João Vaz
joaosfvaz@gmail.com · linkedin.com/in/joaovaz00 · joao-vaz.com
I build tools for 12,000+ car dealers and 10M+ visitors.
Product Manager at OLX Group (Motors, B2B), part of Prosus. I set the strategy for a 10-person team, and I build my own agents along the way.
Tools for car dealers by day. After hours, chess, sport and a camera.
The lighter version of my site: what I do for fun, some of my photos and the things I build on the side. The full CV is one switch away.
Hiring for something specific? or read the quick answers.
- +150%
- weekly engagement across 3 data products, in 18 months
- 12k+
- professional car dealers in PT · PL · RO
- 40+
- experiments — A/B, AA & fake-door
- 75+
- in-person dealer interviews
- 90+
- PMs trained on AI tooling
What I do when the laptop closes.
I build tools for 12,000+ car dealers.
I am a Product Manager at OLX Group (Motors, B2B), part of Prosus. My team builds the products dealers use to price and sell their cars, and I lead the AI agents for our domain in the dealers' assistant.
- +150%
- weekly engagement across 3 data products, in 18 months
- 75+
- in-person dealer interviews
- 90+
- PMs trained on AI tooling
The products I lead for car dealers.
Six products with one job: help a dealer buy the right cars, price them well and sell them faster. I own the strategy and the roadmap across them, from the data pipelines underneath to the screens dealers use.
The dealers' AI assistant is shared by many teams; I lead the part for my domain. That means the agents that answer dealers' questions about their prices, their listings' performance and the market, in plain language, from our own data. I define what these agents may do, put our data behind MCP tools they can call, and test them with test questions, evals and trace reviews.
- Agent specs
- MCP tools
- Evals
- Traces
A machine-learning estimate of what each car is worth from its specs, and how long cars like it take to sell — shown next to the dealer's asking price, and behind the price label buyers see.
- ML model
- Price-to-market
- Time to sell
Supply, demand, prices and selling speed for every segment of the market, down to the individual competing listings in it — so a dealer can decide what to buy next and how to price what is already on the lot.
- Supply & demand
- Days of supply
- Competitor listings
Views, clicks, saves, messages and calls for every car and for the whole stock, benchmarked against similar cars — the one analytics product every dealer gets, on every plan.
- Funnel metrics
- Benchmarks
The first screen a dealer sees: how the dealership is doing, the health of its stock and alerts that lead straight to the cars that need action — across every branch of a group.
- Stock health
- Alerts
- Multi-branch
One concrete next step per car — renew it before it expires, raise an underpriced car towards its market value, or give it more visibility — from an engine that combines the signals of every product above.
- Pricing
- Renewal
- Visibility
I don't just spec agents. I read their traces.
dealer“Why isn't my Audi A4 getting leads?”
- route → pricing & performance agent38 ms
- tool · listing_performance(car)212 ms
- tool · fair_price(car)187 ms
- mandate · assist · read-only ✓2 ms
- answer · grounded in 2 tool results1.4 s
assistant“It's priced 9% above similar A4s and views fell after day 12. Cars like it sell in about 24 days at market price.”
- correctness
- groundedness
- scope
- plain language
- Evals
- Test questions with known answers for my domain, graded on correctness, groundedness, scope and refusals — so a change is judged on evidence, not on a demo.
- Traces
- I read agent runs span by span to catch invented values, routing errors and the same question getting two different answers.
- Mandates
- What an agent may do for a user: read-only or acting, whether an action can be reverted, and when a human must confirm.
- Automation classes
- Assist, one-click, two-turn and scheduled — each capability gets the lightest class its risk allows.
- Tools & MCP
- Domain data behind MCP tools the agent calls, so answers come from the source, not from the model's memory.
- Context
- Personas, playbooks under a token budget, what an agent is not for and where it hands over.
- Human-in-the-loop
- Human review on critical paths until there are enough traces to trust an LLM judge.
- Skills for PMs
- I wrote the Claude skills rolled out to every PM in our unit, to define their domain's agent and to decide when a change needs a spec.
Three years on one problem: helping dealers sell cars.
Strategy for dealer insights, pricing and recommendations — from the data pipelines to the screens, with stakeholders in five markets.
Outcomes
- +150%
- weekly engagement, 3 data products
- ~72%
- average OKR completion, 2.5 years
- 40+
- experiments — A/B, AA, fake-door
- 90+
- PMs trained on AI tools, 75% now use them
Deliveries
- AI agents for my domainDefined what my domain's agents in the dealers' AI assistant can answer about pricing and listing performance, and tested them with evals and trace reviews.
- Market insights redesignRebuilt the view where dealers see supply, demand and prices for every car segment, on desktop and mobile.
- Segment drill-downLet dealers go from a market segment straight to the competing listings in it, with price, mileage and days on market.
- Consistent listing statisticsMoved listing statistics to one data source, so leads count the same in the product, in sales reports and in BI.
- Product workshop for ~100 peopleCo-designed a two-day workshop for 8 teams, with 8 Claude skills that turn dealer interviews into a scored roadmap.
- AI skills for every PMWrote Claude skills that help each PM define what their domain's AI agent should do, and decide when a change needs a spec.
Same team and scope, on the machine-learning side of the product.
Outcomes
- 75+
- in-person dealer interviews, PL · RO · PT
- 12 mo
- to promotion to Product Manager
Deliveries
- Fair-price estimatesBrought a machine-learning price estimate into the product, so dealers see what each car is worth next to their asking price.
- Time-to-sell estimatesAdded how long similar cars take to sell, estimated from a car's specs.
- Dealer researchInterviewed dealers in person in Poland, Romania and Portugal to understand how they price and sell their cars.
Outcomes
- 6 mo
- from trainee to Associate PM
Deliveries
- Lead-generation discoveryResearched how professional dealers get their leads, to find where the product could help them get more.
- Recommendation experimentsRan A/B tests with Data Science on which types of recommendation to show next to paid-visibility products.
A month-long AI programme by Prosus and the THNK School of Creative Leadership, with people from across the group.
Outcomes
- Selected
- from companies across the Prosus group
- 1 mo
- full time in Amsterdam
Deliveries
- Seller-inbox prototypeBuilt with my team a prototype inbox where an AI assistant screens out buyers who aren't serious.
- Live demo on stagePresented the prototype on stage to the whole programme in Amsterdam.
Toolkit
Agentic AI
AI-assisted building
Data & experimentation
Delivery & technical
CRM & go-to-market
- Education
- MSc Industrial Engineering & ManagementUniversity of Minho & TU Graz · 2021–2023
- Languages
- Portuguesenative
- EnglishC2 · proficient
Things I built myself, from idea to working product.
PM-OS
A knowledge base my team's answers live in, kept true by seven scheduled Claude routines: meetings file themselves and stale pages are made to admit it.
Read more →Team-context MCP
A read-only MCP server that lets the company's internal AI assistant answer stakeholders' questions about my team's work — served from a laptop through a tunnel.
Read more →Portugal Explicado
Taxes, Parliament, laws and the economy of Portugal in plain Portuguese — every number linked to an official source, with open data imported every day.
Visit the site ↗Tabiya
A chess coach that explains every move in plain English: a serverless pipeline downloads my games, analyses them with Stockfish and writes a report.
Read more →Let's build something worth shipping.
Quick answers
- Current role
- Product Manager, OLX Group · Prosus
- Experience
- 4 years in product
- Languages
- Portuguese, native · English, C2
- Based in
- Lisbon, Portugal
- Work setup
- Hybrid
- Relocation
- Open to relocation
- Right to work
- Portuguese and EU citizen: no visa in the EU
- Notice period
- 30 days
- Open to
- Product Manager, AI Product Manager, Data Product Manager and Product Builder roles
Off the clock?
- Level
- XP
- Achievements
- Photos
- Easter eggs
- Time