Tiago Pedro da Costa
As Co-founder & CTO of Zumer, Tiago builds platforms that leverage AI to automate knowledge, improve collaboration, and accelerate sustainability in the construction industry. His work ranges from Abaqus, a platform for project and site management, to an AI-powered assistant supporting BREEAM certification.
29 guides by Tiago Pedro da Costa
Cursor Ask Plan Agent practice exercise
This exercise has you ship one small, real feature or fix using Cursor's Ask, Plan, Agent workflow: explore the...
Andre Albuquerque & Tiago Pedro da CostaCursor vs Windsurf
Cursor and Windsurf are both AI-native code editors built around an agent that edits multi-file projects, and their...
Andre Albuquerque & Tiago Pedro da CostaLovable vs Replit: Which Is Better for Non-Technical Founders?
For most non-technical founders building a first web app with logins and data, start with Lovable: as of October 2026...
Andre Albuquerque +2Do you need a technical cofounder or can you build it yourself with AI
You do not need a technical cofounder to build a prototype or a first MVP with AI tools: one person can now ship a...
Andre Albuquerque +2How to write a technical spec as a product manager
A product manager's technical spec covers what is observable from outside the system: behaviour, constraints...
Andre Albuquerque +2Tiago Pedro da Costa
Tiago Pedro da Costa directs Building with Cursor, Builders Camp's 1 week bootcamp on building with AI in Cursor, with...
Andre Albuquerque & Tiago Pedro da CostaHow to write acceptance criteria with AI
Give a model the story and a state checklist, and it will enumerate the cases you forgot faster than any refinement...
Andre Albuquerque +2How to add Stripe payments to an app built with AI
Use a Stripe Payment Link if you sell one thing and can fulfil by hand, and Stripe Checkout created by your server if a...
Andre Albuquerque +2How to use AI for backlog refinement on a backlog nobody has read in a year
A model can read 400 backlog tickets in one pass and return duplicate clusters, dead items and tickets too thin to...
Andre Albuquerque +2How to use AI for bug reports without inventing the reproduction steps
A bug report becomes actionable at six fields: reproduction steps, expected, actual, environment, frequency and first...
Andre Albuquerque +2How to use AI for capacity planning against real constraints, not optimism
Capacity planning fails on the subtractions, not the total: a model applying holidays, on-call, hiring loops and a...
Andre Albuquerque +2How to use AI for estimation when the model has never met your team
Ask a model to decompose a feature, not to size it: most estimation error comes from forgotten work rather than...
Andre Albuquerque +2How to use AI for incident reviews without losing the blameless part
Use a model for the one part of an incident review that is mechanical: merging deploy logs, alerts and chat into a...
Andre Albuquerque +2AI for QA test cases: expanding acceptance criteria, and what the model will miss
A model turns one acceptance criterion into twenty test cases in seconds, and every one of them tests what the...
Andre Albuquerque +2How to use AI for sprint planning without handing over the commitment
AI is worth about 30 minutes of a sprint planning session: drafting a candidate plan, flagging dependencies and naming...
Andre Albuquerque +2Best AI app builder for PMs and non-technical founders in 2026
Lovable is the best AI app builder for most product managers and non-technical founders: it turns a chat into a...
Tiago Pedro da CostaHow to Build a Prototype with Cursor
Building a prototype in Cursor means scoping a small feature, exploring the codebase with Ask mode, approving a plan in...
Andre Albuquerque & Tiago Pedro da CostaHow to Build a Prototype with Windsurf
Building a prototype in Windsurf means describing the screen or feature to the Cascade agent, using the built-in...
Andre Albuquerque & Tiago Pedro da CostaHow to triage bugs with Claude Code as a product manager
A product manager triaging a bug makes four decisions and none of them is a diagnosis: is it real, who owns it, how bad...
Andre Albuquerque +2Claude Code vs GitHub Copilot for product managers: agent work or completion
GitHub Copilot began as completion inside a developer's editor and added an agent mode; Claude Code began as a terminal...
Andre Albuquerque +2How to use parallel worktrees in Claude Code
Running claude --worktree twice with different names gives you two isolated checkouts of the same repository, each on...
Andre Albuquerque +2Cursor for product managers: Ask, Plan and Agent as three separate jobs
Cursor gives you three modes that map to three different jobs: Ask to understand a codebase, Plan to turn a vague...
Andre Albuquerque & Tiago Pedro da CostaCursor rules for product managers: keeping a generated change inside the lines
A Cursor rule is a markdown file that injects persistent instructions at the start of the model's context, and the four...
Andre Albuquerque & Tiago Pedro da CostaCursor vs Claude Code for product managers: a decision about workflow shape
Cursor and Claude Code now share most primitives, so the real choice is workflow shape: Cursor is a place you work...
Andre Albuquerque & Tiago Pedro da CostaGitHub Copilot for product managers
GitHub Copilot is an AI pair programmer that suggests code inside a developer's existing editor, with plans running...
Andre Albuquerque & Tiago Pedro da CostaHow product managers work with engineers using AI agents
The line between product and engineering work stopped being technical skill and became ownership of consequence: build...
Andre Albuquerque +2Export Lovable project to GitHub and continue in Cursor
Connect the Lovable project to GitHub, clone the new repository, open the folder in Cursor, do your work on a feature...
Andre Albuquerque +2MCP for Jira and Linear, and what each connection can actually reach
The Linear MCP server is read-write by default at mcp.linear.app/mcp, with a separate read-only endpoint one URL away...
Andre Albuquerque +2Vibe coding security checklist before launch, written for product people
Do not put a vibe coded app in front of real users until ten checks pass, and the first four decide most outcomes: row...
Andre Albuquerque +2