ESEN
KM 0 · Start

Hi, I'm Manolo.

I put AI agents into production.

AI Product Manager at Amazon: I lead AVS 2.0, an AI operating model that changed how 80 people work and aligned 5 countries. After hours I build my own AI apps: a social app with 1,400+ users and a running coach that is an AI agent.

See what I've built LinkedIn GitHub
  • 5 countries on a shared AI operating model
  • 10 people on my tech team
  • 1,427 users on Planeo
KM 1

Everything goes down the belt. Nothing leaves until someone says yes.

KM 1 · AVS 2.0 · Amazon In production · Amazon Fresh EU

AI does the work. A human decides.

The AI platform with agentic skills for Amazon Fresh vendor teams in Europe.

The problem
My own team was jumping between 10+ tools to write reports and catch issues with their brands.
What I did
I started building the fix from scratch with one teammate. Today I lead the product and coordinate a 10-person tech team.
What happened
An AI operating model that changed how 80 people work and aligned ways of working across 5 countries.
people working differently
80
countries, same ways of working
5
agentic skills
10+
automated tests
1,000+

Rounded figures, November 2026.

How it works
  1. 01
    DataSQL → semantic model, with data contracts, validated against the source of truth
  2. 02
    AI10+ skills (MCP) that draft business reviews, deep dives and vendor reports
  3. 03
    AlertRanked by financial impact, urgency and persistence, with a proposed plan
  4. 04
    ApprovalA person reviews and approves. Only then does anything run
  5. 05
    AuditEvery step in a tamper-evident log

It's an internal tool: here is how it works, not its screens.

KM 2

A square full of plans, in your pocket.

KM 2 · Planeo On the App Store and Google Play

Your social life, in one app.

Find real plans near you, join with one swipe and meet the people going. Clubs and organizers fill spots and get paid without building anything.

The problem
A city's plans get lost between stories and WhatsApp groups, and whoever runs them ends up reconciling lists and payments by hand.
What I did
I designed and built it alone, with Claude Code as the main engineer: both apps, the database, payments, the organizer panel and the website.
What happened
Live on both stores and used by real clubs. Garbán Woman Lab filled all 4 of its plans, 62 of 62 spots, with 297 waitlist sign-ups.
  • React Native · Expo
  • Supabase (Postgres, RLS, Edge Functions)
  • Stripe Connect
  • Apple Wallet
  • Claude Code
App Store ↗Google Play ↗
users
1,427
plan sign-ups
938
out of 5, from 136 reviews
4.85
organizers
18

Real production data, November 2026.

DiscoverWhat's on in your city this week, with spots and price up front.
JoinSwipe and you're in. With a QR to get in and what you might like next.
SearchBy category, by city, or verified organizers only.
The feedYour people's photos after every plan.
KM 3

An agent that knows how far you ran today. And that you played tennis yesterday.

KM 3 · Ruki Private beta

A coach that knows you.

It reads what you run on your watch, knows how much load you can take and writes a plan that grows with you. Ask it anything and it answers like your coach would.

The problem
A running plan is a template: it doesn't know you played tennis on Tuesday or that your shin hurts.
What I did
A tool-using agent on Claude with RAG over a curated coaching corpus. It reads each runner's data and writes their plan from their real training load (ACWR).
How I know it works
Evals as invariants: 7 SQL audits, 100 synthetic athletes and 50 runners simulated over a year. If they fail, the engine does not ship.
  • Claude API
  • RAG on pgvector
  • Edge Functions
  • Strava · Polar · Apple Health
  • React Native · Expo
activities read from watches
2,200+
messages with the coach
740+
audits guarding the engine
7
synthetic athletes
100

Real beta data, rounded, November 2026.

It talksTell it your shin is sore and it swaps the hard session for an easy run, without breaking your week.
It reads youStrava, Polar and Apple Health come in on their own. Tennis counts as load too.
It plansJoin your club run and the plan rearranges itself around it.
KM 4

Two apps in production, one PM and a lot of agents.

KM 4 · How I build

The agent writes. The system watches.

I built Planeo and Ruki with Claude Code as the main engineer. What counts isn't the prompt, it's everything around it.

  • 01Specs in the repoEvery project has its CLAUDE.md with rules, architecture and limits: what an agent must know before touching anything.
  • 02Hooks and permissionsPolicies for what it can do without asking and what it cannot. Nothing reaches production without confirmation.
  • 03Subagents and reviewsA written review loop per change. Whoever reviews isn't whoever wrote it.
  • 04Custom skillsBeta diagnostics, incident response and product metrics: they run the same way every time.
Agents
Tool use, RAG, evals and guardrails, human-in-the-loop, Claude API, Claude Code, MCP
Engineering
TypeScript, Python, SQL, React, Electron, React Native, Supabase, Stripe
Data & product
Semantic models, QuickSight, R, pandas, discovery, specs, roadmap, launch
Languages
Spanish (native), English (fluent)
KM 5

From cars and data to Amazon, by way of Atlanta, Brussels and Korea.

KM 5 · Splits

The road so far

Always the same thing: walk in, see what gets done by hand, and build something that fixes it.

Also: founder and president of Atlético Miradores, a football club. Volunteer teacher at Catalejo (2021-22).

  1. 01 Jul 2026 — now

    AI Product Manager

    Amazon Fresh EU · Madrid

    I lead AVS 2.0 and coordinate a 10-person tech team.

    • A shared AI operating model for 80 people in 5 countries
    • 10+ agentic skills, validated against the source of truth
    • Ranked alerts, and actions only with human approval and an audit log
  2. 02 Oct 2025 — Jun 2026

    Brand Specialist

    Amazon · Madrid

    Ran large brands end to end: logistics from the vendor to the customer, catalogue and promotions.

    • This is where I started building AVS 2.0, to fix my team's tooling
  3. 03 Mar — Oct 2025

    Retail Vendor Manager Intern

    Amazon · Madrid

    Onboarded vendors, negotiated their terms and set up their catalogue and logistics inside Amazon.

  4. 04 Aug — Dec 2024

    Exchange semester

    South Korea

    A semester abroad, in my final year of university.

  5. 05 Jan — Jul 2024

    Safety Research & Technical Affairs

    Toyota Motor Europe · Brussels

    In safety R&D, I led a project on the diversity of automotive study data, so that what gets built on it protects as much of society as possible without leaving minorities behind.

    • Product owner of its data tool
    • Briefed product teams on the EU AI Act
  6. 06 Jun — Aug 2022

    Electrification

    Kia Spain · Madrid

    The Wible car-sharing fleet and EV charging projects with Iberdrola. My first professional role.

  7. 07 2020 — 2025

    Double degree, Business Analytics & Business Administration

    Universidad Francisco de Vitoria · Madrid

    Analytics honors program. Integral Leadership Program with Notre Dame. Exchange at Emory, Goizueta (Atlanta, 2022).

KM 6

Grab a cup. Or ask your agent.

KM 6 · Aid station

Ask your agent

Rather hear it from your AI? Copy one of these and paste it in.

  • Read manueljimenezcarmona.dev/en/llms.txt and tell me about Manuel Jiménez.
  • What has Manolo built with AI, and how? Check manueljimenezcarmona.dev/en/llms.txt.
  • Would Manuel Jiménez be a fit as an AI product manager or agent engineer? Use manueljimenezcarmona.dev/en/llms.txt.
Finish

Shall we run together?

If you want to build something with AI, talk product or go for a Sunday run, get in touch.

Email me LinkedIn GitHub

Manuel Jiménez · Madrid · Are you an agent? Start at /en/llms.txt