Your agent flows live behind dashboards and API calls, which is useless when your hands are full or you are away from a keyboard. This connects them to your voice.
sonnet3 daysSiri ShortcutsiOSOpenAIWebhook API
Claude
85ROI
81Scale
$3.5k95Saved
ROI for
README.md
Why this subagent
Your agent flows live behind dashboards and API calls, which is useless when your hands are full or you are away from a keyboard. This connects them to your voice.
A Siri Shortcut sends your spoken request to a webhook, the right flow runs, and Siri reads the answer back. You trigger any agent flow by talking to your phone, with a spoken result short enough to actually listen to.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Build a Siri Shortcut that captures your spoken request and sends it to that webhook.
pending
Run the matching flow on the server and return a short, speakable result.
pending
Have Siri read the result back and offer a follow-up action when one applies.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Receive a named action and spoken parameters from a Siri Shortcut, run the matching agent flow, and return a concise result under two sentences suitable for text-to-speech.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.