# Léonard Henriquez

> Co-founder & CTO of Topo (YC W24). I build the infrastructure AI agents run on: durable execution, context, search and orchestration.

Coding since twelve, then business school and product. Co-founder and CTO of Topo (YC W24), where our AI SDR went from $0 to $1M ARR in three months.

## Profile

- [Full profile](https://hqz.me/index.md): about, key figures, every project, principles, recognition and contact, in one Markdown file (same content as https://hqz.me/llms-full.txt).
- [Career](https://www.linkedin.com/in/leonard-henriquez/): every role and school with dates, on LinkedIn only.
- [Website](https://hqz.me/): the HTML version.

## Projects

- [Topo](https://hqz.me/projects/topo.md): AI agents for B2B outbound sales, used by 150+ customers including Air France and Aircall. I designed the platform: durable agent workflows on Temporal, the Playbooks engine, a search index of about a billion profiles, and an MCP server with 170+ tools. (Released, 2022–present)
- [Self-driving engineering](https://hqz.me/projects/self-driving-engineering.md): Rebuilt how a five-person team releases software around coding agents: a harness that lets agents install, run, test and observe the whole product, strict CI gates, and a path from customer feedback to a preview, a demo video and a one-click release. (Released, 2025–2026)
- [Company Brain](https://hqz.me/projects/company-brain.md): A shared Markdown memory that the team and its agents both read and write. At Topo: a Go daemon syncing to S3, compare-and-swap writes, LLM-resolved merges and an MCP server. As a product: provenance, review and permissions for every fact. (Released, 2026)
- [Software Factory](https://hqz.me/projects/software-factory.md): Turns websites and apps without APIs into read-and-write MCP tools for agents. A pipeline captures how a site behaves, distills it, generates the connector, runs it, and heals it when the site changes. (Building, 2026)
- [Agent Control Plane](https://hqz.me/projects/agent-control-plane.md): A control plane for background coding agents: any harness, any sandbox, self-hosted by small teams. Launching a task is decoupled from where it runs. It grows out of the background-agent platform I built at Topo. (Building, 2026)
- [Version control for agents](https://hqz.me/projects/version-control-for-agents.md): One trunk where every change lands signed by the agent that made it, conflicts resolve as they happen, and any agent’s work can be rolled back. A layer over plain Git, not a replacement. (Exploring, 2026)
- [Durable execution on S3](https://hqz.me/projects/durable-exec-s3.md): What Temporal would look like if S3 were the database: durability on the server, thin clients in any language, primitives for agents that run for hours. (Exploring, 2026)
- [Search for agents](https://hqz.me/projects/agent-search.md): An S3-native engine shaped around how agents query: many precise, iterative queries that mix full text, vectors and filters. (Exploring, 2026)
- [System 1 judges](https://hqz.me/projects/system-1-judges.md): Fast, calibrated scoring: a judgment split into dozens of yes/no questions, answered as probabilities by a decision model in one call and aggregated in code. First use case: outbound emails. (Exploring, 2026)
- [Low-cost inference ASIC](https://hqz.me/projects/inference-asic.md): How low can the cost per million tokens go on a mature 12 nm node, with LPDDR and an SRAM cache instead of HBM? (Study, 2026)
- [MLP: neural networks from scratch](https://hqz.me/projects/mlp.md): A neural network written three times, in 2012, 2015 and 2026, now a small C++ library with no dependencies that reads handwritten digits with 97.4% accuracy on MNIST, live in the terminal. (Released, 2012–2026)

## Contact

- Contact: LinkedIn (https://www.linkedin.com/in/leonard-henriquez/)
- GitHub: https://github.com/leonard-henriquez
- Website: https://hqz.me/