Method

From product taste to production systems.

Pedro Antonelli is primarily a frontier AI Engineer, building senior-level multi-agent systems where architecture, data, interface and operations are designed as one working product.

The operating model

How the work gets shipped

Every engagement starts by mapping the real workflow: inputs, decisions, exceptions, owners and the places where AI can safely remove manual drag. That map becomes the architecture, not a slide that gets forgotten.

The build combines product taste with frontier engineering depth: LangChain and LangGraph for orchestration, RAG and data engineering for grounded systems, dreaming/simulation loops for exploration, DevOps for deployment and observability, and multi-cloud comfort across GCP, AWS and Azure.

The accelerator is a senior-level agent swarm built with frameworks like OpenCLAW and Hermes. An orchestrator delegates research, coding, review, automation and publishing to specialized sub-agents running in parallel, keeping the human focus on judgment, scope and product quality.

The path

How I got here

2018 — 2021

Product & visual design

Built a foundation in product design — interfaces, brand systems, and a relentless focus on how things feel to use.

2021 — 2023

Into engineering

Started shipping the things I designed: full-stack web, APIs, data pipelines and the DevOps to keep them running across clouds.

2023 — 2024

All-in on AI

Went deep on LLMs: LangChain, LangGraph, RAG and agentic architectures. Started building real systems, not demos.

2024 — now

AI Engineer & my swarm

Designing and engineering complete AI products — and operating a swarm of agents built with OpenCLAW and Hermes that ships alongside me.

How I work

Principles I build by

Design is not decoration

A model is only useful if a human can actually use it. I obsess over the experience as much as the architecture.

Grounded over confident

I’d rather a system say “I don’t know” than hallucinate. Retrieval, citations and evals keep it honest.

Ship, then observe

Production teaches what demos can’t. I deploy early, measure everything and iterate on real signal.

Leverage through agents

My swarm does the parallel grunt work so I can stay on the judgment calls that actually need a human.

What’s under the hood

Things I can take from zero to production

Agents & Orchestration

LangChainLangGraphOpenCLAWHermesClaudeOpenAIMCPDreaming loopsMulti-agent evals

Retrieval & Data Engineering

RAGData pipelinesETL/ELTSQLpgvectorPineconeQdrantPostgresRedis

Cloud & DevOps

GCPAWSAzureDockerTerraformGitHub ActionsCloud Run

Product & Frontend

Next.jsReactTypeScriptNode.jsPythonFastAPIFigma

Let’s build

Have an idea that needs AI to actually work?

Tell me what frontier workflow you want to build. I’ll bring multi-agent architecture, automations, data pipelines, product design, DevOps and a swarm of agents to ship it.

Start a conversationEmail me directly