Saved

Photo β†’ Pattern β†’ Futures β†’ First Move

See what a place could become.

Upload one property photo, answer the obvious questions, and get a believable first plan: what the place is trying to become, where the ideas sit, and what to test first.

1Upload one clear photo
2Tell VerdeAI the situation
3Create your futures board
4Copy, save, or export the plan

Start here

Create your result board.

Upload a photo or run the self-test. VerdeAI will build a clear board with six futures, a recommendation, and one first move.

⬜ Photo ⬜ Situation ⬜ Main problem ⬜ Analysis
Next best action

Upload a photo or use demo mode to begin.

Need a no-upload test?

Run the shaded garden self-test. VerdeAI will simulate photo upload, starter clue, analysis, report, Vision Board, and a saved project card.

Autosave is ready.

v7.3 keeps a local recovery copy while you test, so closing the page should not mean starting from zero.

Tester pass

Share this without explaining the whole thing.

Ask testers to do one quick loop: upload a real photo, tap the closest starter clue, read one overlay card, then copy the tester summary or send quick feedback. For app checks, use the public tester page or shaded garden self-test first.

  1. Upload or demo
  2. Tap one clue
  3. Read overlay
  4. Save or export
Public Tester Page

Share this first

One photo. One clue. One visual idea.

This is the simplified page for real testers. They should not need to understand the whole app. Upload a photo or run the shaded self-test, then look at the plant overlay and first move. AI rendering is being prepared, but the safe beta still shows concept overlays until you choose a paid provider.

  1. 1Upload or run self-test
  2. 2Tap one starter clue
  3. 3Screenshot the plant overlay
  4. 4Copy the tester summary
Plant Overlay Preview

Plant overlay mockup, not a final AI render yet. It is meant to show where ideas could sit on the actual photo.

Generated workspace

Six possible futures

The cards will become more specific once you run an analysis.

Waiting for a photo or demo run.

Property DNA

What VerdeAI noticed

    Biggest warning

    Run the analysis first. The garden oracle refuses to guess before coffee.

    Site clues

    Add a main problem and property note to make the result sharper.

    Best first move

    Run the analysis and VerdeAI will choose one cheap, reversible action to test.

    Next steps
      Live report preview
      
                      
      Original
      Selected future overlay
      Future Scorecard
      Property movie β€” 5 year evolution
      Action Roadmap
      Risk / Confidence Notes
      Plant / material palette
      Printable VerdeAI Report

      Copy this after testing. v6.2 keeps the current analysis stable, improves the public dashboard polish, and prepares render prompts without charging for AI.

      Design Studio

      Refine selected future

      These controls change style only. In v6.0 the analysis stays locked and autosaved, so design refinements cannot reset the situation, pattern, main problem, or overlay labels.

      Safe to test: tick Cleaner / minimal, then check Report or Vision Board. The result should stay on the same analysis.

      AI Prompt Preview
      Send this to a tester

      One clean handoff

      Copy the tester result, send it with one screenshot, and ask for one simple reply: useful, confusing, or not believable yet.

      1. Run a real photo or self-test.
      2. Tap Copy clean tester result.
      3. Send it with one screenshot of the board.
      4. Ask: β€œWould you try the first move?”
      Tester Export

      Shareable test summary

      Use this when sending VerdeAI to an early tester by text, Messenger, Facebook, or a feedback form. Keep it short: one board screenshot, one copied result, one question.

      Alpha Readiness
      AI Render Roadmap

      Real rendering, safely locked until the backend is ready.

      VerdeAI still uses free concept boards. v7.3 keeps real rendering safely locked while adding the backend connection checklist for a future one-image render test: pick one future, preview the prompt and likely cost, then only render after a secure backend confirms everything.

      Real AI renderingDisabled
      BackendNot connected yet
      API keyNot added
      Paid callsLocked
      Need the setup guide? Jump straight to the plain-English steps for connecting real rendering later.
      Real render setup guide
      Current status

      Safe mode: real rendering is still off.

      Frontend stays on GitHub Pages. A backend/proxy will handle provider calls later. Replicate / FLUX remains the first candidate. One render comes first, and cost is shown before anything paid happens.

      GitHub Pages frontend Backend/proxy handles provider calls Replicate / FLUX first candidate One render first Cost before rendering
      What happens next?
      1 Choose one future 2 Preview prompt 3 Preview cost 4 Confirm one render 5 Keep concept board if render fails
      Choose first render provider

      Recommended path: start with one provider and one image.

      VerdeAI is ready to plan real rendering, but paid rendering stays disabled until a backend proxy, server-side API key, and cost confirmation are in place.

      OpenAI image generationPlanned

      Strong prompt-following option, but pricing and image workflow should be tested carefully before all-six rendering.

      Needs backend proxy and server-side OpenAI API key.
      Stability AIPlanned

      Credit-based image provider option. Useful later if it gives better cost or style control for property concepts.

      Needs backend proxy and server-side Stability API key.
      Recommended safe first path Not ready yet β€” ready later
      1. Choose one provider only: start with Replicate / FLUX.
      2. Render one future image only.
      3. Show the estimated cost before rendering.
      4. Keep the concept-board fallback if the render fails.
      5. Require a second confirmation before rendering all six futures.

      First provider setup checklist

      1
      Backend host chosen Netlify Functions, Cloudflare Workers, Vercel, or a small backend.
      2
      Provider account ready Use one provider first; Replicate / FLUX is the recommended first test path.
      3
      Server-side API key Stored only in backend environment variables, never in frontend code.
      4
      Endpoint tested /api/render/estimate works before /api/render is unlocked.
      5
      Cost lock confirmed One render requires cost confirmation; all six require a second confirmation.
      Deployment limits

      GitHub Pages is fine for the app, not for secret API keys.

      GitHub Pages can host VerdeAI's public interface, but it cannot safely hide provider API keys. Real rendering needs a backend/proxy layer.

      Real rendering status:Disabled until a backend host, server-side key, endpoint test, and cost lock are all ready.
      Netlify FunctionsGood static-site companion for serverless API routes.Possible first backend path.
      Cloudflare WorkersLightweight edge functions with environment variables.Good low-cost candidate.
      VercelSimple serverless functions with frontend hosting options.Strong developer path.
      Small backendMore control, but more setup and maintenance.Later option.
      Which backend host should I use?

      Recommended first path: keep the frontend where it is, add one small proxy.

      GitHub Pages can keep hosting VerdeAI's public interface. The first real render test only needs a small serverless proxy that hides the provider key, estimates cost, and renders one future after confirmation.

      Netlify FunctionsSimple first path

      Good match if VerdeAI is later moved to Netlify or you want a familiar static-site + function setup.

      Needs: Netlify project, environment variable for provider key, one serverless render function.
      Cloudflare WorkersGood proxy path

      Good fit if you want to keep the current frontend and add a separate lightweight render proxy.

      Needs: Cloudflare account, Worker secret for provider key, CORS allowed for the VerdeAI site.
      VercelDeveloper-friendly

      Strong option if the project later becomes a fuller web app with API routes and deployments together.

      Needs: Vercel project, environment variable, API route deployment.
      Small custom backendLater

      Most control, but more setup, maintenance, and hosting decisions. Not the best first test.

      Needs: server hosting, deploy process, environment variables, monitoring, and CORS setup.
      Recommended next setup step

      Choose one backend host, add a server-side Replicate API key there, test /api/render/estimate, then unlock one confirmed mock-to-real render. Do not render all six until one image is reviewed.

      Real render setup guide

      When I am ready to connect real rendering.

      Use this later, only when one paid image test is worth it. Paid rendering stays disabled until every safety step is done.

      Current status

      Real renderingDisabled BackendNot connected yet API keyNot added Paid callsLocked
      Simple summary
      • Frontend stays on GitHub Pages.
      • A backend/proxy handles provider calls.
      • Replicate / FLUX is the first candidate.
      • Render one image first.
      • Show cost before rendering.
      1Keep GitHub Pages frontendThe current public page can stay where it is.
      2Choose backend/proxyNetlify Functions or Cloudflare Workers hides the provider key.
      3Create Replicate accountUse Replicate / FLUX for the first landscape-style test.
      4Add server-side API keyStore the key only in backend environment variables.
      5Test estimate endpointCost preview must work before any paid render unlocks.
      6Render one image onlyOne future first. All-six rendering stays locked.

      What will cost money?

      • Provider image generation once real rendering is enabled.
      • Possibly backend hosting if free limits are exceeded.
      • Repeated renders, especially all-six future sets.

      What stays free?

      • The current GitHub Pages frontend.
      • Concept boards, mock render previews, reports, sharing, and saved projects.
      • Prompt preview and cost-estimate rehearsal before provider connection.
      Do not do this yet

      Do not paste API keys into index.html, JavaScript files, GitHub Pages settings, screenshots, or public GitHub files. Real provider keys belong only in a backend host's secret environment variables.

      Backend connection checklist

      What happens later when real rendering is enabled.

      This is the future connection path only. v7.3 still makes no paid calls, keeps all providers disabled, and uses mock render previews until a backend is configured.

      1Frontend sends requestThe browser sends the chosen future, prompt, and analysis to VerdeAI's backend.
      2Backend checks settingsThe backend confirms provider, key, mode, CORS, and request limits.
      3Backend estimates costThe estimate endpoint returns the likely price before any paid render is unlocked.
      4User confirms one renderOnly one future image is allowed for the first real test.
      5Backend calls providerThe provider key stays server-side. The browser never sees it.
      6Image or fallback returnsThe frontend shows the rendered image, or keeps the concept board if rendering fails.

      Before connecting real rendering

      Backend host chosenNetlify Functions or Cloudflare Workers selected.
      Replicate account readyProvider account exists for the first FLUX test.
      API key server-sideKey stored only in backend environment variables.
      Estimate endpoint tested/api/render/estimate works before rendering unlocks.
      Render endpoint mock-tested/api/render is checked in mock mode first.
      Cost limit confirmedOne-image test limit agreed before any paid call.
      Current v7.3 status

      Ready to plan the backend connection. Not ready to make paid renders. Keep GitHub Pages as the frontend and only connect a backend when you are ready for one controlled image test.

      AI Render Setup

      Choose a future provider plan

      Rendering is not connected yet. These controls only prepare the plan, prompts, mock results, and cost warnings. Nothing paid happens from this static page.

      Replicate / FLUXPlanned option for realistic image generation. Needs backend key.planned
      OpenAI image generationPlanned option for prompt-led image generation. Needs backend key.planned
      Stability AIPlanned option for credit-based rendering. Needs backend key.planned

      Safety rule: API keys belong in server environment variables only. VerdeAI will not make paid image calls until a backend proxy is configured and you confirm the cost.

      Render readiness checklist

      Before paid renders

      One-future render rehearsal

      Choose one future before spending anything

      This is a safe simulation. Pick a future, preview the property-specific prompt, check the estimated cost, then confirm a mock render. No provider is contacted in v7.1. This is only a rehearsal for the future paid render flow.

      Cost rule: real rendering will start with one image only. All six futures stay locked behind a second confirmation when a backend provider is connected.

      First real provider setup

      What is needed before real images?

      This is the practical path before VerdeAI can turn one concept board into a real AI-rendered image. It stays disabled until each item is handled safely.

      1Backend hostingA server endpoint must run the render request, not the browser.
      2Server-side API keyThe provider key goes in environment variables only.
      3Provider accountChoose one provider first: Replicate / FLUX, OpenAI, or Stability.
      4Cost estimateShow the estimated price before any paid render happens.
      5Render one image firstOnly unlock all six futures after the first render is reviewed.
      Developer detailsBackend proxy contract

      Future endpoint shape

      The browser should call VerdeAI's own backend. The backend then calls the image provider using a private API key stored in server environment variables.

      v7.1 scaffold ready:GET /api/render/providersPOST /api/render/estimatePOST /api/render
      POST /api/render
      {
        futureId,
        provider,
        prompt,
        imageReference,
        confirmCost: true,
        maxCostUsd,
        count: 1,
        fallback: "concept-board"
      }
      Render Prompt Builder

      Generated from the current property analysis, selected future, starter clue, visible-site language, and design refinements. Copy one prompt to test manually with a provider later, or use the mock render buttons to check the flow without spending money.

      Deployment

      Netlify-ready static package

      1. Unzip this package.
      2. Drag the full verdeai-v7.3 folder into Netlify.
      3. No build command is required.
      4. Open the generated link and test shaded self-test β†’ result board β†’ copy tester result β†’ AI Setup safe-mode check.

      Included files

      • index.html
      • styles/main.css
      • js/app.js
      • config.js
      • netlify.toml and _redirects
      • CHANGELOG.md and BUILD_STATUS.md
      Property Futures Board Property Futures Dashboard

      Generated result board

      Your property futures board.

      Every upload, demo, or self-test becomes one clear result: today’s property, six futures, VerdeAI’s recommendation, and one practical first move.

      After a board is ready, this button takes testers straight to the result.

      Your board is ready

      Result summary

      Upload, demo, or self-test to create your board.

      VerdeAI will summarise the best future, why it fits, and the first practical move here.

      Your property today
      Six possible futures

      Generated from the current photo, selected clues, and VerdeAI pattern logic. These are concept boards, not final AI renders yet.

      5-year property movie
      Optional AI rendering

      v7.3 keeps AI rendering optional and secondary. No paid image calls are made here; every result board uses honest concept boards until a safe backend rendering provider is connected.

      Tester Mode

      60-second tester pass

      v6.0 is designed so an early tester can create a Property Futures Board, copy a short result, and give one useful sentence of feedback without you explaining every button.

      Owner shortcut:

      Use this first when you just want to check the app works without uploading the same photo again.

      1. Upload one real property photo or use demo mode.
      2. Use the Next best action button if unsure.
      3. Tap the closest starter suggestion. It runs the analysis automatically.
      4. Read the first overlay card and the Best first move.
      5. Open Export and copy the tester invite or summary.
      6. Save feedback before leaving, or tell the owner what felt fake or useful.

      Questions for testers

      • Did the six futures make you see the property differently?
      • Did the result feel specific to the photo and situation?
      • Which future would you actually try?
      • Was one first action clear enough?
      • Did the clue coaching make it clear that this is not full AI vision yet?
      • What felt fake, confusing, or unfinished?
      Project History

      This records useful tester actions such as photo upload, starter clue, analysis, save, and design refinement.

        Climate profile

        Add a postcode and run analysis to generate a basic climate clue.

        Maintenance calendar

        Vision Board

        Quick view of the current future, overlay labels, design direction, and first experiment. The labels now sync with the latest analysis result.

        Saved Local Projects

        Saved in this browser/domain only. v6.0 also autosaves the current session after upload, clue, analysis, design, and report changes.