#46 One Minute Blog: 3 AI Prompts


It's Friday. And this is your One Minute Blog (OMB) – AI edition. A short email of good stuff for you to think about over the weekend, that takes about a minute to read this time with a tiny shot of prompt magic, delivered even faster than your thoughts.

Read time: Approx 1 minute.


Want to actually use AI this Monday, not just read about it? Here are a few killer prompts to try, straight from the latest AI releases. Dive in:

  1. For the Corporate Strategist (using Anthropic's Claude with Research):
    • Prompt: "Research the key challenges and opportunities for entering the [your specific target market] market. Use our internal Q1 product feedback (upload it!) and recent online industry reports. Give me a summary and three strategic recommendations."
    • (Why? Turns raw data & web noise into actionable strategy.)
  2. For the Productivity Seeker (using Notion AI for Work):
    • Prompt: "Summarize all discussions related to Project Phoenix from my meeting notes, Slack messages, and emails in the last month, and identify key pending decisions."
    • (Why? Cuts through clutter to find what actually needs doing.)
  3. For the Developer & Data Whiz (using OpenAI's Codex in ChatGPT):
    • Prompt (Corp Pro focused): "Write a Python script to read ‘sales_data.csv’, calculate the total sales per region, and output a new CSV with ‘region’ and ‘total_sales’."
    • (Why? Automates data tasks you thought needed a specialist.)

Feeling that spark? These are just a taste.

Get the full breakdown of 9 major AI updates (OpenAI Codex, Google's AlphaEvolve, Notion AI, Meta's CoRaL, ElevenLabs sound, and more), complete with use cases for devs AND corporate pros, plus ALL the prompts to try...

Subscribe to "Last Week in AI" for your weekly 3-minute power-up: 👉 lastweekai.com/subscribe 👈

That’s all for this minute. Go make Monday count.

-CT

Sunday Scoops

Business & Tech in 5 minutes or less.

Read more from Sunday Scoops

Anthropic dropped Claude Opus 4.7 this week, this model is built for long-running coding tasks, multi-file refactors and complex debugging sessions. From my early testing the model is quite different to what we are used too and it tends to ask lots of followup questions similar to what we've seen with GPT 5.4 and in comparison to Opus 4.6 we see fewer tool errors, and crucially the model now verifies its own outputs before reporting back. Cursor’s CEO called it “a meaningful jump in...

👋 The thing about AI right now is that most people are using it the same way they used Google in 2005. They type a question. They get an answer. They move on. That’s fine. But it’s leaving most of the value on the table. This week, I’m running a series called Get AI Native in 2026. Not a course and definitely not theory. Every issue, I’ll walk you through one or two things you can actually set up this week that will change how you work. Step by step. This issue is about two tools that...

After three years of hype, AI is finally meeting reality. The gap between a cool demo and a working business is closing fast. LLMs are writing production code, robots are landing on doorsteps, and autonomous taxis are actually turning a profit. We have moved from “what if” to “what is.” Here is the current state of the frontier: from the infrastructure of open source to the rise of physical world agents, and the inevitable shift toward AGI and monetization. the models Most people still...