Can AI replace Escourtly?
The core loop is a weekend build on top of rrweb: snapshot the DOM on each click, inline the assets, and replay the snapshots as a clickable walkthrough. What takes the project from a demo to something you would put in front of a prospect is capture fidelity · real apps are full of canvas, cross-origin iframes, shadow DOM and lazily loaded assets, and every one of them is a separate fix. Past that sit the parts that are infrastructure rather than features: no-login share links and embeds that stay up, custom domains with certificates, funnel analytics, and CRM sync. Build it for your own product and one sitting gets you a long way. Build it to replace the subscription and you have signed up for the edge cases.
01What it costs
Checked Aug 14, 2026 · source: escourtly.com.
| Plan | Monthly | Billed yearly | What you get |
|---|---|---|---|
| Founder | $49 | — | Unlimited walkthroughs, steps and plays; all features; custom domains |
02Could AI build it for you?
The core job: Record a DOM snapshot on each click with a browser extension, annotate the steps, and publish them as a clickable walkthrough at a public URL.
What a working version needs:
- Node and a Postgres database
- a Chrome MV3 extension build step
- an OpenAI/Anthropic API key for step descriptions
- somewhere to host the public demo pages
Submitted by the product's founder · verdict and prompt follow the same criteria as the other entries in this category, and the DIY substitute is a self-hosted rrweb recorder rather than a video tool.
03What you'd give up
- 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
People still pay for Escourtly because the first capture is the easy part. The subscription absorbs the long tail: the app that renders blank because its fonts were behind a CDN, the embed that has to load fast from someone else's marketing site, the custom domain, the lead that has to land in HubSpot without anyone copying it across. A founder who builds this for one product will probably be happy. A team that wants it to work on every product they ship is buying maintenance, not software.
05The build prompt
Paste this into an AI coding tool (such as Claude, ChatGPT, Lovable or Replit) to build your own version.
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.
06Open-source starting points
- rrweb: MIT-licensed DOM record and replay · the capture engine this whole category is built on.
App prices, verdicts, alternatives and build prompts are adapted from Can I Vibecode It? (MIT License, © 2026 Rob Hallam). Each price shows the date it was checked and its source. Prices change; confirm on the vendor's site before you decide.
Get new verdicts in your inbox.
One short email when new verdicts land: what AI can now do for you, and what it still gets wrong. No spam. Unsubscribe anytime.