Thiago Portela Teotônio's Work | ContraWork by Thiago Portela Teotônio
Thiago  Portela Teotônio

Thiago Portela Teotônio

AI engineer shipping production RAG and agent systems

New to Contra

Thiago is ready for their next project!

Cover image for Hi Contra, I'm Thiago, an
Hi Contra, I'm Thiago, an AI engineer from Brasília, Brazil. This is Galley Brain, the multi-agent system I run on my own VPS. Each agent owns an area (finance, schedule, operations) and takes real actions through MCP connectors, with Telegram and voice as the interface. It started as my personal assistant and is turning into a product for restaurant owners. I build RAG systems, AI agents and n8n automations for real operations. If you're working on something similar, let's connect.
0
4
Cover image for Galley CRM: a sales CRM
Galley CRM: a sales CRM for restaurant-focused businesses with lead scoring, pipeline stages and a native automation engine (Postgres triggers plus a pg_cron worker). On top of it I built n8n workflows with an AI agent that qualifies leads over WhatsApp and Instagram using CRM tools, and a daily follow-up flow that finds stalled leads, drafts re-engagement messages and decays their score. Built and tested on a dedicated demo instance.
0
6
Cover image for Galley Watch: a food safety
Galley Watch: a food safety compliance SaaS for restaurants. Covers daily checklists, temperature logs, equipment maintenance, document expiry tracking, photo evidence by employee, audits and reports, with a manager dashboard for compliance, non-conformities and overdue maintenance. Multi-tenant architecture on Supabase with row-level security, piloting with a restaurant group.
0
10
Cover image for Galley Kitchen: a SaaS module
Galley Kitchen: a SaaS module that reconciles POS sales against recipe cards to calculate theoretical ingredient consumption and food cost automatically. Covers recipes, pricing, inventory counts, suppliers, quotes and purchase orders. Built on Supabase and PostgreSQL with row-level security and multi-tenant design, tested on real data from a restaurant group
0
15