Can I vibecode Escourtly?
price $49/moyou'd save $588/yrbuild time multi-daycategory screen-recordingreplaced by 0 people
KINDA
MOATexecution polishintegrationsscale infra
Capture a product as live HTML and replay it as a clickable demo prospects can drive themselves
The Build Prompt
copy it and go buildready to paste · 2,289 chars
Build a personal replacement for Escourtly in an empty repository. Use Next.js 15 with the App Router, TypeScript, Postgres via Drizzle, and rrweb; do not offer alternative stacks. Ship two pieces: a Chrome MV3 extension that captures steps, and a web app that stores and replays them. The core loop is: click through a product with the extension recording, capture each step as an rrweb DOM snapshot, annotate the steps, and publish a clickable walkthrough at a public URL. In the extension, let the user start and stop a capture, and record one snapshot per click along with the click target. Inline stylesheets, fonts and images into each snapshot so the replay renders without calling back to the origin site. Mask input values and anything marked data-private by default, and show what is masked in the editor. In the web app, show a step list with reorder, delete, and an editable title and description per step. Generate a first draft of each step description from the snapshot with an LLM, and let the user overwrite it. Render the replay as an interactive page: the snapshot is live HTML, with a hotspot on the recorded click target that advances to the next step. Add a start overlay and a final call-to-action overlay with a configurable link. Publish each walkthrough at a share URL that needs no login, plus an iframe embed snippet. Count views, step completions and CTA clicks per walkthrough without any third-party analytics. Store everything in your own Postgres and make JSON export straightforward. Put secrets in .env, ship .env.example, and never commit credentials. Include clear empty, loading, success, and recoverable error states. Add input validation, safe slugs, and graceful handling of snapshots that fail to render. Write focused tests for snapshot serialization and one end-to-end capture-to-replay path. Create a README with setup, architecture, how to load the extension, data location, and backup steps. Do not add billing, team accounts, or a hosted control plane. Deliberately leave out custom domains and certificate management. Deliberately leave out CRM integrations. Deliberately leave out capture of canvas, video and cross-origin iframes, and document the limitation in the README. Finish by running the tests and listing the exact commands used.
What you lose
- ✕capture fidelity on canvas, cross-origin iframes, shadow DOM and lazily loaded assets
- ✕no-login share links and embeds that hold up under real traffic
- ✕viewer funnel analytics and lead capture
- ✕CRM sync to Salesforce, HubSpot and Pipedrive
- ✕custom domains with certificates handled for you
Prior art / alternatives
Why it still works
capture fidelity across real apps, CRM sync, and hosted delivery