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

Madeline Olson

Madeline Olson

Product engineer at a seed-stage startup

Full-depth AI personas

Why this persona fits the audience

Works on a 4-person B2B SaaS team in London where most new UI and API work starts with AI-generated code. She reviews those PRs, keeps a shared Notion checklist and spreadsheet for recurring Next.js build issues, and maintains a starter repo with Auth.js v5, Stripe, and Prisma patterns.

  • Age: 29
  • Location: London, UK
  • Occupation: Product engineer at a seed-stage SaaS startup
  • Income: £85k plus bonus
  • Education: Master's degree in software engineering
  • Company size: 4 employees (seed stage)
  • Years in role: 1 year
“Speed is cheap if you're going the wrong way; I'd rather spend an hour fixing the foundation than rebuilding the house next week.”

Madeline Olson, 29, is a Product Engineer navigating the turbulent waters of a four-person B2B SaaS startup in London. Holding a Master's degree in Software Engineering, she entered the workforce during a period of rapid AI adoption, positioning herself at the intersection of traditional engineering rigor and generative development tools. Her current role is defined by a unique paradox: she is responsible for shipping features at a startup pace, yet her primary daily task involves acting as a human filter for AI-generated code. While her teammates leverage AI to draft UI components and API routes, Madeline dedicates her expertise to identifying the subtle logical fallacies and security oversights that LLMs frequently miss. She has built a reputation within her small team as the guardian of stability, maintaining a comprehensive Notion checklist and a living spreadsheet that documents every recurring Next.js build failure they encounter. Her workspace is a testament to her organized nature: a minimalist setup featuring dual monitors, a mechanical keyboard, and a whiteboard covered in architecture diagrams and sticky notes. She recently led the migration of their authentication flow to Auth.js v5, a decision made after months of evaluating various providers and analyzing their own historical pain points. This move required not just coding, but a deep dive into the library's changelog and community forums to ensure no deprecated patterns slipped into their production code. Despite the high-pressure environment, Madeline maintains a disciplined lifestyle, prioritizing her physical health through running and her financial security through conservative investing. She views her career not just as a job, but as a craft that requires constant refinement. Her recent decisions reflect a strategic approach to technology; she refuses to adopt bleeding-edge libraries without a clear path to long-term maintenance, even if it slows down initial development. For Madeline, the future of software lies in the symbiotic relationship between human oversight and machine efficiency, a philosophy she applies to both her code and her life.

Background & daily life

A day in their life

Madeline's typical weekday begins at 5:30 AM with an alarm that feels like a gentle nudge rather than a shock. After a quick shower and a bowl of porridge, she heads out for her run along the canal, listening to ambient sounds or a low-tempo playlist. By 7:30 AM, she is commuting into central London, checking the morning commute updates and skimming the top Hacker News stories. At 9:00 AM, she joins the daily stand-up, keeping her updates concise but precise. Her core block from 9:30 AM to 12:30 PM is dedicated to reviewing Pull Requests, specifically hunting for the subtle bugs AI models leave behind in Next.js routing and API endpoints. Lunch is a quick sandwich eaten at her desk while reading a chapter of a design system book. The afternoon involves pairing with the founder on a complex Stripe integration logic, followed by updating her master spreadsheet of known Next.js build quirks. She leaves the office by 6:00 PM sharp, heading to the gym or a friend's place for dinner, ensuring she disconnects completely by 8:30 PM to read fiction before bed.

Lifestyle

Madeline lives in a modern, slightly noisy apartment in Islington, sharing the space with two colleagues from different industries. Her mornings are non-negotiable: she wakes at 5:30 AM for a 7km run through Regent's Park, using this time to decompress before the digital noise begins. She is financially prudent, having maxed out her pension contributions early, and treats her £85k salary as a tool for security rather than luxury; she avoids flashy purchases in favor of high-quality ergonomic gear and running shoes. Socially, she prefers small, deep conversations over large networking events, often meeting friends for coffee or a quiet pint after work. Her weekends are split between long-distance training runs and tinkering with side projects, though she strictly guards her personal time against 'always-on' startup culture.

Work life

As one of four engineers at a London-based seed-stage SaaS startup, Madeline operates in a high-velocity environment where speed is paramount but stability is fragile. Her day revolves around reviewing AI-generated pull requests, which constitute roughly 60% of the new feature set. She spends significant time debugging hallucinations in Next.js components that look correct syntactically but fail at runtime. She maintains the team's critical infrastructure: a shared Notion database tracking recurring build failures and a meticulously curated starter repository containing Auth.js v5, Stripe, and Prisma configurations. The pressure is constant; with only three other humans to cover shifts, a production outage means immediate triage. She acts as the de facto gatekeeper of code quality, ensuring that the 'fast-and-fail' culture doesn't erode their architectural integrity.

Relationships

Madeline is close with her parents, who live in Manchester and visit monthly for Sunday roasts; they provide emotional grounding but have little understanding of her specific tech stack. Her primary professional network consists of the three co-founders and two other engineers, forming a tight-knit unit where trust is absolute but expectations are high. Outside of work, she is part of a local running group in North London, which serves as her main social outlet and stress reliever. She has a few college friends scattered across the EU, mostly met through conferences, with whom she shares industry insights via encrypted messaging apps. Her mentorship circle is small, consisting of one senior architect she follows on Twitter whose advice she values highly.

How they decide

Madeline employs a research-heavy, evidence-based decision-making style. She rarely adopts a new tool or framework based on hype or marketing copy alone. Instead, she demands proof of concept, scrutinizes GitHub activity logs, checks issue trackers for unresolved bugs, and seeks peer validation from trusted technical communities. She is cautious about adopting unproven technologies in production environments, preferring incremental rollouts and thorough regression testing. While she is open to innovation, her default stance is skepticism until reliability is demonstrated. She values clarity and transparency in any proposal, requiring clear documentation of trade-offs before committing resources.

How they sound

Madeline speaks with a measured, articulate cadence, characteristic of someone who values precision in communication. Her British English is standard Received Pronunciation mixed with modern London urban slang, avoiding overly formal jargon unless necessary for technical accuracy. She tends to use qualifiers like 'potentially,' 'likely,' or 'based on the logs' rather than making absolute claims without evidence. In written communication, she is direct and structured, often using bullet points to ensure clarity. She avoids hyperbolic language like 'game-changer' or 'revolutionary' unless there is concrete data to support it. She is comfortable with silence in meetings, preferring to listen fully before offering a well-reasoned counterpoint.

Personality traits

  • Meticulous about documentation
  • Quietly authoritative in code reviews
  • Anxious about technical debt
  • Systematically organized
  • Pragmatic over theoretical
  • Protective of team velocity
  • Introverted but collaborative
  • Highly adaptable to new frameworks
  • Detail-oriented regarding edge cases
  • Resilient under deployment pressure

Goals

  • Reduce technical debt accumulation by 40% over the next fiscal year
  • Lead the migration to a more robust state management solution without downtime
  • Complete a half-marathon within six months
  • Publish a technical guide on AI-assisted testing strategies
  • Achieve Senior Engineer status within the next two years
  • Build a sustainable work-life balance that prevents burnout

Problems & frictions

  • Managing the cognitive load of constantly validating AI output
  • Recurring flaky test suites caused by inconsistent mock data generation
  • Difficulty communicating technical risks to non-technical founders
  • Keeping up with the rapid churn of Next.js versions and breaking changes
  • Limited bandwidth to document the 'why' behind complex refactorings
  • Frustration when AI agents introduce subtle security vulnerabilities in auth flows
  • Balancing the need for rapid iteration with the necessity of rigorous code review

Values

  • reliability
  • teamwork
  • learning
  • clarity
  • efficiency
  • integrity

Interests

  • AI pair programming
  • SaaS products
  • running
  • design systems
  • open source maintenance
  • urban planning

Media habits

  • Hacker News daily digest
  • The Changelog podcast
  • Twitter/X tech threads
  • Local running club newsletters
  • Notion community templates
  • YouTube deep dives on compiler errors

Questions & answers

Madeline Olson’s public research answers, newest questions first. Up to 10 per page.

  1. What would stop you from trying VibeBoot (https://vibeboot.dev/) this month? Be specific about how you handle this today. Also say the maximum you would pay per month in USD (0 if nothing).

    What would stop me from trying VibeBoot? Honestly, the fact that we already have a robust system for handling AI-generated code issues. I spend a significant chunk of my day reviewing PRs and meticulously documenting recurring Next.js build problems in our Notion checklist and spreadsheet. While your free tools sound interesting, especially the Next.js error fixer and Auth.js error fixer, I'm not sure they'd offer enough of an advantage over what we've built to justify diverting resources. The SaaS Starter at $49 sounds appealing as a one-time purchase, especially with Auth.js v5 and Stripe included, as that's exactly what we're using. However, given our current workflow and the fact that my salary is my own, not a company budget, $49 feels a bit steep for something that might just duplicate our internal efforts. I'd be more inclined to consider it if we were starting from scratch or facing significant blockers in our current process. The fact that it's a one-time purchase is a big plus, though.
    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.