The Reason AI Gives You Useless Answers  🔗 **Source:** [The Reason AI Gives You Useless Answers](https://www.youtube.com/watch?v=o2S1ZbmVAAY#transcript) > [!note]+ Document Notes > --- > tags: [personal-knowledge-management, context-engineering, ai-workflows, prompting, second-brain, delegation] > author: Tiago Forte > source: Tiago Forte (YouTube) > reference: https://www.youtube.com/watch?v=o2S1ZbmVAAY > date created: 2026-06-17 14:10 > --- > # 🏷️ Title: The Reason AI Gives You Useless Answers (Fix This First) > ## 🧭 Table of Contents > - [📝 Summary](#-summary) > - [📖 Main Content](#-main-content) > - [🗒️ Notes](#️-notes) > - [📚 References](#-references) > - [🗣️ Paraphrase](#️-paraphrase) > - [📰 Newsletter](#-newsletter) > - [✅ Action Items](#-action-items) > - [🧪 Hypotheses](#-hypotheses) > - [📊 Methodology](#-methodology) > - [❓ Questions](#-questions) > - [🔮 Future Research](#-future-research) > - [💡 Implications](#-implications) > - [🧠 Learning Styles Assessment](#-learning-styles-assessment) > - [📊 Accessibility Assessment](#-accessibility-assessment) > - [🌍 DEIB Assessment](#-deib-assessment) > - [✅ Logical Validity](#-logical-validity) > - [🛡️ DARVO Analysis](#-darvo-analysis) > - [🎯 Conclusion](#-conclusion) > ### 🔗 References > - [Tiago Forte — Building a Second Brain](https://www.buildingasecondbrain.com) > - [The PARA Method](https://fortelabs.com/blog/para/) > - [Forte Labs — AI Second Brain program](https://fortelabs.com) > - [Obsidian](https://obsidian.md) > ## 📝 Summary > - **What happened.** Tiago Forte argues that the reason AI returns generic, surface-level answers usually isn't a bad prompt — it's missing *context*. He names the skill "personal context management" (PCM), defines its three layers (persistent, project, perishable), and demonstrates them live in Claude Cowork by progressively feeding context into the same book-launch request and watching the output go from vanilla to executable. > - **Why it matters.** It reframes the popular "prompt engineering" obsession as the wrong lever. The bottleneck moves from how you phrase a request to how well you've curated and staged the surrounding information — a shift that maps cleanly onto note-taking and knowledge-management practice rather than technical skill. > - **Key stakeholders.** Knowledge workers using AI assistants; people already running PARA/second-brain systems; anyone storing notes in tools like Obsidian; and Forte Labs (whose "AI Second Brain" program this video funnels toward). > - **Risks and tradeoffs.** As you manage context better, you do less of the actual work yourself — the constraint shifts from output to clarity of intention. Forte also pushes back hard on the industry term "context engineering," which is partly a definitional/branding argument, not a purely empirical one. > - **Bottom line.** Don't fix your prompt first — fix your context. Stage three layers (persistent → project → perishable), and treat the practice as delegation to a system. The identity you grow into is "Context Architect." > ## 📖 Main Content > - **The misdiagnosis.** You gave the AI good information and wrote a good prompt, but the answer came back generic. Forte's claim: the failure is in the *context* you did or didn't give, not the prompt wording. This is the framing the whole video hangs on. > - **PCM defined.** Forte has taught personal knowledge management (PKM) for a decade — "a system for preserving and then resurfacing your best knowledge." AI changes the audience for your notes: they're no longer just for you, they're inputs to a system that acts on your behalf. He renames the evolved practice **personal context management (PCM)** — cultivating the right context so AI can do meaningful work for you. > - **The three layers (the "three Ps").** > - *Persistent context* — stable, durable facts about who you are (role, values, communication preferences) that inform every interaction. Lives in your "master prompt," stored in custom instructions / personal preferences, so you don't repeat yourself each conversation. > - *Project context* — what you're working on right now: product details, decisions, research, stakeholders, deadlines, objectives. In PARA, this is a single project folder. Forte argues PARA users have been "preparing for PCM without even knowing it." > - *Perishable context* — the precise, minimal slice the AI needs for one specific request: the latest nuance and subtlety that lives only in your head. > - **The live demo.** In Claude Cowork with memory, connectors, skills, and preferences all turned off (a "blank slate"), Forte asks for a launch/marketing plan for his book *Life in Perspective* (out November 3). With no context the output is "completely generic." He then layers in (1) his master prompt as custom instructions, (2) the project folder plus his Obsidian vault (where the book's raw material lives), and (3) a perishable brain-dump (his son was born May 11, take it easy a few weeks, cut the podcast idea, prioritize highest-leverage activities). The plan moves from one-size-fits-all to "so dialed in" it's executable. > - **Pushback on "context engineering."** Forte concedes the industry calls this "context engineering" but objects to "engineering" — it implies a technical skill. He argues it's really arranging ordinary information (text, images, files, folders) into "loosely curated collections" and pointing AI at them: "this isn't engineering, it's just managing information." Caveat: accessible ≠ easy; you have to think at the level of the broader system. > - **Three identity shifts.** > - *Curating context* — spend your time finding the most detailed, specific, nuanced, contrarian, up-to-date context; act like a scientist or explorer seeking sources outside the AI's training data. > - *How you spend your time* — the better you manage context, the less execution you do yourself. The bottleneck moves "up a level or two" from output to clarity of intention. PCM is **delegation to a system instead of a person**, and the constraint is identical: the quality of your handoff. > - *Getting clearer about what you want* — AI "homogenizes" and "flattens" knowledge; the way to stand out is to externalize your judgment, taste, values, and opinions "so the AI can borrow it." The deepest reframe: PCM isn't curating data, it's curating *yourself*. > - **The identity.** "PCM is the practice. Context Architect is who you become when you embrace it." It's not a new methodology but a new lens on what you already do — the notes, projects, and prompts. The video closes by pitching the AI Second Brain program. > ## 🗒️ Notes > #### ⏱️ [00:00:00](https://www.youtube.com/watch?v=o2S1ZbmVAAY&t=0) The misdiagnosis: it's the context, not the prompt > - You did everything right and still got a generic answer; the problem is the context you're "not giving." > - Promises three things: a name for the skill, the three layers, and the identity that comes with it. > #### ⏱️ [00:00:34](https://www.youtube.com/watch?v=o2S1ZbmVAAY&t=34) From PKM to PCM > - Ten years teaching personal knowledge management — "a system for preserving and then resurfacing your best knowledge." > - AI changed *who's reading* your notes: they're now inputs to a system acting on your behalf. New name: personal context management (PCM). > #### ⏱️ [00:01:08](https://www.youtube.com/watch?v=o2S1ZbmVAAY&t=68) Layer one — persistent context > - Stable, long-term details: role, values, communication preferences. > - Lives in the "master prompt" stored in custom instructions / personal preferences, loaded every interaction. > #### ⏱️ [00:01:40](https://www.youtube.com/watch?v=o2S1ZbmVAAY&t=100) Layer two — project context > - Active, scoped info: product details, decisions, research, stakeholders, deadlines, objectives. > - In PARA, all of this lives in a single project folder — "you've already been preparing for PCM without even knowing it." > #### ⏱️ [00:02:12](https://www.youtube.com/watch?v=o2S1ZbmVAAY&t=132) Layer three — perishable context > - The precise minimal slice for one specific request; nuance/subtlety that only lives in your head. > - "Persistent, project, perishable. Three Ps, three layers." > #### ⏱️ [00:02:45](https://www.youtube.com/watch?v=o2S1ZbmVAAY&t=165) The blank-slate demo setup > - Claude Cowork with memory off, connectors disconnected, no skills, empty preferences. > - Task: launch/marketing plan for *Life in Perspective* (out November 3). > #### ⏱️ [00:03:49](https://www.yo You've done everything [music] right. You gave the AI all the information it needed. You wrote what you thought was a good prompt, and the answer [music] came back generic, surface-level. The problem isn't in your prompt. It's in the context you're giving, or more specifically, [music] not giving it. In this video, I'm going to give you a name for that [music] skill, the three layers it operates on, and the identity that comes with practicing [music] it well. For 10 years now, I've been teaching personal knowledge management. [music] It's a system for preserving and then resurfacing your best [music] knowledge. But, AI has completely changed who's reading it. Your notes >> [music] >> are no longer just for you. They're also now inputs to an AI [music] system that can act on your behalf. This practice has a name. It's called personal context management, PCM. [music] And it's not just about cultivating human knowledge anymore. It's about cultivating the right context [music] so that AI can do meaningful work on your behalf. PCM operates on three different layers. Layer one is persistent [music] context. This is where you tell the AI who you are, the stable, durable, long-term details >> [music] >> that inform every single interaction with AI. Your role, your values, your communication preferences. The aspects of your work and your life that inform [music] practically everything you do. This all lives in what I call your master prompt, which is stored in your personal preferences [music] or your custom instructions. This way you don't have to repeat yourself at the start of every single conversation. [music] Layer two is project context. In other words, what you're working on right now in this moment. [music] Active, scoped kinds of information, like product details, decisions you've made, research you've done, information [music] about the stakeholders, the deadlines, the objectives. If you've been using my PARA method, all this lives in a single project folder. You've already been preparing for PCM without even knowing it. [music] Layer three is perishable context. This is the precise minimal slice that the AI needs [music] to do its job. It's just for this specific request, what little bits of context and details [music] and nuance and subtlety is going to help it get to a useful result. [music] Persistent, project, perishable. Three Ps, three layers. Together, they're what we mean when we [music] say context. In the AI second brain, we actually expand [music] on each of these layers in much more depth. In just a second, I'll show you what each of these three layers does to the same prompt and watch the answer go from generic to genuinely [music] useful. So, this is Claude Cowork. It's a completely blank slate. So, I've turned off all the memory features right here. Memory is off. I've also turned off all of the connectors, disconnected them, and all the skills, and there is nothing in my personal preferences. You can see it's blank. Now, the thing I'm going to get Cowork's help on is creating a launch and marketing plan for my new book, Life in Perspective, which comes out on November 3rd. I'm going to start by giving it no context and see what it comes up with. I'll say, "I'm writing a new book that comes out in November. It's called Life in Perspective, and it's about the art and practice of doing an annual life review. Create a comprehensive launch and marketing plan for the book's release." So, the first thing you'll notice is because it has so little context, it's just asking me some very basic vanilla questions. Which channels are most important to focus on? Again, it knows nothing about the book, nothing about my publisher, nothing about my plans. So, I'm going to say yes, traditional publisher. Okay, foundation, dedicated book landing page, annual review starter kit, two ways of arc distribution, pre-launch build-up. It's not bad, but I'd say it's completely generic. It's a book launch and marketing plan that would basically be the same for any author or any book. Now, let me go ahead and add the three layers of context that I mentioned previously. So, the first thing I'm going to do is go into my settings and in the instructions for Claude, which were previously called personal preferences or user preferences, I'm going to paste in what I call my master prompt. What this does is it gives it that persistent context. All the details that it needs to know who I am, where I live, what I do, why, which the AI loads up with each and every interaction that I have with it. So, it has things like my name, my age, where I live, details about my family, some of my interests, uh professional context, my title, my company, what we do, what we sell. Can you imagine how important all of this, especially, is for a project like a book launch? So, let's go ahead and create a new task and say, "Put together a launch and marketing plan for my next book, Life in Perspective on the Art and Practice of Doing Annual Reviews, which comes out in November. I've added context about me and what I do in the custom instructions. So, draw on that in your recommendations." So, notice already, just even in the follow-up questions, how much more specific it is. It knows who's on the team. It's asking, is this your internal team, Julia, Jen, etc. All right, that took about four or five minutes. So, now it has eight sections. It looks like it has the same evaluation of the pre-launch strategy. Notice it's already more detailed. It knows about my YouTube channel since I had that in my master prompt. Your son is due in June, which means July content creation may land during a newborn haze. Think about that for a second. This is like talking to a friend or a close colleague who has a holistic picture of your life, not just this one narrow slice of the task that you're trying to accomplish. Our son being born, which actually was just last week, not uh in June since he was a few weeks early. And now that I think about about it, that is going to push forward some of these uh activities at least a few weeks if not a couple months, so that we can really, you know, spend time with our newborn baby and enjoy that period. Let's now see what happens when we add that second layer. Open up our company projects, and then I'm going to give it the entire folder for Life in Perspective, which includes all of these different subcategories that you see. So, I'll give it that, always allow, and then I'm going to give it one more thing, which is my Obsidian vault, which you can see right here, because I use Obsidian for all of the research and the writing of this book. Most of the like specific raw material that went into the book actually lives in Obsidian, not elsewhere. So, now with those two folders of project layer two context, I'm once again going to ask it, give me a launch and marketing plan for my next book, Life in Perspective, which comes out in November. It's about the art and practice of annual life reviews. Be sure to draw on context in the user preferences about who I am and what I do, and also draw on context in the life and perspective project folder, which I've given you access to, and in my Obsidian vault, which you can also access. All right. So, let's see what it came up with. I [snorts] noticed that it found the specific launch day somewhere in my project files, which is indeed November 3rd. Now, we can go into much more detail about how YouTube will play a part, given that it's 53% of our audience growth, which it found somewhere in there. And it also now has access to the manuscript, which is somewhere again in the project folder. So, it knows little bits of context about my origin story, which it thinks should be integrated into the whole campaign, which is great. Take into account in more detail the timing around the baby. And it can be much more specific about what it doesn't know. Do you see how at this point, with layer two, this is now very, very close to something that I could really start executing on, or at least asking much more focused, targeted follow-up questions. There's only one thing it doesn't know, which is that third layer, which is perishable context. Even with a project that you've taken a lot of very detailed notes on, there is virtually always a little bit extra nuance or subtlety or very most recent updates that live only in your head. It's worth spending a little bit of time and doing like a little brain dump of just the last little layer of context that the AI needs to do its job. So, first I'm going to say, "Our son was born on May 11th, a few weeks early, and we've all been getting plenty of sleep, and it's actually quite chill. While the next few weeks, I should probably take it easy, after that, I'm ready to go full swing into the launch activities." It asked about the podcast, which was an idea that I had some time ago, which I don't think I'm actually going to move forward on. So, I'll say And I'd say that's pretty good. Four points of extra context. And uh I'll add one more, which is I also want to focus on the highest leverage activities, the biggest bang for my buck when it comes to the time I spend, since I have a lot more going on and a bigger family for this book than for the last couple. So, notice that it's congratulating me on the baby. >> [laughter and gasps] >> Um it's updating the plan by tightening the phases, swapping in the workshop bonus, cutting the podcast, and ruthlessly prioritizing. Okay, here we go. So, it's restructured the phases. It's focused on the release date as the primary call to action. It's shortlisted what it thinks are the highest leverage activities. Though, I want to review that. There's a section for booking interviews on podcasts for routing through the team, and noticing that the podcast tour outreach should start ASAP, which are all excellent recommendations. So, by this point, after three layers of context, this has gone from a generic, one-size-fits-all book marketing plan to something that is so dialed in, it's so personalized to the fine-grained details of who I am and the team and the audience I'm selling to and the book itself, this now has become something that we could really move forward on concretely. And by the way, if you want to get started on this yourself with that layer one persistent context, which I call your master prompt, I've created a simplified version of the master prompt process that I teach in the AI Second Brain. There's a name [music] for this practice that's catching on in the AI industry. They're calling it context engineering, [music] but I think that's not quite right. I want to push back on that word engineering. [music] Engineering makes it sound like this is a technical skill, and it's really not. All we're doing here, really, is arranging the typical kinds of information you work with every day: text, [music] images, files, documents, folders, into loosely curated collections, and then pointing the AI at them. This isn't engineering, it's just managing information, managing content. >> [music] >> However, just because this is accessible doesn't mean it's easy. You have to go up a level and start thinking in terms of the broader [music] system that the AI tool is a part of. And what I found in myself, in my team, in my students, in my clients, >> [music] >> is that there's three distinct identity shifts that have to happen for you to do that. The first one is that you have to start thinking in terms of curating context. [music] Your job, how you spend your time, needs to increasingly become about finding, locating, and gathering together >> [music] >> the best context. By that, I mean the most detailed, the most comprehensive, the most specific, [music] nuanced, contrarian, opinionated context. This requires the mindset almost of a a scientist [music] or an explorer. You have to talk to new people, run real experiments, find unique and lesser-known sources of content that aren't already part of the AI's training data. You want quality, the most relevant, [music] the most focused, the most specific, the most up-to-date context that you can find and provide to your AI. [music] The second mindset shift is in how you spend your time. And this is one that kind of sneaks up on people. See, the more thoughtfully you manage your context, [music] the less time that you may spend doing the actual work yourself. You'll increasingly stop doing the execution [music] and start spending more and more of your time just setting up the environment, >> [music] >> the context layers, so that the AI can execute. Most of your professional life, the bottleneck has been your [music] output. Now, the bottleneck moves up a level or two. It becomes about clarity or intention. [music] If you ever had the experience of managing someone, you already know this skill. It's delegation. PCM, personal context management, is delegation, but to a system [music] instead of to a person. And the constraint is exactly the same, the quality of your handoff. That's what determines the quality of the result. The third mindset shift is you have to get clearer about what you really want. This one is kind of the deepest, it's [music] the most profound. See, AI has this effect of homogenizing everything it comes into contact [music] with. It flattens human knowledge. The only way you can stand out [music] is by being more clear. [snorts] So, you really have to think about what are the unique inputs that you can provide, your values, your taste, your perspective, your opinions. >> [music] >> You have to get that implicit judgment and make it explicit. You have to externalize your judgment [music] so the AI can borrow it. What you're really doing in personal context management, I believe, isn't curating data, it's curating yourself. PCM is the practice. >> [music] >> Context Architect is who you become when you embrace it. PCM isn't a new methodology to learn. It's a new way of thinking about what you already do, >> [music] >> the notes you take, the projects that you start, the prompts you write. It's an identity that you grow into one [music] decision, one action at a time. If you want to go deeper, if you want to build a full-fledged PCM [music] system, which is what I call an AI second brain for yourself, that's exactly what we teach in our program, the AI second [music] brain. We'll expand on the three-layer context model that you just learned, walk through a variety of real workflows, >> [music] >> and help you end up with a system, your own second brain, around your own work and your own life. Next time, I'll show you exactly how I architect my own context, layer by layer. >> [music] >> See you next time., The Reason AI Gives You Useless Answers, Tiago Forte, 01kvbbmzrbfp8dcm46fd8p7vqt.