Tools Guides for Product Managers & AI Builders
Every tools guide Builders Camp has published so far.
When to use an AI agent vs a workflow
Use a workflow when you can draw every step before the first input arrives, and an agent only when the path depends on...
Andre AlbuquerqueAI coding agent terms product managers need to know
Four terms out of this whole vocabulary change a product manager's decisions: context window, tool use, guardrails and...
Andre Albuquerque & Guilherme SalgueiroHow to use AI for accessibility review, and where it stops
Deque's analysis of more than 2,000 audits and nearly 300,000 issues found automated testing completely covered 57...
Andre Albuquerque & Ricardo LuizHow 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 & Tiago Pedro da CostaHow 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 & Tiago Pedro da CostaHow 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 & Tiago Pedro da CostaHow to use AI for churn analysis and still know why they left
Separate voluntary from involuntary churn first, because a failed card and a disappointed customer need different fixes...
Andre Albuquerque & Mário AraújoHow to use AI for cohort analysis without reading noise as a trend
Below roughly 100 members per cohort, a weekly retention grid is mostly noise: an observed 30 percent on 40 users...
Andre Albuquerque & Mário AraújoHow to use AI for competitive analysis that survives a check
Rank your sources by how costly it is for the company to be wrong in them: filings, terms of service, published price...
Andre Albuquerque & Mário AraújoAI for competitive battlecards: one sourced link per claim, or the row does not ship
A battlecard is a claim document built on facts you do not control, so the method matters more than the writing: every...
Andre Albuquerque & Mário AraújoHow to use AI for customer feedback analysis without losing the evidence
Customer feedback analysis with AI holds up when the codebook exists before the model runs, every theme carries...
Andre Albuquerque & Mihaela DraghiciHow to use AI for customer interviews without handing it the room
AI belongs in three slots around a customer interview and in none of them during it: drafting and de-biasing the guide...
Andre Albuquerque & Mihaela DraghiciAI for customer onboarding content: write for activation, then check whether it moved
Onboarding content is the largest body of copy most teams never audit, and AI makes it trivial to double it and...
Andre Albuquerque & Ricardo LuizHow to use AI for design feedback that is not just taste
Ask for a review against Jakob Nielsen's 10 usability heuristics, one row per heuristic, pass or fail, with the...
Andre Albuquerque & Ricardo LuizHow 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 & Tiago Pedro da CostaAI for executive summaries: writing for someone who reads 200 words
An executive summary is five sentences: what happened, the number, why now, what it cost, and what you need from the...
Andre Albuquerque & Inês LourençoHow to use AI for funnel analysis without trusting a broken step
A funnel drop-off tells you where people leave, never why, and roughly half the dramatic drops in a first analysis are...
Andre Albuquerque & Mário AraújoHow 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 & Tiago Pedro da CostaAI for internal comms: the announcement is easy, the tone edit is the job
A model drafts an internal announcement in under a minute and gets the structure roughly right and the register wrong...
Andre Albuquerque & Inês LourençoHow to use AI for jobs to be done research on real transcripts
A job statement is only as good as the struggling moment behind it, and that is the exact part a model invents first...
Andre Albuquerque & Mihaela DraghiciAI for launch planning: build the plan from the scope, not from a template
A launch plan generated from a generic checklist is wrong before you read it, because it does not know what you cut...
Andre Albuquerque & Inês LourençoHow to use AI for market research you can actually defend
Decide the threshold before you size anything: nobody needs the market number, they need to know whether the...
Andre Albuquerque & Mário AraújoAI for meeting prep: walking into a decision meeting already argued with
Thirty minutes of prep changes a contested decision meeting more than an extra day of analysis: one sentence naming the...
Andre Albuquerque & Inês LourençoAI for negotiation prep: rehearsing positions before the room decides them
Negotiation prep with a model is two artefacts: a grid of interests and priced tradeables, and a rehearsal where the...
Andre Albuquerque & Inês LourençoHow to use AI for OKRs that survive contact with the quarter
The highest value use of AI on OKRs is the stress test, not the draft: ask for the data source and query behind every...
Andre Albuquerque & Inês LourençoHow to use AI for persona research that survives its first challenge
A persona built by AI is only as good as the transcripts behind it, and the useful discipline is one extra column: for...
Andre Albuquerque & Mihaela DraghiciAI for positioning and messaging: variants are cheap, the differentiator is not
A model will write eight positioning variants in the time it takes you to write one, and every one of them is available...
Andre Albuquerque & Inês LourençoHow to use AI for pricing analysis without trusting what people say they will pay
The highest-value pricing analysis AI can run is not a survey, it is the billing replay: recompute every historical...
Andre Albuquerque & Mário AraújoHow to use AI for prioritization when an AI score is an argument, not an answer
A model will score 60 backlog items on RICE in about two minutes, and at least two of the four inputs it uses will be...
Andre Albuquerque & Inês LourençoHow to use AI for product analytics without waiting on an analyst
Three question types are safe to hand a model with no analyst in the room: recomputation, definition archaeology, and...
Andre Albuquerque & Mário AraújoWhat AI for product discovery actually speeds up, and what it quietly breaks
AI safely speeds three parts of a discovery loop and should not touch the other two. Recruiting messages, interview...
Andre Albuquerque & Mihaela DraghiciHow to use AI for product documentation that survives the next release
Documentation fails on maintenance, not on drafting, so point AI at drift detection before you point it at writing...
Andre Albuquerque & Guilherme SalgueiroAI for product marketing: five stages, and the two AI should not decide
Product marketing runs as a loop of five stages: market insight, narrative and positioning, product exploration, launch...
Andre Albuquerque & Inês LourençoHow to use AI for product ops work that repeats every week
Product ops work splits cleanly into two piles, and only one is automatable: recurring artefacts with a right answer...
Andre Albuquerque & Guilherme SalgueiroAI for product presentations: structure first, slides second
A decision deck needs nine slides, and slide one is the ask. AI fills that structure from a source document in a single...
Andre Albuquerque & Inês LourençoAI 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 & Tiago Pedro da CostaHow to use AI for roadmap planning without outsourcing the sequence
The useful AI move in roadmap planning is synthesis, not sequencing: paste six categories of scattered input and get...
Andre Albuquerque & Inês LourençoAI for sales enablement: turning product truth into material reps will use
Sales enablement fails on usability, not volume: reps use material that is short, true and findable in the ninety...
Andre Albuquerque & Inês LourençoHow 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 & Tiago Pedro da CostaHow to use AI for stakeholder updates people actually read
Hand a model your notes and it drafts a complete weekly update in about a minute, which is the right division of labour...
Andre Albuquerque & Inês LourençoHow to use AI for support ticket triage without confusing volume with severity
Support triage makes four calls: what kind of request this is, who answers it, how urgent it is, and whether it signals...
Andre Albuquerque & Mário AraújoUsing AI for survey analysis without producing a confidently wrong summary
AI earns its place in survey analysis on one job: coding open-text answers into fixed categories consistently across...
Andre Albuquerque & Mário AraújoHow to use AI for usability test analysis without losing the evidence
A model will code five transcripts against your code list in minutes and tally how many participants hit each problem...
Andre Albuquerque & Mihaela DraghiciHow to use AI for user flows without losing the edge cases
A model will draft a plausible happy path in under a minute, which is the boring half of the work and worth automating...
Andre Albuquerque & Ricardo LuizWhich AI tools for user research fit which kind of research?
Pick the tool from the research type, not the other way round: transcription plus a general model covers moderated...
Andre Albuquerque & Mihaela DraghiciWhat an AI wireframe generator is actually good for
A generated wireframe settles two things: what is on the screen and in what order. It settles nothing about whether the...
Andre Albuquerque & Ricardo LuizBest AI Tools for Product Managers in 2026
The best AI tools for product managers in 2026 are not one tool but four categories: a reasoning and writing assistant...
Andre AlbuquerqueBest MCP servers for product managers, chosen by the job you need done
Choose an MCP server by the product job it does and by whether it offers a read-only path, not by how often it appears...
Andre Albuquerque & Guilherme SalgueiroBest vibe coding tools for product managers
There is no single best vibe coding tool, but there is a right first one: pick a prompt-to-app builder if nobody on the...
Andre Albuquerque & Ricardo LuizBolt.new for product managers
Bolt.new turns a prompt into a running full-stack app inside an in-browser environment, with a free plan of 1 million...
Andre AlbuquerqueHow to build a personal AI operating system as a product manager: five layers and a loop
Build a personal AI operating system in five layers, in order: context about you and your work, connections to your...
Andre AlbuquerqueHow 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 Lovable
A Lovable prototype starts with a structured prompt, not a feature list, and a masterplan.md file that keeps the AI...
Andre Albuquerque & Ricardo LuizHow 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 Build an AI Assistant with MCP
Building an AI assistant with MCP means adding one or more MCP servers to an AI tool like Claude Code, scoping each...
Andre Albuquerque & Guilherme SalgueiroHow to Build an MVP with Replit
Building an MVP in Replit means scoping the smallest usable version, letting Replit Agent build and deploy it from a...
Andre AlbuquerqueChatGPT for product managers
ChatGPT for product managers works best as a set of Projects, each with its own instructions and attached files, rather...
Andre AlbuquerqueHow 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 & Tiago Pedro da CostaHow to run a competitor teardown with Claude Code without inventing facts
A competitor teardown in Claude Code is worth running only if every factual row can name the saved source file it came...
Andre Albuquerque & Guilherme SalgueiroHow to manage context in Claude Code when you are a product manager
A Claude Code session degrades once the transcript fills with superseded decisions, and the fix is four habits: check...
Andre Albuquerque & Inês LourençoHow to triage customer feedback with Claude Code and keep every quote traceable
Triage works when every theme cites the row identifiers behind it, which means the export has to stay a file with...
Andre Albuquerque & Inês LourençoHow to pull product data without SQL using Claude Code
Profile the dataset before you query it: column types, distinct values in every small column, null counts, and the date...
Andre Albuquerque & Guilherme SalgueiroHow to run a design review with Claude Code
Give Claude Code the spec and the component file, and ask for a table of every requirement with present or absent and a...
Andre Albuquerque & Ricardo LuizClaude Code first week for product managers: a day by day ramp
Five days, 30 to 45 minutes each, ending with one artefact a colleague actually read. The ramp works because each day...
Andre Albuquerque & Guilherme SalgueiroClaude Code hooks: what they enforce that CLAUDE.md cannot, and how to use them in a product workflow
Claude Code hooks are commands Claude Code runs at a fixed lifecycle event, and a PreToolUse hook that exits with code...
Andre Albuquerque & Guilherme SalgueiroHow to build a launch checklist with Claude Code
Build the checklist from two inputs: the diff, which tells you what actually changed, and the spec, which tells you...
Andre Albuquerque & Inês LourençoHow to turn meeting notes into decisions with Claude Code
A decision record needs four fields per decision: what was decided, who owns it, what would reverse it, and the...
Andre Albuquerque & Inês LourençoHow to analyse product metrics with Claude Code
Claude Code analyses a metrics export by writing a script against the file and running it, so you get the number and...
Andre Albuquerque & Mário AraújoClaude Code permissions and safety for product teams
Permission rules are evaluated deny, then ask, then allow, and a deny at any level cannot be overridden anywhere else...
Andre Albuquerque & Inês LourençoClaude Code plugins for product managers, and how to ship one to your team
A Claude Code plugin bundles skills, agents, hooks and MCP servers into one installable directory with a manifest, so a...
Andre Albuquerque & Guilherme SalgueiroHow to verify AI-generated code as a product manager, before it merges or reaches a decision
Verify AI-generated code by asking for evidence instead of a summary: the test output, the build result, a screenshot...
Andre Albuquerque & Inês LourençoHow to synthesise a roadmap with Claude Code, and where the agent must not decide
An agent can assemble every roadmap input into one candidate list with sources attached and name the contradictions...
Andre Albuquerque & Inês LourençoClaude Code setup for product managers: install to first useful output
A working Claude Code setup takes one install command, one login and one project folder, and Anthropic's quickstart...
Andre Albuquerque & Guilherme SalgueiroHow to build Claude Code skills for product managers
Convert a prompt into a skill on its third use, not its first. A skill is a folder holding a SKILL.md file with a name...
Andre Albuquerque & Guilherme SalgueiroHow to build Claude Code slash commands for PM work
A slash command is one markdown file whose filename becomes the command, so .claude/commands/standup.md becomes...
Andre Albuquerque & Guilherme SalgueiroHow to use Claude Code subagents for PM workflows
A subagent runs one slice of a job in its own context window and hands back only the summary, which is why a four-hour...
Andre Albuquerque & Guilherme SalgueiroClaude Code use cases for product managers, and what each one is good for
Twelve Claude Code jobs are worth a product manager's time, and only five of them need repository access at all. The...
Andre Albuquerque & Guilherme SalgueiroHow to synthesise user research with Claude Code
Synthesise in two passes rather than one: code each transcript on its own, then cluster those codes across transcripts...
Andre Albuquerque & Inês LourençoClaude 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 & Tiago Pedro da CostaHow 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 & Tiago Pedro da CostaHow to write a CLAUDE.md file as a product manager
Keep CLAUDE.md under 200 lines and fill it only with rules that are true in every session on this project, which for a...
Andre Albuquerque & Guilherme SalgueiroClaude Code CLAUDE.md vs skills vs hooks vs subagents: where each rule belongs
Put a rule in CLAUDE.md if Claude must always know it, in a skill if it is needed only for some tasks, in a hook if it...
Andre Albuquerque & Guilherme SalgueiroCursor 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 CostaHow to debug AI generated code when you are not an engineer
Debug AI generated code with a fixed loop: reproduce the bug on purpose, read the full error, ask the AI to explain...
Andre AlbuquerqueWhy vibe coded apps look generic, and how a design system prompt fixes it
Vibe coded apps look generic because prompts describe features, not a look, so the tool falls back on its default...
Andre Albuquerque & Ricardo LuizFigma for product managers
Figma for product managers means using its prototyping mode to connect static frames into a clickable flow you can test...
Andre AlbuquerqueGemini for product managers
Gemini is Google's AI model family, delivered through a standalone chat app and built into Gmail, Docs, and Sheets on a...
Andre AlbuquerqueGitHub Copilot for product managers
GitHub Copilot is an AI pair programmer that suggests code inside a developer's existing editor, with plans running...
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 & Tiago Pedro da CostaHow to Become an AI Product Manager
Becoming an AI product manager means adding an evaluation and guardrail layer on top of the core PM skills you already...
Andre AlbuquerqueHow to Build an AI Product from Scratch
Building an AI product from scratch starts with naming what a wrong answer costs, not what a right one looks like...
Andre AlbuquerqueHow to Design an AI Agent
Designing an AI agent means deciding what it can see, what it may use, when a human has to approve its action, and what...
Andre AlbuquerqueHow to prototype with AI: from idea to clickable MVP
Prototype with AI in five steps: write the landing copy, map the shortest first-time user flow, list the minimum...
Andre AlbuquerqueHow to use AI as a product manager
Use AI as a product manager by auditing your recurring work first, ranking tasks by how much time they take and how...
Andre AlbuquerqueHow to Write Evals for AI Products
An eval set is a fixed list of real inputs and the pass or fail rubric you score them against before any prompt or...
Andre AlbuquerqueJagged frontier AI: what product managers should hand to AI and what to keep
The jagged frontier is the uneven line between tasks AI handles well and tasks it gets confidently wrong, and the two...
Andre AlbuquerqueLovable for product managers: what it is good for and where it stops
Lovable is good for three PM jobs: clickable prototypes that answer whether to build something, small internal tools...
Andre Albuquerque & Ricardo LuizLovable knowledge base: give Lovable a memory with project knowledge, source-of-truth docs and a task backlog
The Lovable knowledge base is two text fields, workspace knowledge and project knowledge, that Lovable reads on every...
Andre Albuquerque & Ricardo LuizHow to make AI write in your voice: samples, hard rules and banned phrases
To make AI write in your voice, give it three to five real samples of your writing instead of adjectives, a short list...
Andre AlbuquerqueMake.com for product managers
A Make.com scenario starts with one trigger, chains together one or more action modules through field mapping, and...
Andre AlbuquerqueMCP for analytics tools, and the read-only boundary that keeps it safe
Analytics over MCP replaces the weekly assembly job, not the dashboard: you ask the question in plain language and get...
Andre Albuquerque & Mário AraújoMCP 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 & Tiago Pedro da CostaMCP for product managers, and what the protocol actually changes
MCP is an open standard, announced by Anthropic on 25 November 2024, for connecting an AI application to external...
Andre Albuquerque & Guilherme SalgueiroMCP security for product teams, and the approval boundary to agree first
The MCP specification names user consent, data privacy and tool safety as key principles and then states plainly that...
Andre Albuquerque & Inês LourençoMCP setup for product managers, from first connection to first useful answer
You can connect an MCP server in the Claude apps with a URL and no command line, on any plan from Free to Enterprise...
Andre Albuquerque & Guilherme SalgueiroMCP troubleshooting for product managers, five failures and how to tell them apart
Almost every broken MCP connection is one of five things: it never connected, it is not authenticated, it is registered...
Andre Albuquerque & Guilherme SalgueiroMCP vs plugins and integrations, and when a protocol beats a point connection
A protocol wins when many clients need many tools, because one server serves every client that speaks MCP instead of...
Andre Albuquerque & Guilherme Salgueiron8n workflows for product managers
An n8n workflow starts with a trigger node, adds one or more action nodes that map data between steps, and ends with a...
Andre AlbuquerqueNo code for product managers: what to build and which tools to use
No code for product managers means building a working product or process from five parts: a database (Airtable), a...
Andre AlbuquerqueNotebookLM for product managers
NotebookLM answers questions strictly from the sources you upload, citing the exact passage each answer draws from...
Andre AlbuquerqueNotion for product managers
Notion for product managers means running PRDs, roadmaps, and sprint rituals as connected databases instead of separate...
Andre AlbuquerquePerplexity for product managers
Perplexity's advantage for a product manager is cited, checkable research by default, organized into persistent Spaces...
Andre AlbuquerqueRAG for Product Managers
Retrieval-augmented generation, or RAG, retrieves the most relevant passages from your own data at answer time and...
Andre AlbuquerqueReasoning model vs fast model: which to use for each PM task
Use a fast model for short, well-defined PM tasks like summarising a call, tagging feedback or drafting a status...
Andre AlbuquerqueA ChatGPT prompt to write SQL queries that get the numbers right
A ChatGPT prompt to write SQL queries works when it carries what the model cannot see: the dialect, the business...
Andre Albuquerquev0 for product managers
v0 turns a text prompt into a working React and Next.js screen built with shadcn/ui components, with a live preview and...
Andre AlbuquerqueVibe coding for product managers, explained
Vibe coding is describing software in plain language to an AI and reviewing what comes back, and for a product manager...
Andre Albuquerque & Ricardo LuizVibe coding mistakes to avoid, and the fix for each
The costly vibe coding mistakes are product mistakes, not coding ones: building before you know the problem, letting...
Andre AlbuquerqueVibe coding projects for product managers
Ten vibe coding projects, each sized to one weekend and each built to prove exactly one product skill, from encoding a...
Andre Albuquerque & Ricardo LuizWhat is agentic coding for product managers, and what changes for you
Agentic coding is the shift from a model that completes your next line to one that explores a codebase, plans an...
Andre Albuquerque & Guilherme SalgueiroWhen not to use an AI coding agent
An AI coding agent earns its cost on work that is large, mechanical, well specified and reversible, which is a narrower...
Andre Albuquerque & Inês LourençoHow to decide which tasks to automate
Automate a task only when it repeats on a schedule, follows rules you can write down, and costs more time over a year...
Andre AlbuquerqueSix workflow automation best practices for non-engineers
Treat every automation like a small product: ship a one-trigger version first, keep it inside the fewest tools...
Andre AlbuquerqueZapier automation ideas for product managers
The Zapier automations worth building as a PM fall into three kinds: product on autopilot (Zaps that run part of the...
Andre AlbuquerqueZapier vs Make for product managers
Zapier wins on the largest app catalog and the fastest path to a first linear automation; Make wins on a lower entry...
Andre Albuquerque