Expert insights on AI email assistants

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 Highlight outdated files or duplicated info.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

Gmail’s AI email assistant writes like a committee of lawyers designed it. Pete Koomen’s recent post Horseless Carriages explains why: developers control the AI prompts instead of users. In his post he argues that software developers should expose the prompts and the user should be able to control it. He inspired me to build my own. I want a system that’s fast, accounts for historical context, & runs locally (because I don’t want my emails to be sent to other servers), & accepts guidance from a locally running voice model. Here’s how it works: 1. I press the keyboard shortcut, F2. 2. I dictate key points of the email. 3. The program finds relevant emails to/from the person I’m writing. 4. The AI generates an email text using my tone, checks the grammar, ensures that proper spacing & paragraphs exist, & formats lists for readability. 5. It pastes the result back. Here are two examples : emailing a colleague, Andy (https://lnkd.in/gtjt3BPp), & a hypothetical founder (https://lnkd.in/gDwM4f22). Instead of generics, the system learns from my actual email history. It knows how I write to investors vs colleagues vs founders because it’s seen thousands of examples. The point isn’t that everyone will build their own email system. It’s that these principles will reshape software design. - Voice dictation feels like briefing an assistant, not programming a machine. - The context layer - that database of previous emails - becomes the most valuable component because it enables true personalization. - Local processing, voice control, & personalized training data could transform any application, not just email, because the software learns from my past uses We’re still in the horseless carriage era of AI applications. The breakthrough will come when software adapts to us instead of forcing us to adapt to it. Centered around a command line email client called Neomutt (https://neomutt.org/). The software hits LanceDB, a vector database with embedded emails & finds the ones that are the most relevant from the sender to match the tone. The code is here (https://lnkd.in/gZ-AaAWa).

Anthropic just shipped Skills, Microsoft 365 integration, and enterprise search for Claude. After talking to dozens of enterprise companies this year, I think they're solving the right problems. 💰Context tax is killing enterprise AI adoption. Most AI tools require you to manually gather information before asking useful questions. You're copying emails, uploading documents, explaining organizational context. The AI might be smart, but you're doing all the integration work. Claude's Microsoft 365 connector changes this. Direct access to SharePoint, Outlook, Teams, and OneDrive means the AI already knows what your organization knows. Ask about Q3 strategy, and it pulls from the actual discussions, documents, and decisions. They also launched Skills — reusable instruction bundles that work across Claude's web app, API, and command-line tool. Think of these as expertise packages—instructions, scripts, and resources Claude loads on-demand. And lastly, the new Enterprise search is a shared project that searches multiple connected tools simultaneously. One query pulls information from HR docs in SharePoint, email discussions in Outlook, and team guidelines from various sources—then synthesizes it into a single answer. Model providers like Anthropic and OpenAI are realizing that enterprise AI needs to be operational, not just conversational. Less chatbot, more sidekick that accesses your actual systems and takes action.

Can You Tell the Difference Between AI and Human-Written Emails? I had the opportunity to serve as an expert judge for a Washington Post feature by Geoffrey Fowler, evaluating five emails written by different AI tools—Claude, DeepSeek, ChatGPT, Copilot, and Gemini—plus one from a human writer. The challenge? Figure out which email was the best. The results? Claude won - (it even beat the human writer!) Here’s why—and what it tells us about the future of AI-powered communication: -AI Emails Are Improving—But Not All Are Created Equal Each AI-generated email had a distinct style. Some were overly formal, others were robotic, and a few completely missed the mark. Claude’s writing stood out for being the most natural, structured, and persuasive. But here’s the catch: AI-generated emails don’t all sound the same. Each tool has its own strengths and weaknesses:   •  Claude excelled at clarity, nuance, and sounding the most human.   •  ChatGPT was engaging but sometimes too wordy.   •  Copilot was direct but lacked warmth.   •  Gemini and DeepSeek struggled with context and precision. The takeaway? Choosing the right AI assistant matters. - The Best AI Emails Feel Personal—Without Overdoing It One of the biggest issues with AI-generated emails is tone mismatch. Many sound overly polished—so much so that they feel fake or even manipulative. For professionals using AI to write emails, this is key: Your AI assistant should enhance your tone, not erase it. - AI Is Great at Writing—But Terrible at Judgment One thing was clear from judging these emails: AI is brilliant at sentence structure but still struggles with discernment. Some AI tools misread the email’s context, making unnecessary recommendations. None of the AI-generated emails fully adapted to the emotional nuances of the request. This reinforces what I always tell executives: AI can help draft, but humans must decide. Before sending an AI-assisted email, ask yourself: -Does this actually answer the question? -Does it sound like me? -Would I feel good receiving this? The best professionals don’t just use AI—they train it to reflect their judgment, communication style, and emotional intelligence. Can you detect the difference between AI-written and human emails? Share your thoughts in the comments! (and full article in comments!)

Last week, the AI safety world caught its breath as security researchers demonstrated how an LLM could be tricked by a fake email into opening malicious links, all without human intervention. That’s right: your AI assistant, heralded as your productivity savior, might just become your most polite cybercriminal. While we’ve long accepted that humans are the weakest link in cybersecurity, it seems we’ve successfully outsourced that weakness to our machines. Progress? AI systems are now parsing emails, browsing the web, summarizing documents—and doing it all with the trust level of a golden retriever and the attention span of a squirrel. Combine that with prompt injection attacks that still fly under the radar, and we’re not far from an LLM confidently summarizing “Prince of Nigeria” emails as legitimate business opportunities. The takeaway? Governance is no longer a checkbox—it’s an arms race. If your AI policy consists of “don’t be evil,” you might want to update it to “don’t be gullible.” In the meantime, CISOs should start asking themselves: • Who’s vetting what our AI tools can access? • What’s our policy for AI-generated actions? • And most importantly: Can our AI tell the difference between a phishing attempt and a meeting request from Steve in accounting?