AI Tools For Communication

The best test of an AI agent isn't a benchmark. It's a lost jacket in Phuket. My co-founder left a Ralph Lauren Purple Label blazer at the airport. Wool, herringbone, dark blue. Not cheap. So we asked our AI agent to get it back. Not as a demo. As a genuine request. Within an hour: it identified the airline, found the lost & found email at Phuket airport, drafted the claim in the right format, coordinated with another co-founder for flight details, and proposed a logistics chain to get it shipped back via Munich. Nobody told it the steps. It figured out the process, executed it, and kept the thread alive across days. Here's why this matters more than any enterprise demo: Enterprise AI is full of controlled scenarios. Curated data, predefined workflows, success metrics chosen in advance. A lost jacket is messy. Ambiguous. Requires judgment calls about who to contact, what tone to use, when to follow up. Two weeks in, our agent runs our daily operations: pipeline monitoring, meeting prep with context, automated follow-ups, morning briefings personalized per founder. But the jacket is what convinced me this is real. Not because the task was hard — because nobody had to define the workflow. The agent understood the goal and navigated the ambiguity. That's the gap between "AI tool" and "AI colleague." Tools need instructions. Colleagues need context. We're building both MING and Hyperize with agents now. Happy to share what we're learning. #AI #Agents #OpenClaw #EnterpriseAI

How I actually use AI at work (Real examples from my day) When people ask me how I use AI at work, I don’t start with the flashy stuff. It’s really the everyday things that actually make the difference. 🧠 Brainstorming clarity When I hit mental blocks writing product docs or framing complex engineering trade-offs, I’ll prompt LLMs to “explain this to a PM with no infra background” or “turn this email thread into a design doc.” It helps me get unstuck. 📥 Inbox triage Between 0 to 1 podcast guests, content campaigns, and Google work, my inbox gets overwhelming. I use AI to quickly summarize long threads or help me draft professional but human replies. A game-changer. 🎙️ Content repurposing After recording a podcast episode, I drop the transcript into AI to generate ideas for titles, hooks, and social copies. It saves 2–3 hours per episode, and lets me focus on the creative direction instead. 🔍 Prompt engineering = the new shortcutting I don’t copy/paste AI outputs blindly, but I’ve learned to prompt better, faster, and more intentionally over time. Learning how to collaborate with AI is the real unlock. — 🗓️ I’m excited to share this as part of LinkedIn’s inaugural #AIinWork Day! If you’re curious how AI fits into your workflow, I’d love to hear what’s working for you 👇 #AIinWork #ArtificialIntelligence #FutureOfWork

I built an “AI Decoder Ring” with my son to turn messy Slack threads and vague emails into clear checklists, dependencies, and paste-ready confirmations. The post shares the exact prompts, a copy-and-paste template, and a simple Project setup that keeps everything scoped, private, and consistent. If you’re a creative who struggles with organization, this will help you work calmer and faster—read the full story and steal the system.

The new ChatGPT connectors are really useful! Chat can now access Gmail, Google Cal, and Drive, so it can: -Skim unread emails & give a summary -Summarize threads + draft replies -Pull key info from old convos -Do meeting prep + agendas Before I get into some prompts you can copy, quick reminder that enabling connectors gives ChatGPT view access to your private data. I'm an AI power user and it's part of my job to test everything, so personally, I make the sacrifice for the extra features. But please be careful if your job is data-sensitive! 1. Email Intelligence Get ChatGPT to skim your recent unread emails, give you a summary, and rank them in importance: "Summarize all my unread emails in Gmail that I received over the past 48 hours. Rank it in order of importance." 2. Search & Data Extraction Get ChatGPT to find threads and draft in your tone "Find all my emails with [Jennifer], then compare it to my most recent email from [Jennifer]. Give me the takeaways in bullet points. Then, draft a short reply in my tone based on that context." 3. Inbox Memory Get ChatGPT to pull key info from old convos and compare to recent emails: "When is OpenAI DevDay this year and when was it during the previous years (2023, 2024)? What makes this year different. Use a mix of internet information and my email inbox context" 4. Meeting Briefs / Agendas Get ChatGPT to look at your Google Cal and your email to prep for upcoming meetings "Look at my next Google Calendar event. Give me a rundown of the person and the event with context from my Gmail so I come prepared. Also suggest a meeting agenda." I'm just the surface here on how you can use these connectors, but they've been very useful so far as someone who spends hours in my inbox every day If you enable them, I would love to hear your use cases! Will be featuring the top responses in The Rundown (1M+ readers!)

Everyone talks about using AI for writing. I use Claude to run my day. It’s not a tool. It’s an operations partner—if you give it the right prompts. Here’s exactly how I use Claude as my assistant (connected to Gmail, Drive, and Calendar): 1. Morning Briefing Prompt Start the day with clarity. “Check my calendar, unread emails, and recent docs. Summarize today’s meetings with prep notes. Pull any open loops or tasks from emails. Suggest a time-blocked plan for deep work + admin. Flag anything urgent or out of alignment.” I open Claude before I open my email. 2. Pre-Meeting Prep Prompt No more last-minute scrambling. “I have a meeting with [Name] about [Topic]. Pull key context from emails, docs, and last calendar invite. Extract action items from last call. Draft talking points and 3 smart questions to ask.” Perfect for client calls or collabs. 3. Research & Synthesis Prompt Working on a project? Claude becomes your researcher. “I’m working on [project]. Pull relevant threads from Gmail. Scan docs with [keyword] and summarize insights. Build a timeline of progress + open items. Draft a quick project update I can send or post.” This alone has saves me 3 hours a week. 4. Workspace Organization Prompt Your brain, but with folders. “Find all docs related to [project]. Suggest categories or themes. Create a folder/tag structure that makes sense. Highlight outdated files or duplicated info. Build a cheat sheet with links + purposes.” Perfect if your Google Drive looks like a tornado. 5. Smart Inbox Prompt Catch up without the chaos. “Find unread emails from VIP contacts. Summarize key threads and flag what’s urgent. Draft quick replies where possible. Link any emails to related docs or calendar events. Build a follow-up plan so nothing slips.” It’s triage for your inbox—with logic. Claude isn’t just for content. It’s for operations, decisions, and daily momentum. Want more tips like this? Join 3,400+ readers of 9-To-Thrive → https://lnkd.in/gXMzXweK

This is how I use ChatGPT for my daily software engineering tasks and end up saving 20 hours per week. Nothing fancy. Very simple. But when integrated into your workflow, it saves time, and clears a lot of mental load. 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱 𝗙𝗮𝘀𝘁𝗲𝗿  • Slack and Teams threads piled? – Copilot. No more scrolling through chaos.  • Long email chains? – One clean summary and I’m instantly caught up.  • Missed a meeting? – AI gives me the recap + action items. 𝗖𝗼𝗱𝗲 𝗦𝗺𝗮𝗿𝘁𝗲𝗿  • Generate edge test cases – Always catches one or two I didn’t think of.  • Refactor messy functions – It gives 2–3 cleaner versions with reasoning.  • Boilerplate – Handles class templates, config files, repetitive setup.  • Catch logical bugs – Just explain it to AI, it spots issues. 𝗪𝗿𝗶𝘁𝗲 𝗕𝗲𝘁𝘁𝗲𝗿 & 𝗙𝗮𝘀𝘁𝗲𝗿  • Write README files – Explain the project casually, AI formats it like a pro.  • Generate API docs – Paste code, get clean documentation in Markdown.  • Turn comments into diagrams – Use GPT + Mermaid to visualize instantly.  • Write JIRA & PR summaries – Rough bullets in, clean descriptions out.  • Respond to tricky emails – Start in Hinglish or native lang, AI fixes the tone.  • Draft cold emails or intros – AI helps me phrase what I used to overthink. 𝗧𝗵𝗶𝗻𝗸 & 𝗘𝘅𝗽𝗹𝗮𝗶𝗻 𝗖𝗹𝗲𝗮𝗿𝗹𝘆  • Brainstorm solutions – Ask GPT for 2–3 design options with pros/cons.  • Simplify concepts – “Explain like I’m new” always gets the job done.  • Create onboarding guides – Dump notes, AI turns them into clean docs. 𝗖𝗼𝗺𝗺𝘂𝗻𝗶𝗰𝗮𝘁𝗲 & 𝗣𝗿𝗲𝘀𝗲𝗻𝘁  • Turn bullets into slides – Use tools like Napkin to create visual decks fast.  • Write posts or announcements – Start with bullets, let AI expand clearly. 𝗖𝗹𝗮𝗿𝗶𝘁𝘆-𝗗𝗿𝗶𝘃𝗲𝗻 𝗛𝗮𝗯𝗶𝘁𝘀  • Use AI as a thinking partner.  • To get a good answer, you first have to ask a good question.  • That act forces clarity.  • Even before AI replies — you already understand better.  • I call this the 𝘾𝙡𝙖𝙧𝙞𝙩𝙮 𝙇𝙤𝙤𝙥. This isn’t the future. This is today’s reality. Include AI in every possible way in your workflow and become a 10X Dev. Future is for 10X Devs. P.S.: How are YOU using GenAI in your workflow? 

The moment you find a way to give agentic AI like Claude Code access to all of your corporate tools and context, everything changes. New AI drops every week. Cerebras, Opus 4.6, OpenClaw, Moltbook. I'm sure several more launched while I was writing this post! I'm overwhelmed trying to keep up while actually trying to stay on top of my job. So here's one concrete thing that's actually changed how I work. The problem with every ChatGPT-style tool is that you are the integration layer. You copy from Jira, paste into the chatbox. Copy from Slack, paste into the chatbox. The AI is smart, but it's totally blind. You're doing all the research so the AI can do the thinking. So... a couple weeks ago I started using Claude Code with MCP connections to my actual work tools — Gmail, Calendar, Slack, Jira, Google Docs, Snowflake, etc — and something clicked. It's not just that it has context (though that matters a lot). It's that it's actually agentic. It doesn't just answer questions — it takes actions. It searches, cross-references, drafts, creates (with your permission, of course!). It operates across your systems instead of waiting for you to spoon-feed it. I asked Claude: "What's the current state of the current migration project? Check Jira, Slack, and the design doc." And of course, Claude just did the work: searched my real systems. Pulled threads together on its own, no 15-minute research manual context gathering phase before I could even start thinking. The bottleneck hasn't been model intelligence for a while now! It's context and agency. Once the agent can see your systems and act on them, the whole workflow inverts. You stop doing the work and start directing and refining the work. "Draft a follow-up email to yesterday's design review — pull the notes from the doc and the attendee list from the calendar invite." It does the research, writes the draft, you ask for revisions, make your edits, remove the still-too-real AI slop effect as much as you can, and send. That shift matters most for managers. Our days can sometimes feel like 70% or more context-gathering and 30% judgment calls. AI that can't see our systems only helps with the 30%. An actual agent eliminates the entire gathering phase. There's a million AI tools fighting for your attention right now. Ignore most of them. Connect one agent to your real work systems and see what happens.

I spent the day at OpenAI learning how communications leaders are using Codex. Here are my notes! Save this post — the prompts at the bottom are ready to copy + paste straight into Codex. 💻 Before anything: get set up 1. Download Codex and go to your Plugins 2. Connect Gmail, Google Calendar, Slack, Notion, Drive, etc. 🧠 The mindset shift Think of Codex as your own Chief of Staff — AI that does the work for you, even when you're not at your desk. Stop asking "What will AI replace?" Start asking "What can I do now with AI that I never had time for before?" Comms teams are using Codex for interview briefings, building micro sites, product launch recaps, executive voice guides, living customer story banks, & so much more. 📝 Executive Voice Guides Don't just set a tone for your exec. Build a voice model. Tell Codex to research your executive's podcasts, keynotes, press, X, LinkedIn, and earnings calls — one sub-agent per research lane. The output: a sourced voice dossier with a PREFER / AVOID vocabulary table. Save it as a Skill (a reusable instruction pack that teaches Codex how to handle a specific type of work) so your whole team can run it. 🆕 2 new features worth knowing /plan — For complex projects where you don't know where to start. Codex asks clarifying questions and maps it all out. /goal — The inverse of /plan. Work backwards from the outcome you want. Great for quantitative goals. 🏆 The pro moves Stop writing prompts. Build commands. Anything you do 2–3x a week should be a Skill. AppShot — Such a cool feature. It's a screenshot tool that captures an entire webpage...even the context that isn't visible on your screen. 🤯 Ask yourself: My job would be so much better if I never had to _______ again. That blank is your first automation. 📌 2 prompts to try right now Morning brief (set as automation): "Check @Slack, @Google Calendar and @Gmail and write me a morning brief everyday at 8am in this thread. I want you to collapse all the chaos of work into a single note every morning over coffee ☕" Inbox triage: "Read my recent email and identify the 5 most important emails I should get back to. Prioritize messages that need my reply or follow-up. Deprioritize newsletters, calendar noise, receipts, and generic press blasts. Use recently sent emails to match my tone. For each item, include a concise draft reply if one is needed, and any missing context or assumptions. Do not send anything yet." That's all for now! Thanks for reading my longest LinkedIn post ever. BIG THANK YOU to our stellar hosts for all the Codex gems: Kathleen Chaykowski, Lindsay McCallum Rémy, Caffrey Lynch, Brittany Darwell, Shaokyi Amdo, Laura Peng, Kelsey Pedersen, Jim Prosser and (of course) Taya Christianson.

When I ask journalists how they're using ChatGPT (or other LLMs), many/most are quick to go on the defense and tell me they've never used it. But honestly? That's a mistake, because these tools can help you do some really cool things — like managing your biggest stressor (your inbox). Three examples from my week: I always see the Gemini box pop up on my Gmail, but have never typed anything into it. I asked it to try two things, and got brilliant results. Prompt 1: Please analyze any email pitches that have come in between March 1-April 14 that mention golf, and suggest a few unique story angles for publications based on the contents. Result: I got three really smart angles here, and Gemini even included publication suggestions. Keep in mind, I've literally never used Gemini before, so this tool has no "training" from me, but recommendations felt quite reasonable. Prompt 2: Can you please pull out any email received in 2026 that includes the phrase "press trip invite"? Please include the subject line of the email, the date received, the location of the trip and trip dates. Result: It perfectly extracted these from my inbox and put them together in a spreadsheet for me, even pulling in an invite I'd missed because the press trip part of the email wasn't mentioned in the subject line. Whew! Prompt 3: Can you please go through my inbox and find any single-day event invite emails from the past two weeks, then craft a short and sweet reply that respectfully declines? (All of these are not in my home base, FYI.) Result: It drafted quick replies tailored specifically to each one, formatting them in a way that's easy to copy and paste, and including hyperlinks to the specific emails so I can click through, paste and send. I'm not going to use AI to reply to most emails, but for batching tasks like this (and not leaving people hanging), it saved me a ton of time. Would you try any of these prompts for analyzing emails? What other ways are you using AI to hack your inbox?

One thing that has always felt broken about AI at work is this: The model can sound smart, but most of the time it has no clue how your company actually works. In partnerships, the real value is not just finding an answer. It’s being able to create something useful from context scattered across emails, docs, tickets, and past decisions. For me, that could be an exec brief before a partner meeting, a joint account plan, or a follow-up note that actually reflects the product history, open issues, prior commitments, and where the relationship really stands. The hard part is not writing. It’s making sure what you create is grounded in reality. The announcement is simple but important: Glean's MCP server now brings real company context directly into ChatGPT and Claude! I've put more info in comments. With Glean’s MCP server, ChatGPT and Claude can work against real company context: docs, tickets, emails, decisions, with permissions intact and information staying up to date. That matters a lot. Instead of copying sensitive information into a chat window and hoping for the best, teams can ask things like: • What changed in the Q1 roadmap? • What did we decide in the last review? • Can you summarize this project and point me back to the source? And what comes back can be grounded in the actual source material, not just a polished guess. What makes this different for me is simple: this is not AI pretending to understand the business. It can work from the actual context, point back to the source, and stay inside the same permission model your company already trusts. That is what makes it useful. And that is what makes it real for work. #WorkAI #EnterpriseAI #MCP #ChatGPT #Claude #Glean