AI Platform
Speco
Vercel for training and deploying AI agents — a company uploads its data, creates a specialist agent, tests it, and deploys it through API/MCP.
Speco is Vercel for training and deploying AI agents. A company uploads its files, docs, and internal knowledge, creates a specialist agent, tests it in the Playground, and deploys it through API and MCP endpoints — without needing to understand prompts, evals, infrastructure, model optimization, or MCP server setup. The platform handles the full lifecycle around the agent: ingestion, dataset generation, evaluation, optimization-strategy recommendation (prompting, RAG, or fine-tuning), per-case quality scoring, Playground testing, API key management, deployment monitoring, and workspace configuration. The simple version: train and deploy AI agents from your data, live at specoai.com.

Media

Speco hero — Turn domain knowledge into deployed specialists.

Six steps from raw data to deployed specialist.

Everything you need in one control plane.

Dashboard overview — specialists, deployments, and pipeline runs.

Playground — interactive specialist testing with real-time inference.

MCP integration — expose specialists as tools for downstream AI agents.
Related collections
Education & Global Exposure
Stanford Visiting Student — Summer 2024
The summer where João's horizon stopped feeling local.
Research & Applied Domain AI
Research & Legal AI
Research foundation → applied legal intelligence.
Startup Ecosystem
YC Startup School — San Francisco 2024
Early pattern-recognition inside the YC ecosystem.