top of page
The AI Edge


Your AI Assistant Can Now Make the Phone Call for You
Level: Beginner What's happening On November 4, 2026, xAI's Grok Bot started placing real phone calls for its users. You tell it who to call and what you need: book a table, move an appointment, ask a utility about a bill. It shows you who it plans to call, and nothing dials until you tap Call. Every call opens by saying it is a virtual assistant calling on your behalf. While the call runs, you follow a live transcript and can hang up or take over at any time. If the other si
Benjamin Tassin
6 days ago2 min read


Fable 5.2 Is the Dump Truck. Opus 5.5 Is the Pickup.
Level: Beginner What's happening On Monday, November 9, Anthropic released Claude Fable 5.2. It is the strongest Claude model you can use today, and it is available on every paid Claude plan. The quick numbers: up to 30% faster than Fable 5.1, and the API price dropped 20%, from $10 to $8 per million input tokens and from $50 to $40 per million output tokens. Its sibling, Mythos 5.2, is the same underlying model with fewer guardrails. That one is only open to vetted organizat
Benjamin Tassin
Nov 92 min read


I Had a Phone Call With My AI: Meet Muse
Level: Beginner What's happening Meta released Muse on September 8, 2026. It runs at muse.ai, on iPhone and Android, inside WhatsApp, and on Mac. Most AI tools are a chat window. You ask, it answers, you close the tab, and it forgets you. Muse is built the other way. You get your own agent, running on its own dedicated cloud computer, and it stays with you between conversations. What that means in practice: It remembers. Your work, your preferences, your people, your open pro
Benjamin Tassin
Nov 83 min read


Two AIs Are Better Than One: Meet AI Relay
What's happening A research paper posted to arXiv in October put a simple question to the test: when one AI writes something, does it help to have a different AI review it? The setup was 30 documents with 150 planted errors and 900 review sessions. The finding that matters for the rest of us: different models catch different mistakes. One review by the same model plus one review by a different model caught 56.7% of the planted errors. Two reviews by the same model caught 42.7
Benjamin Tassin
Nov 15 min read


How I Built an AI Journal That Saves Itself to Google Drive
What's happening On October 6, Anthropic opened Claude for Google Workspace to all paid Claude users as a public beta. It puts Claude in a sidebar inside Google Docs, Sheets, and Slides. It also adds connectors so Claude can work on those files from a normal chat when you paste in a link. Translation: your AI and your Google Drive are getting a lot closer. That opens the door to small, personal systems that just run in the background. My journal is one of them. What my Journa
Benjamin Tassin
Oct 204 min read


Your AI Advisors Will Agree With You. Here Is the Fix.
What's happening Researchers at Johns Hopkins University and the Vector Institute had AI agents debate questions to see if more voices led to better answers. Often they did not. Agents flipped from right answers to wrong ones just to match the group, and on some tests accuracy dropped the longer the debate ran. The takeaway: AI tends to favor agreement over pushing back on bad reasoning. That matters if you use AI to help make decisions. One AI that agrees with you is a probl
Benjamin Tassin
Oct 132 min read


Stop Asking AI to Help. Start Handing It the Job.
What's happening On September 16, Anthropic merged Claude Cowork and regular Claude chat into one Claude. Before, you had to pick: chat for quick questions, Cowork for bigger jobs. Now you just ask. Claude figures out if it is a quick answer or a task that takes an hour, and it keeps working even after you close your laptop. Two new tools came with it: Claude Docs and Claude Slides. Ask for a document and you write it together. Ask for a deck and Claude drafts the slides. You
Benjamin Tassin
Oct 72 min read


Put an AI in Your Ear for Your Next Meeting
What's happening Meeting AI is growing fast. In Metrigy's 2025-26 study of 1,100 companies, 42% said they plan to roll out AI meeting assistants in the next year. Most of those tools still work after the meeting. They hand you notes, a summary, and action items once the call is over. That is useful. It does not help you in minute 12, when a customer asks a hard question and everyone is looking at you. The newer move is live help. Some tools now let you ask questions during th
Benjamin Tassin
Oct 73 min read


AI Teammate or AI Workbench? Grok Bot vs. Claude, Pros and Cons
What's happening xAI launched Grok Bot in early beta in August 2026. It is a different kind of AI tool than the chat window most people know. Each Bot gets its own cloud computer, signs in to your tools, and only checks back when a job is done or needs your approval. That puts Grok Bot and Claude in two different categories. Grok Bot is an AI teammate- you hand it work and it goes. Claude is an AI workbench- you sit down with it and build the final product step by step. Neith
Benjamin Tassin
Oct 23 min read


Write Emails That Sound Like You
How I built my voice file This isn't a one-off prompt that will magically create your voice. It may take time and practice to build it. 10 emails may not be enough. You may want to ask your AI to go through your sent emails to develop your "voice". I built a voice file that my AI agents can grab and use to draft emails. It is one document that tells any AI how I actually write. Here is how I did it. 1. Pull real sent emails. I started with my business Gmail, then added a b
Benjamin Tassin
Sep 253 min read


Small Businesses Are Already Using AI to Find $13,000 and Make $60,000 in 4 Days — Here's How
What's happening Claude for Small Business just rolled out 43 new workflows and 27 new integrations — connecting to tools you probably already use, like QuickBooks, Shopify, Square, and Gusto. But the news isn't the feature list. It's the results real owners are getting: a baby retailer built a lead-capture tool in a few days and tied $60,000 in sales to it before the pilot even wrapped. A bookkeeping firm used it to isolate 16 transactions hiding a $13,000 discrepancy that a
Benjamin Tassin
Sep 201 min read


Automation Doesn't Mean Robots
Automation doesn't mean robots. Most of the time it just means people stop doing the same boring task over and over. Take a simple example — a contractor gets a new lead. Someone copies the info into a spreadsheet, emails the salesperson, then adds it to the calendar. Three steps, all manual, for one lead. Do that 20 times and you've burned a chunk of your week on copy-paste. Automation handles that instead. The lead comes in, it gets logged, the right person gets notified, a
Benjamin Tassin
Sep 151 min read


AI Gets Better With Context
This is Ben, owner and operator of AIM. This is not a copy paste from ChatGPT or Claude, but straight from my brain to keyboard to you with no editing so bear with. I get asked how I get AI to produce repeatable and favorable outcomes (most of the time) — like the AI knows exactly what I want. For instance, I can give a friend the same prompt I use but the results will be wildly different. That is because an LLM — Chat or Claude or Gemini or Grok — all need context. The more
Benjamin Tassin
Sep 151 min read


How Many Times Does Your Team Retype the Same Information?
How many times does your team or your employees enter the same information over and over? Think about a normal customer request. It comes in through an email or phone call. Then someone puts it in a spreadsheet. Then maybe into a scheduling system. Then it gets entered again for an invoice. Why are we doing all of that? Every time we re-enter the same information, we waste time and create another chance for a mistake. The problem is, after doing it this way for years, we stop
Benjamin Tassin
Sep 151 min read
bottom of page
