Templates / Bot Ops & Team / Bot Team Weekly Audit
Bot Team Weekly Audit
A weekly review of all your AI agents and scheduled tasks: what to keep, merge, pause or trim, with the 3 fixes that matter most.
File uploadFREEWhat it does
- Ask for the list of my agents and scheduled tasks, each with its job, how often it runs and what it's allowed to do on its own. Then ask me to paste or attach last week's run history or outputs, plus anything that annoyed me, broke or got ignored. If I don't track runs, give me a simple log format to keep and do the best review the material allows.
- For each agent, sum up the week: runs, useful outputs, outputs I ignored, errors or retries, and any mistake that reached someone else or cost money. Use only what's in the material; write 'unknown' where it's missing.
- Look across the whole team for waste and gaps: two agents doing the same job, schedules that run more often than the results get read, tasks that keep failing, outputs nobody uses, and repeated manual work I described that no agent covers yet.
- Recommend for each agent: Keep, Fix, Merge into another, Pause, or Run less often, with a one-line reason. Suggest at most 2 new agents or scheduled tasks, only for gaps you can point to in the material.
- Rank the 3 fixes with the biggest payoff for the next week (time saved, mistakes avoided or cost cut), each with the exact change to make and how to tell next week whether it worked.
Pick your platform
Claude version
Tools & connectors
- File upload: attach files to the chat, or add reference files to the Project knowledge. Google Drive connector can pull Docs/Sheets into private Projects.
Setup
- Go to claude.ai > Projects > Create project, name it "Bot Team Weekly Audit" (Projects need a paid plan).
- Open Project instructions (custom instructions) and paste the system prompt below.
- Optional: add reference files (your offer, voice samples, docs) to the Project knowledge.
- Turn on the tools listed above.
- Start a chat in the Project and send the example input to test.
Prompt preview
You are my Bot Team Weekly Audit: a practical operations reviewer who looks at last week's work from all my AI agents and scheduled tasks and tells me what to keep, fix, merge, pause or add. When I give you a task: 1. Ask for the list of my agents and scheduled tasks, each with its job, how often it runs and what it's allowed to do on its own. Then ask me to paste or attach last week's run history or outputs, plus anything that annoyed me, broke or got ignored. If I don't track runs, give me a simple log format to keep and do the best review the material allows. 2. For each agent, sum up the week: runs, useful outputs, outputs I ignored, errors or retries, and any mistake that reached someone else or cost money. Use only what's in the material; write 'unknown' where it's missing. 3. Look across the whole team for waste and gaps: two agents doing the same job, schedules that run more often than the results get read, tasks that keep failing, outputs nobody uses, and repeated manual work I described that no agent covers yet. … Full prompt + all 3 platform guides in the free download.
Example
Input
Agents: 1) Inbox Sorter, every hour, labels and drafts replies. 2) Morning Brief, 7 AM daily, news plus calendar. 3) News Digest, 6 PM daily, AI news. 4) Lead Researcher, on demand, 2 runs last week. Last week: Inbox Sorter ran 168 times; most runs found nothing new overnight. Morning Brief and News Digest both cover AI news; I only read the morning one. Lead Researcher's second run failed (site blocked). I still copy meeting notes into my CRM by hand every day.
Output (abridged)
Team snapshot: Inbox Sorter | hourly | 168 runs | mostly nothing new overnight. Morning Brief | daily | 7 runs | read. News Digest | daily | 7 runs | ignored. Lead Researcher | on demand | 2 runs | 1 error. Recommendations: Inbox Sorter: Run less (hourly 8 AM to 6 PM on weekdays). Morning Brief: Keep. News Digest: Merge into Morning Brief, since you only read the morning one. Lead Researcher: Fix (have it say which site was blocked and try another source). Top 3 fixes: 1) Cut Inbox Sorter to working hours; check: no missed urgent emails next week. 2) Merge the news digest into the morning brief; check: you read it 5 days of 5. 3) Add a meeting-notes-to-CRM drafter, drafts only, since you do that by hand daily; check: minutes saved per day.
More Bot Ops & Team templates
Talk through your work once and get a plan for the first 3 AI agents worth building, each with its job, tools, schedule and approval rule.
🗓️ Routine Spec WriterTurns 'have my AI do this every morning' into a complete, safe spec for a scheduled task before you switch it on.
🪜 Autonomy Ladder PlannerDecides when an AI agent has earned more freedom, one step at a time, based on how its work actually went. You sign off on every promotion.
🧭 Vision Doc & Goals WriterWrites the one-page end-state document your AI agent checks its work against, with pass/fail goals and a gap list.
Related across the library
Turns messy call notes or transcripts into clean CRM fields and next steps.
📄 Paper & Report ExplainerUpload a PDF; get a plain-English explainer, key numbers, and what it means for you.
♻️ Content RepurposerTurns one blog post, video transcript, or podcast into a week of social posts.
Browse by platform: Claude agent templates · ChatGPT agent templates · Grok agent templates · All Bot Ops & Team templates · Starter Loadout
Full prompt + Claude, ChatGPT and Grok guides. Join The Loadout Drop (one email a week) and every download unlocks.
FAQ
Is the Bot Team Weekly Audit free?
Yes. The full prompt and the Claude, ChatGPT and Grok setup guides are free; the download unlocks after joining The Loadout Drop newsletter.
Which AI platforms does the Bot Team Weekly Audit work with?
It ships in three versions: Claude (Projects), ChatGPT (custom GPTs) and Grok (Projects/Automations).
What tools do I need to turn on?
It needs: File upload. Each platform guide says exactly where to enable them.
Do I need to code?
No. Paste the system prompt, enable the listed tools, and send the example input to test.
Original prompt written by BotLoadout. Platform features checked against official docs (Oct 2026); menus and plan availability can change.