Wraps the response. On Netlify the agent is an Edge Function on every path.
On Netlify the agent is an Edge Function on every path. It wraps the response, so robots.txt and Organization data are switches here.
netlify/edge-functions/reflexa.js — An Edge Function, with path = "/*" in netlify.toml.
import { reflexa } from './reflexa-agent.js'
const agent = reflexa({ token: Deno.env.get('REFLEXA_TOKEN') })
export default async (request, context) => {
try {
return await agent.handle(request, context, () => context.next())
} catch {
return context.next()
}
}Get reflexa-agent.js and the site's token from the dashboard's Agent page, put the token in REFLEXA_TOKEN, deploy. Then press Check the connection in the dashboard: it fetches the domain proof from your real domain and the agent is live.
What it does not: a page's words live in your repository — connect it in the dashboard and the agent commits the title, description, opening and FAQ you approve.
How installing the agent works, in general → · what the agent does and never does →
No. Installing puts the agent in place and binds it to the site by its token; nothing is applied. Every switch is your click in the dashboard and every word it writes is shown to you first.
Remove the file and redeploy. Whatever was last switched on stops being served on the next request. Your checks and the agent's memory stay in your Reflexa account.
Counts every AI visit, page by page. Serves /llms.txt and the domain proof. Appends the AI-crawler groups to robots.txt. Puts the Organization JSON-LD into every page's head. A page's words live in your repository — connect it in the dashboard and the agent commits the title, description, opening and FAQ you approve.
Yes — it belongs to this one site and should live in an environment variable, never in a file you commit. It grants nothing beyond this site, and the domain proof refuses it from any other host.
The 23 checks run from outside before anything is installed — you see what the agent would do before it does it.