Draft an email reply that sounds like me
YES — AI can do this use case.
2 methods on the page: 1 prompt and 1 agent.
Methods
Give a general LLM three sample emails, then the new thread
LLMPrompt
Steps
- Paste three emails you actually sent.
- Paste the new thread under that.
- Ask for a reply in that voice.
- Trim anything that sounds unlike you.
Prompt
Copied 19
Here are 3 emails I wrote (voice samples), then a new thread. Draft a reply that sounds like me. Voice rules: short, direct, no fluff. Match my greeting and sign-off. Do not add claims I did not make. Ask at most one clarifying question if needed. VOICE SAMPLES: <<<paste 2–3 of your emails>>> NEW THREAD: <<<paste the email you need to reply to>>> Reply:
Add loom and point it at the Gmail thread
Steps
- Add loom from the Grok Bot Hub.
Run this method with your agent
Download .mdCopied 0
--- name: "draft-reply-grok" description: "Use when you need to Draft an email reply that sounds like me. Add loom and point it at the Gmail thread" --- # Add loom and point it at the Gmail thread Job: [Draft an email reply that sounds like me](https://aiagents.org/canai/draft-reply-voice) ## Need - ai agent: [Grok Bot](https://aiagents.org/grok-bots) ## Steps 1. Add loom from the Grok Bot Hub. ## Credit Method author Tess
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/draft-reply-voice - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "draft-reply-voice",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}