The /wayfinder Skill: Navigating the âFog of Warâ of Planning
Weâre currently developing a new series about skills, with the aim of giving you a regular supply of new skills to use in your projects. Weâre kicking things off with an interview â and a super-useful skill â featuring Matt Pocock, whose âAI Skills for Real Engineersâ project has over 220,000 stars on GitHub. He also talks about these skills to 347,000 subscribers on his YouTube channel.
Pocock recently released a new skill called /wayfinder. Its purpose is to help you and your agent figure out a project where the end state isnât entirely clear. Or as Pocock put it in our interview, /wayfinder helps you navigate âthe fog of war,â where you have a project but âyou canât quite decide everything right at the start.â
The following interview has been slightly condensed for readability, so you can read it, absorb Mattâs insights, and then test out /wayfinder for yourself!
Latent Space: What were the goals of wayfinder?
Pocock: What I noticed is I was doing a lot of work with AFK agents [Away From Keyboard] and trying to schedule in a ton of work so that my agents could run virtually overnight. I would just plan a bunch of stuff, and then I would create a spec and then turn that spec into tickets. And I had a really well-developed set of skills for how to turn work into scheduled stuff that agents could just crack on.
But [...] I was finding the planning stage really onerous, because I would have to be constantly thinking about my session management. Like, how many tokens am I into my context window? How deep am I going here?
I didnât want to feel constrained in the planning stage anymore. I wanted an orchestrator layer that would basically say, okay, whatever you want to plan, Iâm going to handle the planning sessions for you. Iâm going to split this out into multiple different threads, do prototyping, do research and pull it all back together, so that you donât feel constrained in the planning anymore.
And then your specs can be even more detailed, and you can just whack off an AFK agent to go and do tons more work.
Latent Space: What was the design process of coming up with this skill?
Pocock: I had this kernel of an idea of, what if I didnât have to manage the handoffs? What would that look like? And then, what would it look like to have some kind of centralized document to have all of those pieces together?
Whenever youâre thinking about context management â because thatâs really what a skill is, youâre managing the context of the agent youâre working in â you need to think about the information flow. So what I wanted to think about is, what if a grilling session could manage other grilling sessions? What would that look like?
Well, the first step to that is, what does the grilling session thatâs being managed need? What does the child need in that situation? So the child probably needs to understand a vague overview of what else is happening, and they need their specific task.
So there, youâve got two documents. Youâve got a map â which is all of the rest of the stuff, all the decisions that have already been made. And then youâve got the specific ticket that goes into the actual session. And what you notice there is that those words are very precise.
Youâve got the map, and youâve got the ticket, and youâve got the session. And once youâve got the kernel of an idea, you then need to come up with the words for that idea. Because once youâve figured out the words, then those entities can be really clearly mapped out by the agent.
Because if you just call everything a ticket, or if you just refer to it in different ways in different places, then itâs going to be really confused and youâre going to get strange behavior. Whereas if you use these very specific, what I call leading words, to lead the agent to understand exactly what each part is, and youâve understood what the information flow is, then youâve got your skill.
Latent Space: What kind of use cases do you think wayfinder would be useful for?
Pocock: Well, Iâve been using it for all sorts of stuff. Iâve been using it to actually plan courses as well. In wayfinder, there are different types of tickets.
So youâve got grilling tickets, which are just a grilling session. Then youâve got prototype tickets for creating prototypes, research tickets for creating [and doing] research, and then task tickets â which are really broadâŚbasically, just anything the human needs to do that the agent canât do. And so once you think about that, you realize, OK, I can apply that to anything.
One really key idea in wayfinder is the âfog of warâ. So this is the concept of, you canât quite decide everything right at the start.
You can make certain decisions, and those certain decisions sort of lead you there and push further out into the fog of war â kind of like Warcraft III style, exploring the map. And once I had the idea of âfog of warâ and âmapâ, I realized those two terms actually work really nicely together, and it really leads the agent into the right idea. So Iâve been using it for engineering, for non-engineering stuff, for course planning, all sorts.
Latent Space: This concept of the fog of war â itâs weird to consider what you donât know that you donât know. Maybe LLMs are good at capturing that.
Pocock: I feel like with the grilling stuff that Iâm still working on, that captures an idea that you donât know stuff, but maybe the agent can contribute something and illuminate a part of the room that you donât quite understand yet.
And wayfinder is just sort of an extra layer on top of that.
Latent Space: Yeah, and thereâs all these artifacts. How much time do you spend teaching the model all this terminology?
Pocock: For the last few months, Iâve been pretty obsessed with terminology â and finding the right terms for certain things. Iâve put together, I havenât actually put it out yet, but itâs an AI coding dictionary â of basically all the terms in AI coding. Itâs in this beautiful graph that you can explore and understand exactly what an agent is, exactly what a harness is, exactly what a model is, blah blah blah.
Iâve redone all my courses to use that dictionary and make it really solid. And then all of my skills use a consistent dictionary as well. So theyâre all working off the [same] assumptions, the same leading words.
I realized that I needed a ubiquitous language between me and the agent. Between me and the agent, there is a communication barrier. And thatâs what Iâm trying to do with my skills all the time, is try to find the right words.
And agents are really good at showing you the opportunities for different wording â really good at domain modeling, actually.
Latent Space: When do we directly use the grill-me skill, versus wayfinder?
Pocock: Use âgrill meâ in cases where you feel like you can plan the whole thing in a single session, and you need to align before you go. So most small features will fit into this. Most stuff where you can see the path ahead of you, but you just want to make sure the agent is on board, âgrill meâ will work with that.
For stuff where you donât know the path ahead, for stuff where you can feel the fog of war in front of you, use wayfinder. Youâre gonna find your way with wayfinder. So thatâs how it works.
How it works
Once you click Generate, Ollama reads this article and crafts 5 comprehension questions. Your answers are graded against the article content â general knowledge won't be enough. Score 70+ to count toward your certificate.
Questions are cached â you'll always get the same 5 for this article.