Hedy
Read meeting sessions and AI-extracted highlights from Hedy.
About
Hedy ships in the w6w first-party pack. It declares 4 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.hedy- Version
- 0.1.0
- Author
- w6w
- Licence
- MIT
- Categories
- AI & Machine Learning · Productivity · Communication
Overview
Hedy is an AI meeting-notes and highlights product: it joins or records a meeting, then produces a transcript, a recap, structured meeting minutes, and a set of AI-extracted “highlights” — the individual quotes and moments the model judged worth surfacing, each with its own cleaned quote, AI insight, and timestamp.
This app covers the read side of that data: listing and reading meeting Sessions (transcript, recap, meeting minutes, structured conversation history) and listing and reading Highlights (the quote-level moments extracted from a session), so a workflow can pull a completed meeting’s output into whatever comes next — a CRM note, a summary digest, a search index.
Hedy’s own OpenAPI document also declares a Webhooks tag, but publishes no paths under it — nothing here was guessed to fill that gap.
Build with Hedy
Three routes to the same 4 actions. The Workflow tab is generated from Hedy's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
List Highlights
highlights-list List AI-extracted highlights (key quotes and moments) across meeting sessions.
Get Session
session-get Fetch full detail for one meeting session, including its transcript and minutes.
List Sessions
sessions-list List meeting sessions with basic information (title, time, duration, recap).
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Hedy's real ids.
{
"manifestVersion": "2",
"name": "hedy-example",
"steps": [
{
"id": "highlight-get",
"uses": {
"app": "io.w6w.hedy",
"action": "highlight-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"highlightId": "<highlightId>"
}
}
]
}Here are some of the things you can do
-
Get Highlight
readhighlight-get -
List Highlights
searchhighlights-list -
Get Session
readsession-get -
List Sessions
searchsessions-list
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Hedy, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Hedy. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "highlight-get",
payload: {
highlightId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action highlight-get --payload '{"highlightId":"<value>"}'Give an AI agent Hedy — without giving it Hedy's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.hedy#highlight-get",
"input": {
"highlightId": "<highlightId>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Hedy connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Hedy's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Hedy itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Hedy declares its own checks, so its health is a property of the app rather than something the host guesses at.
Hedy platform status
Request-rate headroom
x-ratelimit-limit / x-ratelimit-remaining / x-ratelimit-reset headers read from GET /sessions?limit=1.