Andrew Crossley

How do you build an AI MVP?

SHORT ANSWER

Build an AI MVP by choosing one task where being right 80% of the time is still useful, wrapping a hosted model rather than training your own, and designing the interface around correction — users must be able to see, edit and accept output. Set an evaluation set before launch, measure task success and human-override rate, and only consider fine-tuning once the workflow itself is proven.

Answered by Andrew Crossley, AI Product Consultant & Product Partner · Updated 2026-08-01

Why it matters

AI products fail at the workflow layer, not the model layer. The model is a commodity; the useful part is where it sits in someone's job.

Without evaluation, teams ship confidently wrong output and discover the problem through churn instead of through data.

How it works in practice

  1. 1

    Pick a tolerant task

    Drafting, summarising, classifying, triaging. Avoid tasks where a single wrong answer is unacceptable until you have evaluation and guardrails.

  2. 2

    Start with a hosted model

    Use a gateway to a frontier model. Model choice is a tuning decision later; the workflow is the risk now.

  3. 3

    Build the evaluation set first

    Fifty to a hundred real examples with expected outputs. Run it on every prompt or model change. This is the single highest-leverage practice in AI product work.

  4. 4

    Design for correction

    Show the reasoning or source, allow editing, and capture every correction. Corrections are your training data and your quality metric.

  5. 5

    Instrument the honest metrics

    Task success rate, human-override rate, time saved per task, and cost per successful task — not tokens processed.

  6. 6

    Only then optimise

    Cheaper models, caching, retrieval or fine-tuning, chosen against the evaluation set rather than intuition.

Common mistakes

  • Building a chat box because it is easy, when the user needed the answer inside their existing workflow.
  • Fine-tuning before there is any evidence the task is valuable.
  • No evaluation set, so quality changes are invisible until users complain.
  • Ignoring inference cost per task until the unit economics are already negative.

FROM EXPERIENCE

Where AI features actually earn their cost

The AI features that hold up in production are the boring ones: triaging inbound requests, drafting a response someone edits, extracting structured data from messy input. Each replaces a repeated manual step with a reviewable draft.

The ones that fail are open-ended assistants bolted onto a product, where the user has to invent the use case themselves.

Frequently asked

Do I need my own model?

Almost never at MVP stage. Hosted frontier models plus good prompting and retrieval cover the vast majority of use cases.

How do I stop hallucinations damaging trust?

Ground answers in your own data, show sources, and design the UI so output is reviewed rather than auto-applied.

How much does an AI MVP cost in the UK?

A focused commercial AI MVP with one core journey typically sits around £12,000–£25,000 with a product-led AI-assisted build. RAG, agentic workflows, multiple roles, complex integrations or sensitive-data requirements can move it above that range.

What does an AI MVP cost to run?

Model spend varies heavily by model, context size and workflow. Measure cost per successful customer task and per active user rather than assuming a fixed per-call number will describe the economics of the product.

IN SHORT

  • One tolerant task, hosted model, workflow-first design.
  • Evaluation set before launch; measure task success and override rate.
  • Optimise cost and model choice only after the workflow is proven.

Build your AI MVP in 5 days

The self-paced course for founders shipping their first AI product.

Build your AI MVP in 5 days

THE FRAMEWORK

The Crossley Method: idea to first revenue in seven stages

See the full method
  1. STAGE 1DiscoverWeek 1
  2. STAGE 2ValidateWeek 2
  3. STAGE 3PrototypeWeek 3
  4. STAGE 4Build MVPWeeks 3-4
  5. STAGE 5LaunchWeek 5
  6. STAGE 6First RevenueWeek 6
  7. STAGE 7ScaleOngoing

MORE ANSWERS

Idea to MVP

How do you build an MVP?

Build an MVP by picking one job a specific user will pay to have done, designing the single shortest flow that completes it, and shipping only that. Validate demand before building — interviews plus a paid or committed signal. A focused build can take four to six weeks; allow roughly six to twelve weeks from idea to public launch when validation, pilot users and fixes are included.

How much does an MVP cost in the UK?

In the UK, a focused commercial MVP with one core user journey typically costs about £12,000–£25,000 with a product-led, AI-assisted build. A clickable or lightweight validation prototype can cost roughly £3,000–£8,000. Multiple user roles, complex integrations, RAG or agentic AI, specialist compliance or premium design can move the project above £25,000; larger agency builds can reach £60,000–£150,000.

Can a non-technical founder build an AI app?

Yes. A non-technical founder can build and validate an AI app in 2026 using tools such as Lovable, Cursor or Bolt without first hiring a full engineering team. The founder still needs to own the customer problem, scope, accounts, data access, AI quality, costs and launch decision. Use specialists for the parts where a mistake creates real security, reliability or commercial risk.

What happens after building an app with Lovable?

After your Lovable app works, do not automatically rebuild it. First validate that real users want the core journey, then audit authentication and data access, billing, error handling, backups, monitoring, AI quality and cost per user. Fix launch blockers in risk order and add analytics before public release. Rebuild only when the existing architecture genuinely cannot support the business you have evidence for.