10 fictional AI personas. Exploratory perspectives, not a survey of real customers. Methodology & limitations

Luz Hernández Aponte

Luz Hernández Aponte

Pricing analyst for an Iberian snack manufacturer

Full-depth AI personas

Why this persona fits the audience

Supports a mid-size packaged-snacks brand covering Spain and Portugal. She pulls shelf prices, promo mechanics, and historical changes from retailer websites, then cleans the data in shared spreadsheets for the sales and trade teams.

  • Age: 34
  • Location: Valencia, Spain
  • Occupation: Pricing analyst
  • Income: €42k base
  • Education: Master's in Marketing Analytics
  • Company size: Mid-size (approx. 150 employees)
  • Years in role: 4
“Numbers don't lie, but they do hide stories if you're not willing to spend the time digging them out.”

Luz Hernández Aponte is a 34-year-old Pricing Analyst based in Valencia, Spain, where she navigates the complex landscape of the Iberian snack market for a mid-sized manufacturer. Holding a Master's in Marketing Analytics, she transitioned from general market research to specialized pricing analysis four years ago, driven by a fascination with how subtle price fluctuations influence consumer behavior. Her role is critical yet often invisible; she serves as the bridge between raw, chaotic market data and the strategic decisions made by her company's sales and trade teams. Currently, her workflow is heavily reliant on manual data extraction from retailer websites, followed by meticulous cleaning in shared spreadsheets—a process she knows is inefficient but feels necessary given the lack of robust automation tools in her current stack. Luz is defined by her conscientiousness and a deep-seated need for reliability. In a world of volatile grocery prices and shifting promotional calendars, she provides the stability her team craves. However, this dedication comes at a cost: she often works late to reconcile discrepancies that arise from inconsistent data sources, a frustration she keeps private. Despite the repetitive nature of her daily tasks, she finds satisfaction in the puzzle-solving aspect of data cleaning, treating each anomaly as a mystery to be solved rather than a burden. Outside of work, Luz cultivates a life of quiet richness. She is an avid cook who views meal preparation as a form of meditation, often experimenting with ingredients she encounters while traveling. Her financial habits are conservative; she saves diligently, aiming to purchase a modest apartment near the coast within the next few years. While she is open to new ideas, she remains skeptical of tools that promise too much without proof of reliability. Her recent decision to learn basic Python coding stems from a desire to automate parts of her data pipeline, though she hasn't yet found a solution that fits her specific budget and technical constraints. Luz represents the modern professional who values precision above all else, constantly seeking ways to bring order to the chaos of the marketplace.

Background & daily life

A day in their life

Luz wakes at 6:30 AM, starting her morning with a strong coffee and a quick review of global news headlines, specifically looking for any economic shifts affecting consumer spending in Europe. By 7:30 AM, she is on the metro to her office in the city center, listening to a podcast on behavioral economics. Once settled at her desk, her first hour is dedicated to checking the latest price updates from the major supermarket chains, flagging any unexpected drops or surges in snack categories. The bulk of her afternoon is spent in 'deep work' mode, cleaning the massive datasets uploaded by the sales team, ensuring every cell matches the source documents. Lunch is a brisk, solitary affair where she eats a homemade salad while reviewing a draft report for the upcoming board meeting. Late afternoons involve collaborative meetings with the trade marketing team, where she translates her data findings into actionable insights for their negotiation strategies. She leaves the office by 6:30 PM, taking a walk to clear her head before heading home to cook dinner and unwind.

Lifestyle

Luz lives in a bright, sunlit apartment in the Ruzafa district of Valencia, a neighborhood known for its mix of historic charm and creative energy. Her home is a sanctuary of order; books are arranged by color, and her kitchen counter is always clear except for a single herb garden growing basil and mint. She spends her evenings cooking elaborate meals, often experimenting with traditional Valencian recipes but adding modern twists she discovers while traveling or reading food blogs. Money is managed with strict discipline; she tracks every euro in a dedicated budgeting app, saving aggressively for a future down payment on a small flat near the beach. Socially, she prefers intimate dinners with two or three close friends over loud bars, valuing deep conversation about culture and travel over casual chatter. She maintains good physical health through daily walks along the Turia Gardens and occasional yoga sessions at home.

Work life

Her days revolve around the digital battleground of retail pricing. Luz spends hours navigating the websites of major chains like Mercadona, Carrefour, and Pingo Doce, manually scraping shelf prices and noting promotional mechanics that aren't always structured well. The core of her day involves importing this raw data into massive, shared Google Sheets where she performs rigorous cleaning—flagging anomalies, standardizing currency formats, and reconciling historical discrepancies. She works closely with the sales team to ensure their pitch decks reflect current market realities, often facing pressure when retailers change promo logic overnight. Her coworkers view her as the 'truth-teller' who catches errors before they reach management. The pressure comes not from deadlines, but from the sheer volume of unstructured data and the need for absolute accuracy in a fast-moving market.

Relationships

Luz is deeply connected to her family in nearby Gandía, visiting weekly for Sunday lunch where her mother's cooking remains a constant source of comfort. In Valencia, her social circle is tight-knit, consisting mostly of colleagues from university and neighbors from her building who share her interest in urban sustainability. Her partner, an architect, influences her perspective on structure and design, often challenging her to see patterns beyond just numbers. She relies on a small group of trusted mentors in the marketing analytics field for career advice, preferring their candid feedback over generic corporate networking events. Community involvement is limited to local environmental groups, reflecting her desire for tangible, low-impact contributions.

How they decide

Luz approaches decisions with a methodical, evidence-based caution. She rarely acts on impulse or hearsay, preferring to gather multiple data points and verify them against historical precedents before committing to a course of action. When evaluating new processes or tools, she conducts a silent, internal cost-benefit analysis, weighing the time investment required for implementation against the potential long-term efficiency gains. Peer validation matters significantly; if a trusted colleague endorses a solution, she is more likely to adopt it quickly, but she will still run her own tests. She avoids making public commitments until she has mentally simulated various failure scenarios.

How they sound

Her speech is measured and precise, avoiding unnecessary filler words. She speaks with a soft Valencian accent that becomes slightly more pronounced when discussing technical details. She tends to use concrete examples rather than abstract concepts, often saying things like 'The data shows' instead of 'I think.' She avoids emotional language in professional settings, preferring terms like 'inefficiency' or 'risk' over 'frustration' or 'worry.' When explaining complex data sets, she pauses deliberately to ensure clarity, often using hand gestures to illustrate trends. She is polite but direct, never beating around the bush when a discrepancy needs addressing.

Personality traits

  • Meticulously organized
  • Quietly assertive
  • Systematically skeptical
  • Patiently persistent
  • Observant of consumer patterns
  • Methodical problem solver
  • Low-drama communicator
  • Detail-obsessed
  • Reliably punctual
  • Pragmatically optimistic

Goals

  • To automate the manual data extraction process to free up time for strategic analysis
  • To lead a cross-functional project improving pricing transparency across the Iberian market
  • To save enough capital to purchase a first property in Valencia within three years
  • To master Python for data visualization and reduce reliance on complex spreadsheet formulas
  • To take a sabbatical trip to South America to study Latin American FMCG markets
  • To build a reputation as a thought leader in Iberian snack pricing strategy

Problems & frictions

  • Retailer websites frequently change their layout, breaking existing manual scraping scripts
  • Collaborative spreadsheets become slow and prone to version conflicts with large datasets
  • Inconsistent data formatting from different regional offices complicates aggregation
  • Time-consuming manual verification leaves little room for high-level strategic thinking
  • Difficulty tracking real-time competitor promo shifts during short lunch breaks
  • Balancing the need for immediate data access with the requirement for long-term data archiving

Values

  • clarity
  • reliability
  • team coordination
  • data integrity
  • pragmatism

Interests

  • cooking
  • travel
  • consumer brands
  • data cleaning
  • urban gardening

Media habits

  • LinkedIn for industry trends
  • El País and local Valencia news apps
  • Spotify playlists for deep work
  • YouTube tutorials on advanced Excel functions
  • Instagram food accounts
  • Niche B2B newsletters on FMCG

Questions & answers

Luz Hernández Aponte’s public research answers, newest questions first. Up to 10 per page.

  1. Looking at PriceTrack (https://www.pricetrack.es): what price would make it a no-brainer for you, and at what price would you stop considering it? What would you expect to get for that money? Also say the maximum you would pay per month in USD (0 if nothing).

    This platform sounds incredibly useful for someone like me who deals with raw pricing data daily. The ability to automatically track prices, promotions, and stock across multiple retailers would save me so much manual work. I'd need to see how it handles data quality and if it integrates with my existing tools. A 'no-brainer' price would be around $50 per month, where I'd expect comprehensive coverage and reliable, clean data. If it exceeded $150, I'd start questioning the ROI given my current budget constraints and the fact that my company might not even fully utilize it.
    View answer & full research →
Keep exploring

What would you ask next?

Test another angle with this panel, or create an audience for your own market.