Get one daily status briefing from a team of Grok Bots
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Methods
Paste into a general LLM and get one daily status briefing from a team of Grok Bots.
LLMPrompt
Prompt
Copied 0
Help me set up a daily briefing across my Grok Bot team. You own this process as my Chief of Staff. First, help me choose a shared update log each Bot can access. Prepare this instruction for me to add to each Bot: ‘Whenever a job changes state, add an entry to the shared log with the job, owner, state, evidence link, next step and timestamp. Use these states: needs decision, blocked, done or in progress.’ Don’t assume you can change another Bot’s instructions. Walk me through applying the rule to each one. Build the briefing from that log, using these sections: 1 - Needs my decision. Explain the decision, your recommendation and what’s waiting on my answer. Include any verified deadline. 2 - Blocked. Show what’s stuck, why, who can unblock it and the next action. Distinguish waiting on me from waiting on another Bot, missing information or an outside response. 3 - Completed. Verify completion against the live source wherever possible. For an email, check the sent folder rather than trusting a Bot’s note. Link to the result or evidence. ‘Email prepared’ is different from ‘email sent.’ If you can’t verify completion, label it unverified. 4 - In progress. Show the owner, next milestone and what changed since the previous briefing. 5 - Status unknown. Move any unfinished job with no update for two days into this section. Include jobs whose status you can’t verify. Show the last confirmed update and how to check what’s happening. Silence doesn’t mean completion. Save every briefing in our agreed location so the next one can compare against it. On the first run, establish a baseline. Keep the update short enough to scan in a minute. Skip empty sections. Include each job once, even if several Bots contributed. Link to details instead of copying conversations. Finish with up to three actions that need my attention. Show me a sample first. Once we agree on the format, help me schedule it for my preferred time, timezone and delivery channel.
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/chief-of-staff-daily-briefing - 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": "chief-of-staff-daily-briefing",
"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"
}