Small Steps with AI

Jill McKinley
  • 0.0 (0)
  • Technology
  • Weekly

AI isn't just a search engine. It can help you think through a hard decision, organize your house, plan your retirement, and sometimes — if you let it — say exactly what you needed to hear. Small Steps with AI is hosted by Jill from the Northwoods, a real person figuring out how this technology fits into real life. No coding. No hype. Just small steps.

  1. 12h ago

    AI Vocabulary, Part Two: MCP, APIs, Agents, and More

    AI Vocabulary, Part Two: RAG, APIs, Agents, and More AI has a language of its own. This episode explains retrieval-augmented generation (RAG), APIs, tool calling, MCP, agents, prompt injection, human-in-the-loop oversight, and the larger questions of intelligence and consciousness, using everyday examples. In this episode of Small Steps with AI, Jill from the Northwoods explores the topic through examples and practical observations. In this episode RAG and retrieving external informationAPIs, tool calling, and software accessAI agents, risks, and oversightIntelligence, consciousness, and human judgment Disclaimer [INSERT ORIGINAL SHOW-SPECIFIC DISCLAIMER HERE — exact approved wording not available in the uploaded transcripts] Find more from Jill from the Northwoods at https://jillfromthenorthwoods.com/

  2. Nov 4

    AI Vocabulary Explained in Plain English

    AI Vocabulary Explained in Plain EnglishSmall Steps with AI LLMs, tokens, machine learning, agents, AGI: AI conversations can sound like a secret language. This episode explains common artificial intelligence terms in everyday English, with examples that make the technology easier to understand and use. In this episode:• What artificial intelligence means• Machine learning and deep learning• Generative AI• Large language models• Tokens and context• Prompts and conversations• Chatbots and AI assistants• Agents and agentic AI• AGI and staying informed Explore more episodes at https://jillfromthenorthwoods.com

  3. Oct 28

    How AI Helped Me Adopt Two Cats

    How AI Helped Me Adopt Two Cats Can AI help with a personal decision without making the decision for you? After losing a beloved canary, I found myself weighing whether to welcome new pets into a suddenly quiet home. In this episode I share how an ongoing conversation with AI helped me sort through grief, timing, allergies, travel, cat-proofing, and whether to adopt one cat or a bonded pair. The result was two young brothers—and a useful example of AI as a thinking partner rather than a substitute for human judgment. IN THIS EPISODE• A different kind of AI story• Grieving a canary and considering a new pet• Why timing mattered• AI as a campfire conversation• One cat or two?• Finding the right rescue cats• Preparing the house and settling in• What AI did—and did not—decide CHAPTERS00:00 Introduction: How AI Helped Me Adopt Two Cats02:36 Grieving a canary and considering a new pet05:11 Why timing mattered07:49 AI as a campfire conversation10:21 One cat or two?12:55 Finding the right rescue cats15:33 Preparing the house and settling in18:07 What AI did—and did not—decide20:45 Putting the ideas together23:28 Practical lessons and reflections REFERENCES AND RESOURCESTools and topics mentioned: ChatGPT; Petfinder; bonded cat adoption; pet safety and cat-proofing. AI can help organize questions, but adoption decisions and animal care remain human responsibilities. Jill From the Northwoodshttps://jillfromthenorthwoods.com

  4. Oct 21

    What Not to Share with AI

    AI can explain, compare, draft, and troubleshoot, but useful assistance does not require handing over every private detail. I walk through a practical circle of trust for information, safer ways to share documents, and the extra care needed when AI suggests computer commands or advice with serious consequences. Ask Three Questions Before SharingWhat does AI actually need to know? What happens if its answer is wrong? What would happen if the information were exposed? These questions help separate relevant context from unnecessary identifying details and keep our judgment involved as tools become more capable. Red, Yellow, and Green InformationPasswords, login codes, recovery keys, and full account identifiers belong in the red category. Health, financial, employment, and other people's private information require careful judgment in the yellow category. Generalized examples and nonidentifying context can often provide a greener way to get useful help. Protect Other People and Work MaterialsA friend's diagnosis or a coworker's private situation is not ours to disclose casually. Workplace rules also matter: permission to use an approved company tool does not automatically cover a personal account. I share why checking the rules and removing unnecessary names can make a difference. Look Beyond the Question in a ScreenshotAI may notice more than the detail we intended to show. Documents and photographs can reveal addresses, account numbers, background objects, and other information. Crop to the relevant area and check the finished image before sharing rather than assuming the rest will be ignored. Keep Judgment over Actions and AdviceA command that fixes a problem can also delete files, change permissions, or modify a database. Understand it, make backups, and seek qualified help when needed. For medical, financial, and legal questions, AI can help organize information and prepare questions, while important decisions deserve professional verification. Before your next upload or powerful command, pause and ask the three questions. Share only what is needed, understand proposed actions, and increase verification as the stakes rise. jill@startwithsmallsteps.com and jillfromthenorthwoods.com A note on this podcast: I’m not a software developer or an AI professional, just someone who uses these tools every day and shares what’s working for me. Test anything I mention against your own situation before you rely on it. TIMESTAMPS 00:00 Using AI includes knowing when to pause01:59 Three questions for safer AI use03:05 Relevant context without identifiers06:54 Red information: credentials and codes12:07 Yellow information and privacy14:56 Other people and workplace rules16:39 Green information and general examples18:19 Crop documents and check screenshots20:53 Understand commands before running them23:42 High stakes and your final judgment

  5. Oct 14

    How AI Can Help People With Low Vision

    A listener asked me how AI might help someone with low vision, and that sent me into a series of experiments. I wanted to know what these tools could actually do with tiny print, household products, photographs, instructions, and ordinary objects, and just as importantly, where they could fail. AI Can Help With More Than ReadingA listener question sent me looking at how AI can help people who are blind or have low vision. I tested ordinary situations where a camera, voice conversation, and follow-up questions can turn visual information into something more usable. From Tiny Print to Useful AnswersMagnification and text recognition have been around for years, but generative AI adds another layer. It can read instructions, explain what they mean, answer questions about an object, and sometimes adapt the information to what you actually need. The Tools Are Getting More ConversationalI look at Apple Magnifier and voice features, Microsoft Seeing AI, Be My Eyes, and smart glasses. The interesting change is not simply that technology can recognize something, but that you can keep asking questions about what it sees. AI Can Be Right and Still Miss SomethingOne of my tests produced accurate information while skipping a line entirely. That is an important warning for visual accessibility because a person who cannot see the original may not know that anything was omitted. Match the Verification to the RiskA wrong shirt color is inconvenient. A wrong answer about medication, allergies, finances, legal papers, or physical safety can matter a great deal, so higher-risk situations need another source of verification. Try One Ordinary ThingAI does not replace established accessibility tools, training, specialists, screen readers, or human help. It can be one more flexible tool, and the best first experiment is something small and low stakes. The useful shift is from a tool that simply magnifies or reads to one you can question. Start with something ordinary, keep the stakes low, ask follow-up questions, and learn where AI fits alongside the accessibility tools and people you already trust. Contact: jill@startwithsmallsteps.com | jillfromthenorthwoods.com A note on this podcast: I'm not a software developer or an AI professional, just someone who uses these tools every day and shares what's working for me. Test anything I mention against your own situation before you rely on it. TIMESTAMPS 00:00 AI and low vision03:44 From magnification to conversation05:32 Testing AI on everyday objects07:35 Apple Magnifier and visual questions09:42 When a correct answer is incomplete11:31 Voice control and hands-free help13:35 Seeing AI, Be My Eyes, and smart glasses16:55 The confidence problem19:34 Low stakes versus high stakes23:24 Start with one ordinary task

  6. Oct 7

    I Used AI to Plan a Walking Tour of Marquette

    Someone who runs local walking tours emailed me asking how AI could help him. So I built a pretend scenario: I live in Marquette, Michigan, a friend is coming to visit, and I realize I don't actually know the story of my own town. What happened next shows the most useful AI skill there is, and it isn't prompt engineering. It's asking the next question. **Start With a Plain Question** My first prompt was simple: tell me something interesting about Marquette that I've walked past a hundred times without knowing its story. No role-playing, no special formula. Just a real question about something I cared about. **One Answer Leads to Another** Iron ore led to the Marquette Iron Company of 1849. That led to a settlement first called New Worcester, the Ojibwe community of Chief Charles Kawbawgam and his wife Charlotte, and Father Jacques Marquette, who explored the region nearly two centuries earlier. None of those were in my first question. **The Dock That Washed Away** Marquette's first dock was swept away by Lake Superior almost as soon as it was built. Asking AI to connect that failure to the massive 1931 Lower Harbor Ore Dock turned a concrete landmark I swam beside as a kid into a story about solving one problem over eighty years. **Old Fears About New Technology** The men who moved ore by wheelbarrow watched railroads and pocket docks change their work. The mix of wonder and job worry they felt is the same one many of us feel about AI now. **You're the Editor, Not AI** AI can be wrong, and confidently wrong. If you're going to repeat something to a friend or a tour group, ask for sources, look for a second independent confirmation, and check historical societies, museums, and archives. AI isn't the source. You're responsible for what you repeat. **Lunch Becomes Part of the Tour** A hungry stop turns into history too: the pasty, brought by Cornish miners, adopted by Finnish immigrants, and still a U.P. staple. Then the most useful question of all: "What haven't I asked yet?" You don't need to be a genius to use AI well. Tell it what you're trying to do and who it's for, push back when an answer isn't useful, ask for evidence when something sounds off, and keep asking the next question. It'll introduce you to names, places, and questions you didn't know existed. You can find everything I do at jillfromthenorthwoods.com, and you can reach me directly at jill@startwithsmallsteps.com. --- **A note on this podcast:** I'm not a software developer or an AI professional, just someone who uses these tools every day and shares what's working for me. Test anything I mention against your own situation before you rely on it. TIMESTAMPS 00:00 Using AI to explore your hometown 02:19 The first question 02:58 Iron ore and who founded Marquette 05:24 Why is it called Marquette? 09:38 The Lower Harbor ore docks 11:01 The dock that washed away 17:32 Building the walking tour 20:36 Verify what AI tells you 22:16 Lunch: the Upper Peninsula pasty 26:09 Ask AI what you're missing

  7. Sep 30

    AI Shopping Isn't Magic, But It's Close

    Online shopping gives us enormous selection, but selection isn't the same thing as clarity. This episode is all about how AI changes the shopping conversation, not by magically finding the perfect thing, but by listening to your whole problem the way a search box never could. **When "I Liked It Last Time" Stops Working** Shoe companies redesign their shoes. Hiking pants get discontinued. The old trick of just buying the same thing again falls apart the moment a product changes or disappears, and that's exactly where AI earns its keep. **Describing the Experience, Not Just the Product** Instead of searching for a shoe brand, you can describe what you actually liked about the old one, wide toe box, moderate cushioning, low heel drop, and ask AI to translate that into what's available now. It turns shopping into a translation problem instead of a search problem. **Finding a Chair Built for a Very Specific Body** I talk through how I used AI to find a chair for my short legs and short trunk-to-knee measurement, right down to it telling me exactly what to measure on myself before recommending five real options. **A Camera Upgrade Worth Actually Making** As a birdwatcher, I asked AI whether a newer version of my camera was worth it. It read through specs and reviews I couldn't find on my own and pointed to the one genuine upgrade that mattered for bird photography: subject tracking. **AI Asking You Questions Back** One of the most useful parts of shopping with AI is when it asks you questions instead of just answering yours: why do you want this, what isn't your current one doing for you. That's often where the real requirements show up. **Grocery Shopping and Food Substitutions** From tracing a friend's heartburn back to her coffee, to finding pepper substitutes for fajitas, AI can turn grocery shopping into an experiment instead of a guessing game. This podcast is for entertainment and educational purposes only. I'm not a software developer or AI professional, just someone who uses these tools daily and shares what I've learned. Find all of Jill's podcasts and videos at jillfromthenorthwoods.com. Questions or topic requests? Email jill@startwithsmallsteps.com. TIMESTAMPS 00:00 When "I Liked It Last Time" Stops Working 03:36 Describing the Experience, Not Just the Product 06:29 Finding a Chair Built for a Very Specific Body 07:48 A Camera Upgrade Worth Actually Making 10:12 AI Asking You Questions Back 12:20 Grocery Shopping and Food Substitutions 16:09 Making It Work for Clothes Shopping Too

  8. Sep 23

    Ask AI Before You Upgrade or Subscribe

    # Ask AI Before You Upgrade I got an upgrade email this week for photo editing software I already own, and instead of asking whether the new version was any good, I asked AI a completely different question: do I actually need this? **Ask "Is This For Me," Not "Is This Good"** Almost any piece of software is well-made. The real question is whether its new features match how you actually use it. I compared a new release against my own two specific use cases, cleaning up bad bird photos and prettying up sunset shots, instead of asking a generic "should I upgrade" question, and the answer came back no. **The Best Product Isn't Always the Best for You** The best professional video editor is wrong for someone who just wants a 30-second dog video, and the best backpacking boots are overkill for someone walking a paved trail. AI is good at translating a features list into "will this actually change your life," which a search engine and a comparison chart can't do. **Reading Subscription Tiers Through Your Own Life** Comparison charts tell you what each tier includes, but not which of those things you'll actually use. I described my real workflow to AI and let it sort the plans by relevance, sometimes landing on the cheapest tier, sometimes realizing the expensive one actually saves real time. **The "Beginner's Tax" on New Hobbies** Starting something new, like a Cricut crafting machine, tempts you to buy every accessory available. AI can help separate what a true beginner needs from what's aimed at advanced users, and can flag features you already own somewhere else entirely. **Running a Subscription Audit** I walked AI through my actual software subscriptions against what I really use, which led me to cancel a calendar app subscription once I realized Apple's built-in calendar already did the job. Sometimes the answer AI gives you is simply: you already own this. The real shift isn't that AI makes things cheaper. It's that it can ask "what problem are you actually trying to solve" instead of trying to sell you something. Before your next upgrade or subscription, try handing AI your actual use case and your budget, and see what it tells you to skip. You can find everything I do at jillfromthenorthwoods.com, and you can reach me directly at jill@startwithsmallsteps.com. --- **A note on this podcast:** I'm not a software developer or an AI professional, just someone who uses these tools every day and shares what's working for me. Test anything I mention against your own situation before you rely on it. TIMESTAMPS 00:00 The software upgrade email 01:29 Asking "do I need this," not "is it good" 05:29 The best product isn't the best for you 08:26 Reading subscription tiers through your own life 12:21 A real example: choosing a website plan 17:16 The Cricut trap and the "beginner's tax" 23:07 Why AI beats upselling 26:36 Assigning AI a skeptical role on purpose 28:34 Running a full subscription audit 32:01 The cost of complexity, and the closing takeaway

See All (33)

About

AI isn't just a search engine. It can help you think through a hard decision, organize your house, plan your retirement, and sometimes — if you let it — say exactly what you needed to hear. Small Steps with AI is hosted by Jill from the Northwoods, a real person figuring out how this technology fits into real life. No coding. No hype. Just small steps.

Information

  • Creator
    Jill McKinley
  • Years Active
    2026
  • Episodes
    33
  • Rating
    Clean
  • Copyright
    © Copyright 2026 Jill McKinley
  • Show Website
    Small Steps with AI