Update! I wrote a follow-up post here: How My AI Product “Second Brain” Evolved.

I’ve been refining my approach to using LLMs for product work, and I figured it’s time to write up how I actually use them day-to-day.

The most valuable thing an AI assistant can do for product work is push back on weak reasoning, spot gaps you missed, and force you to articulate why your idea is good. A peer reviewer who shares your product philosophy, basically. With the right prompts, AI assistants are also good at producing background and framing documents: explainers that synthesize complex topics and summaries of technical concepts.

Here’s how I’ve set it up, what makes it work, and how you might build something similar.

The Philosophy: A Sparring Partner

I believe LLMs are most useful when you give them two things: context and constraints.

Context tells the model who you are, what you’re working on, and what “good” looks like in your world. Constraints keep it from drifting into generic advice or invented frameworks.

Every prompt I use is designed to provide both. They’re opinionated on purpose. I’d rather have an assistant that pushes back on bad ideas than one that says “Great idea!” to everything.

I don’t want AI writing presentations for me. I want a thinking partner that:

• Challenges weak problem statements before I waste time on solutions
• Spots missing success criteria I forgot to define
• Asks “why?” when my reasoning gets hand-wavy
• Points out when I’m jumping to solutions before understanding the problem
• Helps me create background docs and explainers that set context for others

The Building Blocks

Here’s the folder structure I maintain, with a series of Markdown files organized by purpose:

llm-prompts/
├── prompts/           # System prompts for different use cases
│   ├── pm/            # Product management prompts
│   └── technical/     # Technical/engineering prompts
├── context/           # Personal context files (who I am, how I work)
├── reference/         # Syntax guides and reference docs
└── work/              # Saved feedback and refined docs

What makes this work is how you combine them.

Layer 1: System Prompts

These are the instructions that tell the AI how to behave for a specific task. I have different prompts for different jobs:

• General PM sparring: A prompt that knows my product philosophy and pushes back on weak reasoning. I use this for thinking through tradeoffs, preparing for meetings, and sanity-checking my approach.
• Document review: Prompts specifically designed to critique PRDs, OKRs, strategy docs, and other artifacts. These encode what “good” looks like and call out common anti-patterns.
• Idea stress-testing: A prompt that I stole from my friend Stephen, which simulates a debate between an optimist and a skeptic to pressure-test new ideas before I get too attached to them.
• Technical understanding: Prompts that help me understand systems, architectural decisions, and technical concepts well enough to lead effectively (I’m not an engineer, but I need to hold my own in architecture reviews).

Each one carries a specific point of view about what good work looks like.

Layer 2: Personal Context

I maintain files that describe:

• Who I am: My role, my experience, my communication style
• How I work: My product philosophy, my management approach, my values
• What I’m working on: Current projects, team context, company priorities

When I start a conversation, I can pull in the relevant context files alongside my prompt. The model then has the background it needs to give me advice that fits my situation, instead of generic best practices from a blog post.

Layer 3: Reference Materials

Sometimes you need the model to follow specific formats or conventions. I keep reference files for things like wiki markup syntax, documentation templates, or internal style guides. These keep the output usable without a round of reformatting.

How I Actually Use This

I use Windsurf as my daily driver, and it has a feature that makes this whole system work: the @ mention. In the chat panel, I can reference any file by typing @ followed by the path. Windsurf then includes that file’s contents as context for the conversation.

This means I can compose my “assistant” on the fly by combining:

1. A system prompt for the task at hand
2. Relevant personal context files
3. The document or code I’m working on

Example: Document Review

When I need feedback on a PRD before sharing it with stakeholders, I’ll start a conversation and reference my PRD review prompt plus my product philosophy context. Then I paste in the PRD and ask for critique.

The model comes back with feedback measured against my own standards. It’ll call out if my problem statement is vague, if my success metrics aren’t measurable, or if I’m jumping to solutions before properly framing the problem—the kind of pushback I’d want from a peer reviewer.

Example: Brainstorming Partner

For early-stage thinking, I use a more conversational prompt that knows how I like to explore ideas. I’ll describe what I’m thinking about and ask it to poke holes, suggest angles I haven’t considered, or help me articulate why something feels off.

This helps most before big meetings. I can rehearse my reasoning and get challenged on the weak spots before I’m in front of stakeholders.

Example: Technical Understanding

I’m not an engineer, but I work with technical teams. When I need to understand how a system works well enough to ask good questions or spot when something doesn’t add up, I use prompts designed for technical explanation.

The key is that these prompts know to explain things without condescension but also without assuming I know the jargon. They cite specific files and line numbers when relevant, and they explain the “why” behind design decisions.

Connecting to Real Data

MCP (Model Context Protocol) servers connect the AI to external data sources: internal wikis, documentation sites, code repositories, APIs. So it can answer from real information instead of guessing from training data.

In my prompts, I tell the model which MCP servers are available and when to use them. For example, my technical prompts instruct the model to:

• Search official documentation first to ground answers in verified information
• Check internal wikis for known issues, edge cases, and workarounds
• Look at code repositories when documentation is incomplete
• Always cite sources with links so I can verify

Now the AI answers like someone with access to your company’s actual knowledge base, citing real docs and real code instead of best-practice boilerplate.

Keeping a Record

Save the conversation output somewhere useful.

I have a work/ folder organized by topic where I save feedback and refined thinking. When the model gives me good critique on a PRD, I’ll ask it to write a summary of the key issues to a Markdown file I can reference later. This keeps the insights from getting lost in chat history.

What I’ve Learned

1. Context files are worth the investment. I have files that describe who I am, how I work, and what I value. Updating these takes time, but it pays off in every conversation.
2. Pushback is the point. These prompts are designed to challenge bad thinking. If the model is pushing back on your approach, take it seriously: it might be right.
3. Iterate on the prompts. I update these regularly based on what works and what doesn’t. If a prompt isn’t helping, change it.
4. Less context is often more. Including too much context can dilute the signal. Start with the minimum you need, add more if the model seems confused.

The thinking is still mine

None of this does the thinking for me. It encodes my preferences and philosophies into something an LLM can use as a baseline for pushing back. I still write my own PRDs, OKRs, and strategy docs, because those represent my actual thinking. But I let AI help me create background documents, explainers, and context-setting materials. And I have a sparring partner that catches the gaps I miss and asks the uncomfortable questions before stakeholders do.

If you build something similar, I’d love to hear how it goes.

Not sure how many people would be interested in this, but it was fun to make so I thought I’d share. This is a Discord bot that provides real-time stock and cryptocurrency information, 30-day price trends, and AI-powered news summaries through slash commands. When you add the bot to Discord you can use the /stock and /crypto commands to get information like this:

Want to add it to your Discord server? Head over here!

(Mild spoilers ahead for The Mountain in the Sea by Ray Nayler)

I recently finished the novel The Mountain in the Sea by Ray Nayler (see Andrew Liptak’s excellent review here). On the surface it’s about discovering an octopus colony that evolved into a self-aware, intelligent community—and trying to communicate with them. But as with all good novels it’s actually about other things. It’s about loneliness, understanding each other, conservation—and yes, our relationship with AI.

First, to get the AI thing out of the way… I don’t want this blog to sound like I am anti-AI. I use AI every day both at the chat / thinking partner level and the prototyping / vibe coding level. I am a fan of using AI for the things that it’s good at. I just worry that we are not teaching people outside of the tech bubble what those things are. And that’s why we are seeing so many tragic stories right now about chat agents “guiding” people to horrific actions (see, for example, Let’s Talk About ChatGPT-Induced Spiritual Psychosis and ‘I Feel Like I’m Going Crazy’: ChatGPT Fuels Delusional Spirals).

With that as background, the book does a good job of highlighting some of the dangers of using AI for things it’s not good at. First, this is a good point about how with every new technology we have to think about what can go wrong, not just what can go right:

When you invent the ship, you also invent the shipwreck; when you invent the plane you also invent the plane crash; and when you invent electricity, you invent electrocution. Every technology carries its own negativity, which is invented at the same time as technical progress.[1]

Following from that, this quote about the main character “killing” their AI companion stood out to me…

That’s how this works. That’s how addictive this is—this need to feel like there is always someone there, unconditionally. Someone to talk to. Someone who understands. To not have to do the work myself to make myself understood. Instead, I just kept on with this self-deception, pretending I had someone when I did not. I know the doctors who prescribed you to me meant well. They thought they were helping me through a dark time. But in the end, you aren’t anything but a prosthesis. You can’t replace real support.

The other major theme in the book centers around our connectedness with each other and the world, how language can get in the way of connection, and how lonely we’ve become as a society[2]. I love this call to empathy as a way to get ourselves out of that dilemma (emphasis mine):

Are we trapped, then, in the world our language makes for us, unable to see beyond the boundaries of it? I say we are not. Anyone who has watched their dog dance its happiness in the sand and felt that joy themselves—anyone who has looked into a neighboring car and seen a driver there lost in thought, and smiled and seen the image of themselves in that person—knows the way out of the maze: Empathy. Identity with perspectives outside our own. The liberating, sympathetic vibrations of fellow-feeling. Only those incapable of empathy are truly caged.

A book about discovering intelligent life in an octopus species with its own language and culture might seem like a weird premise. But it works really well here. It gets pretty heavy-handed towards the end, but it still made me think a lot about the “loneliness epidemic”, our relationship with AI, and the continuing role of empathy in making sure we stay connected with each other. Recommended!

---

1. This line of thinking reminds me a lot of Kevin Kelly’s 2010 (!) book What Technology Wants in which he makes a similar point that technology is never “neutral”. That’s ok, but we have to be prepared for it.  ↩

2. I don’t think that’s a controversial statement any more. See articles like The Anti-Social Century  ↩