Back to Learn

    Lovable AI Prompt Examples, With the Reasoning

    Every example below is a live prompt from our library, quoted verbatim and annotated line by line. No mock examples written for the article: the point is working prompts and reasoning you can reuse, backed by structure data measured across all of them.

    Updated

    What a working prompt looks like, by the numbers

    Before the examples, the shape of the whole library, measured from the 101 prompts themselves at build time. Base prompts cluster tightly around the median because the structure is constant; the channel-optimized Pro variants run roughly twice the length because distribution mechanics take words to specify.

    Prompt length across the library, in words
    Shortest base prompt211Median base prompt250Longest base prompt307Average Pro variant197
    Prompt length across the library, in words
    Categorywords
    Shortest base prompt211
    Median base prompt250
    Longest base prompt307
    Average Pro variant197

    Computed from all 101 library prompts at build time. Base is the free version; Pro is the channel-optimized variant (101 prompts carry one).

    SaaS MVP with User Auth

    SaaS App · built for Product-led Growth

    The flagship prompt, and the one whose Pro version is open to everyone as a teaser. Auth and roles come before any screen that depends on them, which is the ordering mistake that costs SaaS builds the most rework.

    # Context
    Build the foundation of a multi-tenant SaaS: users sign up, get a workspace, and invite teammates who arrive in the same workspace with the right role. The target user is a small team adopting a tool together, so the invite must work before anything is polished.
    
    ## Core Features (Priority Order)
    1. Email and password auth with session persistence across refresh
    2. Workspace created automatically on first sign-in, creator becomes owner
    3. Member list with three roles: owner, admin, member
    4. Invite by email via tokenized link that joins the invitee to the inviter's workspace
    5. Role-gated UI: only owner and admin can invite or change roles
    
    ## Access & Session Rules
    - Roles are read from the database per request, never from client state
    - Protected routes redirect signed-out users to sign-in and return them after
    - Sessions persist across refresh and expire gracefully with a re-auth prompt, not a crash
    - An expired or already-used invite shows a clear error and a way to request a new one
    
    ## Screens & States
    - Sign in / sign up with inline validation, no alert() dialogs
    - Member list: loading skeleton, and an empty state that prompts the first invite
    - Invite dialog with a copyable link and a sent-state confirmation
    
    ## Build Order
    Auth and the route guard first. Then the role-checking helper, before any UI that depends on a role. Then workspace and member reads, then the invite write path including the expired-token case.
    
    ## Safe-Guard Instructions
    - Enforce roles in the database with row-level security as well as in the UI; hiding a button is not access control
    - Never accept a role or workspace id from the client on writes
    - Do not weaken a security policy to make a query work; if the query is denied, the query is wrong

    Why this works

    • Role-based access is in the Context line, not buried in the feature list, so the permission model shapes every screen instead of being retrofitted.
    • Session persistence is named explicitly. Generated auth that forgets the user on refresh is the most common silent failure in this category.
    • The safeguard section bans plain-text passwords and demands graceful session expiry: constraints that survive later edits.

    Table UI with Sorting & Filters

    UI/UX · built for Product-led Growth

    The workhorse UI prompt. Tables are where generated apps quietly fall apart at scale, so this one names the performance strategy up front.

    # Context
    Build a data table for production volumes: sorting, filtering and pagination driven server-side, the current view encoded in the URL, and rendering that stays smooth at ten thousand rows. Tables are where generated apps quietly collapse; this one is specified against that.
    
    ## Core Features (Priority Order)
    1. Column sorting, single-column with direction, ascending and descending, indicator visible
    2. Filters per column type: text contains, select of known values, date range
    3. Sort, filters and page encoded in the URL; a pasted link reproduces the exact view
    4. Row virtualization past a row threshold; the DOM never holds ten thousand rows
    5. CSV export of the current filtered result, not just the visible page
    
    ## Data & Performance
    - Sorting and filtering execute in the database; the client never sorts a partial dataset and pretends
    - Filter changes debounce and cancel in-flight requests; stale responses never overwrite fresh ones
    - Row selection supports select-all-matching with an explicit count, distinct from select-visible
    
    ## Screens & States
    - Loading skeleton rows on first load; a subtle refresh indicator on filter changes
    - Empty-by-filter offers clearing the newest filter; empty-table states differ
    - Active filters render as removable chips above the table
    
    ## Build Order
    Server-driven pagination and sorting first, then filters with URL encoding, then virtualization, then selection and export.
    
    ## Safe-Guard Instructions
    - Export runs server-side against the filter set with a row cap and count warning
    - URL state is validated on parse; a crafted URL must not inject filter logic
    - Column headers are buttons with aria-sort; the table remains navigable by keyboard

    Why this works

    • Virtual scrolling is requested in the stack section, because asking after 10,000 rows exist means a rebuild rather than an edit.
    • URL-persisted filter state is a one-line request that makes the table shareable and back-button-safe, and almost nobody prompts for it.
    • The implementation order (table first, then sorting, then filters) stops Lovable generating filter UI wired to nothing.

    Landing Page + Email Opt-In

    Landing Page · built for Organic SEO

    The highest-intent page type in the library. The prompt starts from the conversion job, not from a layout.

    # Context
    Build a single-purpose landing page: capture an email address before a product launches. The visitor arrives from one known traffic source, so the page carries one offer and one action, and nothing that competes with them.
    
    ## Core Features (Priority Order)
    1. Hero: the offer in one sentence, the form visible without scrolling
    2. Email capture writing to Supabase with UTM parameters stored per signup
    3. Inline success state replacing the form, no redirect, no alert
    4. Duplicate handling: resubmitting the same address confirms instead of erroring
    5. A substantive copy body below the fold: what it is, who it is for, three concrete FAQs
    
    ## Capture & Consent
    - Client and server-side email validation; the server is the one that counts
    - Store source, utm_source, utm_medium, utm_campaign and referrer on every row
    - One-line consent text under the form stating what will be sent and how to leave
    
    ## Copy & Conversion
    - One accent color, used by the submit button and nothing else
    - Proof elements are placeholders clearly marked as placeholders; never invent names or numbers
    - Maximum 65 characters per line of body copy; generous vertical rhythm
    
    ## Build Order
    Static page with final copy first, so something exists to index. Then the form and write path with duplicate handling, then UTM capture, then analytics last.
    
    ## Safe-Guard Instructions
    - The signups table accepts inserts and forbids reads from the client, with no exceptions for debugging
    - No second call to action anywhere on the page
    - The form must not lose the typed address on a validation error

    Why this works

    • “Optimized for lead generation” leads the Context, so the email capture is the page's spine rather than a widget added to a hero.
    • Supabase is named as the destination, forcing the write path to exist. A form with nowhere to send the address is the classic generated-landing-page failure.
    • Social proof is scoped to placeholders. The prompt does not ask Lovable to invent testimonials, because it will, and fabricated proof on a live page is a liability.

    We ran the landing page prompt. Here is what came out.

    On 31 July 2026 we pasted the email opt-in prompt above, unedited, into a fresh Lovable project on the free plan. One round, no follow-up prompts. The whole build, including Lovable enabling its Cloud backend, consumed 1.8 credits of the free plan's 5 daily. What came back:

    The landing page Lovable generated from the prompt: a hero with the offer in one sentence, an email form above the fold, and consent text under the submit button
    The generated page, untouched. Hero, form above the fold, one accent color on the one button, consent line under the form: all five priority features from the prompt are present in round one.
    The same page after submitting an email address: the form is replaced by an inline 'You're on the list' confirmation, with no redirect
    After submitting a test address: the inline success state replaces the form, no redirect, no alert, exactly as the prompt specifies. Resubmitting the same address confirms instead of erroring.

    Two honest observations from the run. First, Lovable respected the safeguard section: it reported the signups table as write-only from server code, with no client reads. Second, the copy Lovable wrote for the page contained an em dash and an invented brand name, which is why the prompt scopes proof elements to placeholders: the structure came out right on the first try, the words are yours to replace.

    The pattern behind all three

    Different categories, same skeleton: the job in the first line, numbered priority, named components instead of adjectives, states and safeguards requested in round one, and a build order that stops Lovable generating UI it cannot wire up. The how-to-write-prompts guide explains each section, including why the structure is also the cheap way to build under Lovable's usage-based pricing.

    The other 98 prompts are free in the library, organised by category and growth channel. If none fits, the generator writes one in this structure for your idea.

    Frequently asked

    Can I copy these prompts directly into Lovable?
    Yes, that is what they are for. Every example on this page is a live prompt from the library, not a mock written for the article, and the full library is free to browse and copy. Replace the audience and the offer before running one: those two lines change what Lovable prioritises more than anything else.
    Why do all the examples follow the same section structure?
    Because the structure is the technique. Context, numbered features, visual style, technical requirements, implementation order and safeguards each remove one failure mode. The how-to-write-prompts guide walks through why each section exists and what skipping it costs.
    What is the difference between the base and Pro versions?
    The base version builds the app. The Pro version adds the distribution mechanics for a specific growth channel, which is why it runs about twice the length: it carries a Growth Features section naming what the app needs to be findable through that channel. The Pro layer is open to everyone on the SaaS prompt below, as a teaser.
    How many prompts are in the full library?
    101, across six categories, each tagged with the growth channel it serves. All of them are free to read and copy; the paid tiers cover the generator and the channel-optimized variants.

    Written by

    Marco Kohns

    Marco Kohns

    Founder of ProtoBites - Venture Growth Studio

    Growth PM at a Silicon Valley scale-up (a16z and General Catalyst backed), ex-Techstars where he consulted 13 early-stage startups, Reforge-trained. Every prompt on this site comes out of shipping ProtoBites' own portfolio products.