile JSON](https://nicolaycamacho.com/api/profile.json)
- [Projects JSON](https://nicolaycamacho.com/api/projects.json)
- [MCP endpoint](https://nicolaycamacho.com/api/mcp)

## Selected projects
- Structor: Local-first Harness Engineering Framework for AI-assisted software teams. Structor generates repository-local governance, contracts, context routing, and validation layers for Codex, Claude Code, and similar coding agents.
  - [Engineering Deep Dive](https://nicolaycamacho.com/projects/structor)
  - [Engineering Deep Dive](https://nicolaycamacho.com/projects/structor)
  - [Structor website](https://www.structorlabs.dev)
  - [GitHub repository](https://github.com/nicolaycamacho/structor)
  - [@structor-dev/cli on npm](https://www.npmjs.com/package/@structor-dev/cli)
  - Demonstrates: Structor demonstrates my ability to design developer infrastructure around ambiguous, fast-moving AI workflows. It combines product thinking, CLI design, repository architecture, validation strategy, documentation systems, and practical AI governance. It is the project that best represents how I think about AI-native engineering: make the system legible, constrain the failure modes, and give both humans and agents a shared operating surface.
- AI Front Desk: AI-native SaaS prototype for small-business front desks: tenant onboarding, website ingestion, generated profile review, embeddable widget delivery, usage limits, and billing hooks.
  - [Architecture Notes](https://nicolaycamacho.com/projects/ai-front-desk)
  - [Architecture Notes](https://nicolaycamacho.com/projects/ai-front-desk)
  - Demonstrates: AI Front Desk demonstrates full-stack product engineering around an AI-native SaaS concept. It shows I can think beyond a prompt box: onboarding, crawling, tenant state, embeddable distribution, billing, rate limits, usage controls, frontend demos, backend workers, and governance checks.
- Crypto Copilot: Simulation-first trading copilot that combines market data normalization, schema-constrained AI trade planning, guardrails, and simulated execution across a Next.js/FastAPI architecture.
  - [Technical Deep Dive](https://nicolaycamacho.com/projects/crypto-copilot)
  - [Technical Deep Dive](https://nicolaycamacho.com/projects/crypto-copilot)
  - Demonstrates: Crypto Copilot demonstrates that I can build AI-assisted systems in a domain where correctness and safety matter. It connects my professional exposure to crypto and trading environments with product engineering: market data ingestion, typed service design, structured AI output, validation, simulation boundaries, and a user-facing copilot workflow.

## Contact links
- [Email](mailto:nicolaycamacho@gmail.com)
- [GitHub](https://github.com/nicolaycamacho)
- [LinkedIn](https://www.linkedin.com/in/nicolaycamacho/)
- [Website](https://nicolaycamacho.com)
- [Resume](https://nicolaycamacho.com/nicolay-camacho-resume.pdf)

## AI and agent interfaces
Nicolay builds and evaluates AI-native systems, agent workflows, developer tooling, MCP integrations, structured outputs, and emerging browser-agent protocols. This site includes machine-readable metadata and read-only agent-oriented interfaces as an ongoing exploration of human-AI collaboration.

## Conversational agent
Ask Nicolay (status: available): A first-party conversational agent that answers questions about Nicolay Camacho — his background, portfolio projects, engineering stack, and how to get in touch. Built and operated as part of this site rather than an embedded third-party widget.
Endpoint: [Conversational agent endpoint](https://nicolaycamacho.com/api/agent)
Transport: HTTP POST returning a Server-Sent Events (text/event-stream) reply stream
Request: POST application/json { "messages": [{ "role": "user" | "assistant", "content": string }] }
Response: Server-Sent Events: `data: {"text":"..."}` chunks terminated by `data: [DONE]`.
Scope: Responses are grounded in Nicolay's public professional profile, projects, background, technology stack, and contact routes. Off-topic or out-of-scope requests are declined.
Safeguards:
- Request validation with per-message length limits.
- Per-minute rate limiting plus per-session question quotas.
- Prompt-injection screening on every visitor turn.
- Topic guardrails that keep answers scoped to the portfolio.
- No non-public data, credentials, authenticated state, or write actions.
Live: send a POST with a messages array to receive a streamed reply.

## Agent-interface security posture
The Agent-Facing Surface exposes public read-only data only, keeps the MCP-style tool list stable, and does not provide write actions or mutable tool registration.
- Public profile and project facts only; no non-public data, authentication state, or production controls.
- Stable read-only tool list with no mid-session tool mutation.
- No browser-runtime WebMCP tool registration yet.
- Future WebMCP adoption requires mature security guidance, feature detection, and the same read-only boundary.

## MCP interface
Endpoint: [MCP endpoint](https://nicolaycamacho.com/api/mcp)
Discovery: [MCP server card](https://nicolaycamacho.com/mcp/server-card)
Registry: [MCP registry manifest](https://nicolaycamacho.com/server.json)
Transport: Stateless JSON-RPC 2.0 over HTTP POST; responses are JSON and sessions are not maintained.
Supported tools: get_profile, get_projects, get_experience, get_contact.

## WebMCP status
WebMCP is a W3C Web Machine Learning Community Group draft for exposing browser-native tools to AI agents. It is not a W3C Standard or stable production browser baseline, so this site monitors it without depending on experimental browser APIs.
If WebMCP becomes broadly available behind stable browser APIs and mature security guidance, this site can expose the same public read-only profile and project data through feature-detected browser tools.