Speaker A
Ever since Karpathy talked about having a personal knowledge base, people who are into AI started creating personal wikis for themselves with all the information that their LLM needs to help them make good decisions.
Discover how Grain automates team knowledge bases by organizing meeting transcripts and data into a company wiki using AI.
Key Takeaways
- Automating team knowledge bases enhances collective intelligence and decision-making.
- Synthesizing multiple data sources into a wiki saves time and improves context quality.
- AI-powered wikis help uncover communication gaps and strategic blind spots.
- Organic growth of Grain’s MCP shows strong user demand despite minimal marketing.
- Integrations like Claude in VS Code make accessing and querying the wiki seamless.
Summary
- Karpathy inspired personal knowledge bases for AI users, but Grain extends this to teams by automating a company wiki.
- Grain records and captures all non-sensitive team meetings, making them accessible to the entire team for shared context.
- AI (Claude) synthesizes meeting transcripts, customer feedback, web clippings, and documents into a structured wiki.
- The wiki provides broader context than raw transcripts, reducing token usage and speeding up information retrieval.
- The system compiles recursive knowledge about entities like people, projects, and companies for better decision-making.
- Grain's MCP (multi-channel platform) usage grew 15x organically, highlighting the value of well-organized knowledge.
- The wiki helps identify communication gaps in strategy dissemination within the team, supported by meeting evidence.
- Users can interact with the wiki through chat interfaces integrated with tools like VS Code and Claude's plugin.
- The wiki structure is managed via index files that guide the AI on what context to prioritize and use.
- The video includes practical advice and prompts for viewers to build their own automated company wikis.
Full Transcript — Download SRT & Markdown
Speaker A
Well, what happens if you have a team? What if you have multiple people who you want to inform, and you want to have access to the data that they need and that you want to get data from what
Speaker A
they're doing so that you can make better decisions? Well, the CEO of grain.com is coming on. He's got millions in revenue. He's got a big team. He's got tens of thousands of users. He's taking everything, organizing it automagically into a wiki, and he's
Speaker A
going to show you how useful that is and how you can set that up for your team.
Speaker A
Let's get started. [music] Presented by Zapier, the AI automation company. Everyone's talking about Karpathy saying that you need a personal wiki and that's what makes your LLM a lot smarter and your AI engagement a lot better. You all
Speaker A
at Grain have got something bigger. What's your version of it? Taking the main idea and basically making it a company wiki with all the context of the company. So, essentially every conversation at Grain we record all of our meetings. We capture all of
Speaker A
our meetings, team meetings, except for the sensitive ones, and give access to the whole team so everyone can have that collective context and intelligence.
Speaker A
And then you have Claude somehow take it and structure it in a wiki so that everything is organized on your wiki.
Speaker A
Why? Why not just say to Claude, "When I have a question, go to Grain, look at my call transcripts, my team's call transcripts, and look all over and bring me my answer." Why do you need the wiki?
Speaker A
So, I do also that. It oftentimes depends on the type of task being done.
Speaker A
The wiki gives a lot bigger context. Not only are we pulling all of our calls, but I'm also pulling in Intercom conversations for context. I'm pulling in things I've clipped from the web, documents that have important
Speaker A
context, things we've written. And so it’s broader. And, you know, if every single time you're pulling contacts from an MCP, it blows through tokens pretty quickly. This has everything already synthesized. So, when it pulls the meetings, that it does save
Speaker A
the raw transcripts, but it compiles them into a wiki with information about companies, people, projects.
Speaker A
I see. So, you get all the transcripts on your computer, and at the same time you have summaries of it, so you can find what you need fast.
Speaker A
Okay. Let's look at what it can do. It compounds into recursive knowledge about different entities, topics, people, companies.
Speaker A
All right. So, you asked it this question earlier today. It's, "What's my strongest proof point for Grain's agent-first strategy?" What did it come back to you with? And does this make sense?
Speaker A
Yeah, it makes a ton of sense. So, we built a really early MCP back when MCPs were maybe not as well developed and supported by the ecosystem. We shipped it. We got some
Speaker A
additional early interest, but there were still just a lot of gaps. We're a startup. We have limited bandwidth, and so our attention went somewhere else.
Speaker A
And then, out of nowhere, you know, starting kind of early this year with some of the improvements, we just started seeing our MCP usage climb astronomically. So, as it says, MCP weekly users grew 15x with almost no
Speaker A
investment. So, that was just kind of what we'd already built. We saw this signal and like, we have to—this is a bright, you know, bright red center of the sun. We need to put everything behind it. So, that's
Speaker A
basically been the company focus for the last several months: improving our MCP capabilities, improving the documentation, improving the examples, doing customer stories of how people are using it, just to, you know, inspire customers on how they can get value from
Speaker A
it. And even with no investment, 15 times more use came out of it. The documentation was not very good, no marketing push, no dedicated team, and still it just absolutely popped. And as we scroll down, we'll see that there are
Speaker A
even people who are switching from Codex, from ChatGPT to Claude just so they could get this access. So, this is the kind of thing that you would say, "All right, I'm trying to make a decision here. I'm trying to understand
Speaker A
if this is the right move. I need a place to ask, and I don't want some generic LLM." That's one example. Let's see another example of how you use it.
Speaker A
And then we'll see how to build it. Yeah, so I asked this one this morning.
Speaker A
Based on my own meeting transcripts, where's the gap between how I communicate strategy and how my team understands it? You know, a strategy is only as good as it is used to focus your team and help everyone on the
Speaker A
team make coordinated decisions. Uh-huh. So, it came up with several gaps that I think as I'm reading I'm like, "Wow, this is really good." So, the first is that the strategic conversations happen in a small circle, and then I don't do
Speaker A
as good a job as, you know, expanding them to the rest of the team. Uh, it gives some evidence from different meetings.
Speaker A
Wow. Let me read it. Evidence: In May 15th capture strategy session, Jake says outright, "I haven't seen any of that or viewed it." Mike had stayed up very late building the design and shared it only to Jeff. When asked why it didn't, why it
Speaker A
hadn't gone wider, quote, "I just ran out of bandwidth." So, that's one issue. Okay. So, fair analysis for you. Gap number two, written objectives are thinner than the conversations that shape them. Um, here, let me read it. Q2
Speaker A
board follow-up, Mike reads the objective document and immediately says he doesn't know if they're aligned even though he was part of the conversation that produced the thinking. So, now when you see this, what do you do based
Speaker A
on this? So, the thing is, right, it's using the context it has, which is the conversations, which is what you want it to do.
Speaker A
Mhm. And so, some of the times it's going to be like, "That is 100% true, and it's helping me see a blind spot." Other times it might say, "You know, this is partially true, but it's missing some context." And then I ask, "How do I get
Speaker A
better context into the wiki?" So, it can make better judgments. Okay. Let's see how you put this company wiki together and you specifically went in one of these chats and said to Opus, he said, "Analyze this for me. How did
Speaker A
we put this together and how can someone else do it?"
Speaker A
Yeah, so I basically just said, "You know, I want to teach people how to do this. Look through what I built and explain what's represented here, how is
Speaker A
it structured, how does it decide what context to use, 'cause it's not going through every single context every time?" And this gets to the last question I'll talk about in a second.
Speaker A
What advice would you give someone to build their own? And then like what's a strong prompt you could use tonight? So, that's the kind of thing to people in the description.
Speaker A
Absolutely. So, it says, "What sources?" Like I said, it's meeting transcripts, customer feedback, web clippings, and other, other inbox, which is manual drops of files and other things that I want to manually put in
Speaker A
there to give it context. Okay. And just so we're clear on the app that we're looking at, this is VS Code. On the left, you see the files that are on your computer structured the way that Claude has structured it for
Speaker A
you. On the right is a chat window, the same kind of thing that we see with any kind of chat.
Speaker A
And that's it's using the docs as reference. Yeah, I'm just using the Claude code plugin in VS Code here. That's what I use. I love it.
Speaker A
Yep. Then you can see how it's structured, kind of explains how it's structured, and then how it decides what to use is it reads wiki.index. It tells, it kind of tells, gives instructions on how, where to look for files,
Speaker A
instructions so that they'll can kind of decide what to weigh and what to pull. You know, we had a conversation earlier about maybe it's maybe in this case my knowledge graph is biasing a bit too much to older
Speaker A
context, and so I want to add a little bit more recently to it because we're constantly learning and changing. So, these are things you want to tweak.
Speaker A
Respect the append-only structure. I like that. Yep. Then advice for someone building their own, these are I don't know if I endorse these. These are LLM this is LLM advice but start with one source. Raw files are sacred, append never overwrite. You you
Speaker A
just mentioned that. All logical. I actually think if we were to start with one source and it's not because you're the the head of Grain the the transcription service but I would start with that. There's just so much value in our meetings and
Speaker A
we don't go back in and mine it unless we're hunting for the one thing somebody said. Meanwhile, the way our company really runs is in there. The way our companies Yeah.
Speaker A
the the things we're really working on are there. alignment, decisions, these all happen in meetings. The context is just so rich.
Speaker A
So, I would start with that and the API for your company in many ways.
Speaker A
Yep, exactly. Say did take everything in my meetings for the last month and we're all using meeting notes. Take it in there and if we've got Grain we've got MCP access, go take it and create a wiki for me using
Speaker A
this structure or if you want you could adjust the structure. I totally believe in this one first and then build beyond it. Raw files are sacred, never edit them. I really like that actually. I hate when they edit because there's no
Speaker A
version control. Yeah, 100% exactly. That's why the way this structure is you have raw is very different than the wiki.
Speaker A
They're in separate folders. So, raw is is what? Raw just stores everything as it comes in and the wiki organizes it and makes sense of it.
Speaker A
Correct, that's right. Exactly. It compiles raw compiles into the wiki. The wiki actually synthesizes, pulls out information into companies, people, topics.
Speaker A
How do you create the automation that does that? So, uh this is what I'm still trying to work on. I think there's something we're all figuring out is like what's real here versus what is something that's more theoretical.
Speaker A
Uh Mhm. These are huge contexts, right? And so trying to figure out how to use those efficiently. So right now I just have a skill that's uh uh raw compile or compile raw.
Speaker A
Okay. So I just run that. I I have not done it. The I use Grain's API webhooks uh with a local ngrok uh server to basically pull every time there's a new meeting. So I've I've automated those coming in. Other things
Speaker A
I'm I'm currently but I'm currently still uh compiling raw as a as a skill.
Speaker A
Um might change that to be, you know, maybe a cron job hosted on Vercel or something like that, but for now I'm just kind of compiling raw when I when I trigger this with the slash command.
Speaker A
I see. So I did an interview with the founder who does this for a personal wiki. He doesn't use a company wiki, though it's basically only company information, but it's only his information, not whatever everyone else is doing. And what he did was he used
Speaker A
Coda Work as a way of triggering this automation since it's happening on his computer anyway.
Speaker A
Oh nice. Yeah. So Coda Work does it and then everything is uh on his computer and then he can use it from there.
Speaker A
Okay. Um we're going to give this to everyone. Is there anything else we should know about this?
Speaker A
see there's a starter prompt here. That I think is pretty good. Okay. And of course we'll give it to them and since I mentioned that wiki that you can use if you're looking to do this in single player mode, I have a
Speaker A
link for you right here where you can watch a video to see how to create this for single player mode.
Speaker A
Yeah, I think one uh one caveat there is I'm still personally using this. I have We know we've actually had conversations about how do we create created true multiplayer version of this like it's effectively like a GitHub repo. That's our next
Speaker A
iteration of that. So right now it's multiplayer in the sense that it's pulling context from you know, everyone's conversations, not just mine. Uh everyone's that I have access to.
Speaker A
But I think that's the next step to make it truly multiplayer is like putting it in a get in a in a in a GitHub repo, everyone writes to it. I think there's questions about how do you manage context there? And and and so,
Speaker A
that we're still kind of figuring that out, but I think that'll be the next iteration of this.
Speaker A
And then, the other thing that I think is fun to show here is uh the way I've set this up is I have I have it um writing to Obsidian. So, this so Obsid- not writing to Obsidian, but
Speaker A
Obsidian is synced with this uh this vault. directory And so, you can see like the knowledge graph build as you as the as the um Because this is Obsidian just looking at the same markdown files that we just
Speaker A
looked at a moment ago in VS Code, but now in an organized structured way.
Speaker A
Correct. Yeah, and you can see it sees all you know, all the context from the different entities.
Speaker A
By the way, Zapier, my sponsor, they've got a new product. I can't talk about it yet that will do what you're talking about. Take it from single player mode to multi-player mode. I can't wait to talk about this.
Speaker A
Amazing. That's going to be amazing. Okay. All right. Hey, my agent says that if you watch this far, you're going to want to subscribe. And Google thinks that if you watch this far, you'll want to watch that video.
Topics:Grainpersonal knowledge basecompany wikiAI automationmeeting transcriptsClaude AIMCPteam collaborationknowledge managementVS Code plugin
