AI Tools For Communication

Zapier is serious about AI fluency in hiring, but we also know that the level of access and building we're expecting is unique in this space. If your only exposure to AI has been the AI built into your tech stack, and you're interested in working at Zapier (or anywhere with a high bar for AI fluency), let's change that! Here are 5 things you can build today with a free trial on Zapier: 1. Email agent → build an agent that reviews your email, flags the high priority messages, and drafts responses. Evolve it by having it also send a Slack message where you can edit/approve responses so you never even have to open your email. 2. Meeting prep agent → Build an agent that scans your calendar each morning for external meetings, pulls relevant email threads and docs for each meeting, and sends you a Slack summary. Evolve it by having it DM you relevant talking points 15 minutes before each. meeting. 3. Weekly wins agent → Build an agent that reviews your calendar, emails, and Slack messages from the past week and writes a draft of what you accomplished that you can reference in 1:1s, performance reviews, etc. Evolve it by having it automatically update a doc so you've got a running list. 4. Research/content agent → Build an agent that monitors topics you care about (competitors, industry news, your name) and sends you a daily digest with reference links. Evolve it by having it prioritize topics to share in your newsletter, social media, etc. (You could also have it create drafts, but as someone who doesn't believe in using AI in this way, I personally wouldn't!) 5. Opportunity tracker agent → Build an agent that monitors your inbox for recruiter outreach, application updates, and interview scheduling emails, then maintains a running tracker doc with status, company, and next steps for each. Or for sellers, you could do the same for sales opportunities. Evolve it by having it automatically draft follow-up emails at the right intervals so nothing falls through the cracks. The bar for AI fluency in 2026 is no longer using AI assistance or being open to the AI features in your tech stack. It's building solutions that increase your productivity, efficiency, and impact. And each of the agents above is an easy to build solution that achieves that, and that you can use to demonstrate solid AI fluency in interviews. Pick one of these agents and build it today (or share something else you've built with us!)

For PMs who want to use AI agents to be more productive but feel stuck coming up with ideas, I've been experimenting with a prompt: (this works best in a project that already has context on you/your team/product) ❝❝❝ Based on what you know about me and my organization, please brainstorm five ideas for an AI automation I can build using platforms such as Zapier Agents/Lindy AI/Relay app/Cassidy AI/Gumloop/ etc. These should help me as a product manager save time on draining-yet-essential tasks that take me away from more valuable, strategic, and creative use of my attention and energy. Ask yourself: What ongoing repetitive work requires some judgment and writing abilities, but not my full expertise and intuition? # IMPORTANT: these should be event-driven AI automations, not batch tasks Only suggest event-driven automations that process items one-at-a-time as they arrive. Do NOT suggest batch tasks that process multiple items on a schedule (e.g., "every morning scan all..." or "weekly compile..."). Why: AI automations shine in one-at-a-time, repetitive tasks. They do best when designed for immediate responses to individual triggers. ❌ WRONG (Batch Task): "Every morning, scan all new support tickets and summarize them" ✅ RIGHT (Event-Driven): "When a new support ticket arrives, analyze it and alert me if it's urgent" # Examples Below are examples of use cases where product managers have gotten a lot of value from AI agents. 1. Compile fragmented information that would require a lot of clicks “When a new message is posted in the #feature-requests Slack channel, distill the customer request into 2-5 keywords. Search those keywords in recent Slack threads, HubSpot conversations, and Gong snippets, and reply to the thread with what you find.” “Every morning scan my calendar for customer calls, and instead of searching the web, DM me with recent interactions from this customer in Salesforce, Gong, and Zendesk.” “Every Monday morning, prepare a competitor activity digest by scanning recent blog posts, App Store updates, and X announcements.” “When a customer churns, post a message in the #churn-lessons channel with recent support interactions, NPS rating and date, and churn survey response.” 2. Boring, Sisyphean tasks with high upside “Monitor the pricing pages of 5 competitors for changes.” “DM me a weekly report with bugs that are nearing their SLA deadline for the associated customer, and cc each respective CS representative.” 3. Scanning exhausting amounts of data “DM me with support cases where the resolution was around product confusion rather than tech.” “Monitor NPS responses being posted as messages in a Slack channel. If something is clearly a technical issue, create a support ticket in Zendesk.” 4. Drafting updates “Every Friday at 10 a.m., write a summary of progress made across all teams in our project board, across epics, changes made to scope, and highlight any timeline changes.” ❞❞❞

Imagine this: You're knee-deep in NGINX server errors, sifting through logs in Elastic Discover. The AI Assistant is already helping you analyze error messages, providing context, and suggesting next steps. But what if we could take it a step further? Here's the secret sauce: Custom prompting to unlock hidden powers! 🔓 I found out that our AI Assistant can actually execute connectors, call Elasticsearch and Kibana APIs, and even generate queries. The key? Teaching it how to use these functions through clever prompting. Here's what I did: 1. Edited the user-specific prompt 2. Used tagged instructions (inspired by the Claude System prompt that was released) 3. Taught the AI how to call the Elastic email connector (steal my prompt below) Here are specific instructions for different types of queries: <email_instructions> If the user's query requires sending an email: 1. Use the Elastic SMTP connector with ID "Elastic-Cloud-SMTP". 2. Prepare the email parameters:   - Recipient email address(es) in the "to" field (array of strings)   - Subject in the "subject" field (string)   - Email body in the "message" field (string) 3. Include - Details for the alert along with a link to the alert - Root cause analysis - All of the details we discussed in this conversation - Remediation recommendations - Link to Business Health Dashboard 4. Execute the connector using this format:   execute_connector(    id="Elastic-Cloud-SMTP",    params={     "to": ["recipient@example.com"],     "subject": "Your Email Subject",     "message": "Your email content here."    }   ) 5. Check the response and confirm if the email was sent successfully. </email_instructions> The result? Magic! ✨ Now, when I ask the AI Assistant to send me an email summary of an error, it doesn't just say "I can't." Instead, it springs into action: - Analyzes the error - Crafts a detailed summary - Sends it directly to my inbox This is a complete transformation of our troubleshooting workflow. We've gone to a fully agentic process that can interact with external systems. The possibilities are endless: - Update ServiceNow tickets automatically - Send Slack notifications - Trigger remediation actions for known issues And the best part? You can customize this to work with any connector or webhook you have set up. It's like giving your AI Assistant superpowers tailored to your specific needs. #AIforSRE #ElasticObservability #AutomationTips #SRELifeHacks #AIOps https://lnkd.in/enNum-Nn

SO many times I've wished I could talk to my Gmail and ask questions. But since Google hasn't set up those tools yet (get crackin' Alphabet!), I created a fairly easy AI workaround to make it possible. The idea with this is that you'll use a Google App Script (don't worry, you don't need to know code!) to analyze your messages. Here's how it works: 1. Put a Google label on any emails that you want to review. That might be all emails from a certain date range, or just the ones sent to a certain person or company. This is an important first step, because AI can't read your entire inbox at once. 2. Ask ChatGPT to create a Google App Script for you using this exact prompt: “Can you create a Google Apps Script that pulls all Gmail messages with the label ‘[Your Label Name]’ into a spreadsheet with columns for Date, To, From, Subject, and Body?” You’ll get a clean, copy-paste-able script that you can drop into https://script.google.com. When you run the script, it’ll export every email with that label into a Google Sheet — no coding experience required. 3. Once your messages are in your Sheets (or an exported spreadsheet) you can ask ChatGPT to help you analyze them. You can say things like: How many times did I email this person in June?” OR “Summarize my back-and-forth with this client.” OR "Are there any pending to dos for this account?" This AI workflow is one of the most helpful ways I’ve found to review my own communication, whether I’m wrapping up a project, prepping for a meeting, or just making sure I didn’t forget to follow up. It's literally saved me half a day of analysis every months. Happy to share the exact script and prompts I've use if you want to try it!

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?

Still drowning in email? That’s a choice. Email sucks. Full stop. When did you hear someone say, "I love email!"? P.S. if someone says that, run away from them... Joking aside, almost every customer we have at one point has joked, "When will AI be able to clean out my inbox?". Well, I decided to spend one day finding out... I made a scrappy little sidekick I now call "Email Pal", built on n8n + OpenAI, integrated w/ Outlook (could also be Gmail). Here is how it works: 1. Tags my incoming emails with categories I actually care about and defined (Opportunities, News, Invoicing, Solicitations, etc.) 2. Drafts smart replies based on the whole thread and other related data, so I don’t respond like a robot. 3. Changes tone depending on who it’s talking to (client ≠ recruiter ≠ founder friend). 4. Finds follow-ups I forgot and drafts those little polite but firm nudges: “You mentioned sending a doc…haven’t seen it yet. Just bumping this :)” Next Steps: Integration w/ CRM and other project delivery systems to build additional context on the overall relationship w/ our customers. Keep in mind, this solution is only for DRAFTS. I tweak, approve, and send. Always. I still wouldn't trust AI to email on my behalf (at least not externally). This isn’t a product. It’s a prototype. But it’s already rescued a deal, recovered meetings, and saved me hours. Email Pal is one of dozens of tiny, high-leverage systems we’ve built. Want to see it in action? Drop me a note. 👇 (Screenshot below) [This post was Human Generated, Human Approved]