Write something
Pinned
2d •
ChatGPT Work Part 3: Connecting Your Email
In Part 1, we used ChatGPT Work to review job-search information. In Part 2, we turned that review into a recurring weekday check-in. Now let’s use ChatGPT Work for something almost everyone deals with: Email. Not sending email. Not deleting email. Not filing email. Just reviewing what is there and helping you decide what needs attention. That is a great early use case because your inbox already contains work. The problem is usually not whether the information exists. The problem is knowing what deserves your attention first. ChatGPT Work can use connected apps when they are available in your account or workspace, and app permissions may control whether ChatGPT can read information or take actions in connected services. Availability depends on your plan, workspace settings, connected apps, and permissions. (OpenAI Help Center) 🔁 Practice This Ask ChatGPT Work to review your recent email and organize it into simple categories. The goal is not to reach inbox zero. The goal is to create a short triage report so you know where to focus. 📌 Stay in Control Use the same safety boundary we have been using: Review and prepare the work, but do not reply, send, delete, archive, label, move, update, schedule, or modify anything without my explicit approval. That line matters. For this practice, ChatGPT Work is helping you review and prioritize. You still decide what happens next. 💬 Sample Prompt Use this as a starting point: Review my recent emails from the last 24 hours. Do not reply, send, delete, archive, label, move, update, schedule, or modify anything without my explicit approval. Create a short email triage report with these sections: - Needs my reply - Waiting on someone else - Informational - Possible follow-up - Time-sensitive - Can likely ignore For each item, include: - Sender - Short summary - Why it is in that category - Recommended next action
Pinned
4d •
ChatGPT Work Part 2: Run the Job Search Review Every Morning
In Part 1, we used ChatGPT Work to review job-search information and organize possible opportunities. Now let’s make it more useful. Instead of running that review one time, let’s ask ChatGPT Work to run it every weekday morning. That is the next shift. You are not just asking: "What did you find?" You are asking: "Can you check this for me every morning and tell me what needs my attention?" 🔁 Practice This Schedule the Job Search Review: 📌 Stay in the same Work thread from Part 1. That matters because ChatGPT already has the context from your first job search review. It already knows the kind of roles you are looking for, the criteria you provided, and what the first review produced. Now give it a simple recurring assignment. 💬 Sample Prompt Use this as a starting point: Schedule this job search review to run every Monday through Friday at 7:00 AM. Each morning, review new job-search related emails, recruiter messages, saved job postings, and relevant connected files you are allowed to access. Use the resume, career summary, or criteria I already provided as the comparison point. Do not apply, submit, message anyone, upload documents, send anything, delete anything, move anything, update anything, schedule anything else, or modify any file without my explicit approval. Each morning, give me a short job search review that includes: - Keep the review concise and practical. - New opportunities found - Roles worth reviewing first - Strong matches - Possible concerns or gaps - Repeated keywords or skills - Recommended next steps - A “Needs Human Review” section for anything uncertain Keep the review concise and practical. That is it. Do not overcomplicate this. A good recurring review should: - Find new job-search information - Separate stronger opportunities from weaker ones - Compare roles against your criteria - Flag uncertainty - Recommend next steps - Avoid applying, sending, uploading, or changing anything - Keep the summary easy to scan
Pinned
6d •
ChatGPT Work Part 1: Job Search Review
Most of us first learned ChatGPT as a conversation. Chat feels like it is asking: What can I answer for you today? That is useful. ChatGPT Work feels different. Work feels like it is asking: What can I take off your plate? You are not just asking for an answer. You are giving ChatGPT an assignment. You define the outcome. You give it context. You let it use connected apps where available. Then you review the result before anything happens. That last part matters. OpenAI currently describes Work as the place for longer, multi-step tasks and finished deliverables, and apps can connect ChatGPT to external tools, information, and actions depending on your plan, workspace, permissions, and settings. (OpenAI Help Center) Start With a Safety Boundary When you are first learning ChatGPT Work, I recommend adding this line to your prompt: Review and prepare the work, but do not apply, submit, send, message, delete, archive, move, update, schedule, cancel, publish, or modify anything without my explicit approval. That may feel like overkill. It is not. Connected apps make ChatGPT Work more useful because the information may already live in your email, calendar, files, or other tools. But useful does not mean uncontrolled. My simple rule is: Analyze first. Recommend next. Act only after approval. Practice This: Job Search Review For the first practice, let’s use a job search review. This is a good starting point because it is useful, but still easy to inspect. We are not asking ChatGPT to apply for jobs. We are not asking it to message anyone. We are not asking it to upload anything. We are asking it to review what it can access, organize the opportunities, and prepare a recommendation for us. Depending on what you have connected, ChatGPT Work may be able to review things like: - Job alert emails - Recruiter messages - Saved job descriptions - Career notes - A resume or professional summary - Relevant files in connected storage
1d •
AI + GHL turned 5 missed calls into $3,800 recovered in Week 1 — here’s the exact flow
Hey AI Bits and Pieces community 👋 I’m Liton — I build AI automation systems for home service businesses (HVAC, plumbing, cleaning, contractors) using GHL + AI + n8n. Quick win worth sharing: The problem: HVAC client missing 5–7 calls per week while on jobs. No follow-up. Leads disappearing. 5 calls/week × $500 avg job = $2,500 walking out the door every week. The automation: 1. Missed call triggers in GHL 2. AI text-back sends within 45 seconds 3. Lead qualifies via SMS conversation 4. Booking link fired if qualified Result: $3,800 recovered in Week 1. $1,500/month retainer locked. No extra staff. No new ads. Just plugging a gap that was already bleeding revenue. --- The best automations aren’t complex — they solve one obvious problem and do it reliably. Happy to be here — looking forward to contributing and learning from this community 🙌 — Liton
2d •
🤖 Here’s a tiny AI website trick most people still don’t know about…
Try adding: /llms.txt to the end of an AI company’s documentation website. It’s basically a clean, AI-readable map of the website, written in Markdown so LLMs and AI agents can understand the important pages without fighting through navigation menus, JavaScript, buttons and all the other wonderful things humans added to websites. 😂 For example, several companies in the Voice AI / AI Agent ecosystem already use it: 🎙️ Vapi → /llms.txt 📞 Retell AI → /llms.txt 🤖 Bland AI → /llms.txt 🔊 Cartesia → /llms.txt 🗣️ LiveKit → /llms.txt ☎️ Twilio Docs → /llms.txt And it goes beyond Voice AI: 🔎 Perplexity uses it 🔥 Firecrawl uses it 🧠 Anthropic / Claude uses it 🌪️ Mistral uses it So what exactly is llms.txt? Think: robots.txt → instructions for crawlers sitemap.xml → map for search engines llms.txt → curated map for LLMs & AI agents Instead of forcing an agent to figure out an entire website, the file can point it directly toward things like: → Documentation → API references → Pricing → Tutorials → Integrations → Product information → Important Markdown pages Some sites even provide llms-full.txt, which can contain a much larger version of the documentation specifically designed to be consumed by an LLM. ⚠️ One important distinction: This isn't some secret "rank #1 in ChatGPT" SEO hack. llms.txt is still an evolving convention, and not every AI system is guaranteed to use it. But when companies building AI agents themselves are publishing these files, it's definitely something worth knowing about. And here's where it gets interesting for those of us building Voice AI… 👀 Imagine giving your voice agent, RAG system or research agent the /llms.txt file of documentation instead of telling it: "Go crawl this entire website and hopefully figure it out." Much cleaner. 🧪 Try it yourself: Find an AI tool you use, go to its documentation site and add /llms.txt. You might be surprised how many already have one. 👇 Has anyone here already added an llms.txt file to their own website?
1-30 of 503
skool.com/ai-bits-and-pieces
AI lessons you can read in under 3 minutes and apply in everyday work and life.
Leaderboard (30-day)
1
+75
2
+37
3
+35
4
+28
5
+26
Powered by