JFDI System - my AI Executive Assistant + full life command center

Basically every project management tool or knowledge management tool I've ever used had the same problem for me, which has got nothing to do with the features that it has, but what it expects from me, which is that I am the worst at going in and keeping them.

Current and up to date and clean and gardened and organized.

I know there's folks who love to spend time and is relaxing for them to go in and, you know, curate their notion or their obsidian.

And there are people who.

Will get a ton of satisfaction from checking the done box on their tasks and things like that.

For me, it's so much more functional.

and therefore if it doesn't get done, I don't get the benefits of it.

And so, you know, I've been playing with stuff like Claude Code for, for much of the year really just to help me build internal tools and solve problems. Around Indy Hall and it's been amazing.

We've, I would say with confidence there would be parts of this year that I don't know that we would've been able to solve the problems that we solved as quickly as we did or as effectively as we did without this one tool, Claude Code, which is kind of wild.

But I've been working on something else that I'm excited to show you.

And Claude Code lives inside of it.

So Claude Code will make an appearance again in just a second.

But it's gonna look pretty different pretty quickly.

And that is, I want to introduce you to.

The JFDI system this is a piece of custom software that I've been working on.

I'd Say all the way back to October when I started building the underlying systems in Claude Code.

And then.

What is now December 13th, so less than three weeks of actual development building the tool that you see on my screen that lives on top of and around, and also deeply interconnected with Claude Code, which I'll get to show you in just a second.

So this is a very new tool, but has already had a materially positive impact on my life, my productivity, my happiness.

I'd say most importantly, like my executive function where, you know, open loops really are a challenge for me where I struggle to delegate or just get things out of my head because if I'm waiting on something to come back, my brain keeps coming back to it.

And it's because I don't have a system that I trust to make sure that if the ball gets dropped somewhere else, that it doesn't make my life difficult.

And that's what I set out to build with the JFDI system.

And for those of you who aren't familiar, the JFDI thing, that's me, that's mine.

I, I got the tattoo first.

And so like, the, the, this is, could not be more deeply personal.

But I'm excited to share it with, with anyone who, who might find this exciting and inspirational for how you might be able to solve your, your problems as well.

So let me take you for a spin through what this tool is and how it works and how Claude code comes into the mix besides actually using Claude code to build the tool.

And that starts with what you see on my screen here.

I get this dashboard autogenerated for me every weekday Monday through Friday.

I might build a custom weekend dashboard now that it's.

So integrated into my day to day.

But for now it's just, this is like a really workday oriented thing.

So, you know, I get my overview where it's taking a look at all of my systems, my calendar, my inbox, my to-dos, my tasks, my projects relationships meetings things that I'm working on, like this system is able to look at all of that stuff and using a Claude Code workflow, a slash command.

And a little army of agents that I built.

It goes, and at eight 30 every morning generates this report for me.

And initially this was just a markdown file and a little summary that I would get in Discord.

Now this gets automatically saved to to the system as, as all this.

Data that's needed to produce this report.

The report's even, you know, interactive now where I can check things off.

This has given me my priorities, my recommendations for what I do in, in what order.

Remember what I said about the executive function part, like this is helping me make those decisions.

I can ignore these all I want, but it's helping me do what I said I wanted to do without having to figure that out.

First thing every morning, it just kinda helps bring me back to where I need to be.

It looks at my calendar, what's coming up, what blocks of time I have to slot in work where I'm not in meetings or, other commitments and things like that, and a little bit of a glimpse ahead.

A snapshot of what my email looks like.

Not all my email, my email that needs work.

And I have it set up to pull anything that is time sensitive and action necessary.

First thing in the morning.

I keep a pretty tidy inbox.

This tool helps to do a lot of that under the hood for me now to my custom rules.

And it works in tandem with Gmails.

Filters to make sure that stuff that isn't work doesn't end up in my inbox at all.

But it does end up in my life when I want it and need it.

My whole relationship system, we're gonna come back to that in, in just a minute.

But this is like my dream CRM built to the way that I want to actually show up in the relationships that I care about, both personal, personal and professional.

My reminder system is a pretty straightforward reminder system just with some ergonomics to the way I like to be reminded.

And the way that.

I typically think about the difference between a reminder and a task that's a part of a project.

And then this goal alignment is probably one of my favorite parts of the system.

I spent some time early on having it interview me about what my goals were for the, the current period of time.

I think we did like a, a 60 to 90 day window.

And it helped me determine sort of a proportional ratio.

'cause you can't have everything be your top priority.

And so we decided all right, through the end of the year.

40% of my effort going into growing Indy hall, 35% into building partnerships and 25% into strengthening existing relationships.

And every day it looks at all of my systems that it can see and it can't see everything.

So this is not a hundred percent holistic, but it's like 85% holistic.

And it says how you doing related to those goals?

And what's cool is often I can come in here and see a bunch of overdue reminders that look scary, but.

This tells me, Hey, those reminders, you can do those tomorrow to stay on track.

This is what you really need to be doing.

And it again, from that like the dream of an assistant who you wake up in the morning and your day is prepared for you.

That's what this is.

And it's been a game changer for me.

And that happens fully automatically thanks to Claude Code slash command and a bunch of agents.

And then everything gets saved to a database and printed out every day for me automatically.

I also get a Discord message still with a, a summary of this so I can glance at that quickly.

But then it links me directly to here.

The next part of the system related to that is reminders.

I didn't set out to build a reminders tool, but as I started building these systems connected to each other, I realized there was, I didn't already, have a reminders tool, I had to go elsewhere to get a reminders tool.

And so starting to fold some of these things in was not because I thought I could necessarily do it better.

I think what I have here is a nice version of a pretty standard thing, like again, I can add some ergonomics.

It's more that it is directly integrated into wherever I already am.

And so because this app is open for me.

Often, all day, every day.

My reminders are always one click away.

I don't have to open a separate tool.

But also I get the opportunity to most deeply integrate this into the rest of the system however I want.

So my version, again, pretty straightforward.

I've got my Anytime reminders, reminders that I know I need to do, but they don't have a date on them.

And then I've got by, you know, overdue today.

Next three days, so on and so forth.

Real easy to, you know, just add a new one based on, you know, how far out.

I could add a reminder for an hour from now or next Monday, or a custom time, and it's very, very easy.

You can't see it because I'm, I'm screen sharing this on my computer.

This is all like mobile first.

So on mobile, like these panels, if you swipe 'em to the right, it auto completes them.

You swipe 'em to the left, it opens up that snooze panel.

By snooze panel, I mean, I mean this is actually like the detail panel where you can either complete the thing or you can snooze it to another day.

And this snooze workflow is one that is deep in my life.

It helps me.

Resurface things that need doing but aren't, don't have a particular due date, but the sort of urgency is up to me in the moment.

That's how I use snooze quite a bit.

So that's in here.

Again, did not sit out to build project management software, but once again, I was not in love with any project management tool.

Every tool I've ever used I felt like failed me because it expected me to do things that software should be able to do.

And it never is like worked for the way that I work.

And I work in a kind of weird way.

To be fair, I know I'm not like the weirdest in the world, but you know, I've got multiple businesses.

That overlap in some interesting and unusual ways.

There's some recurring collaborators in different systems, and so like sometimes I've got project management tools for two different businesses and nevermind the, the money waste, but like they don't talk to each other and that's very confusing and and kind of a challenge.

And then also, none of these tools really help me figure out what to do next.

They tell me like, they're great at making me feel overwhelmed, but they're never great at.

Making me feel like I know what I should be doing next.

So that's what I set out to build here.

And, and I'm gonna go through this in in depth in just a minute.

We'll come back to the project system.

The calendar system is very bespoke for Indy Hall.

I'm not gonna spend a lot of time on it, but what I can tell you is that this centralizes events related to, you know, the events that we host, that our community partners host, as well as other things happening at the Indy Hall Clubhouse, there's been a struggle because we've.

All of these calendars in different systems 'cause they need to do different things.

Keeping them in sync was a, a nightmare of Zapier integrations.

That worked some of the time, which meant I was always thinking about is it working, is it not?

What did I forget?

All those kinds of things.

This solves all of those problems, not the least of which is, you know, one where in order for an event in our system to be visible to the public, it needs to be on our Luma account, which is the, the event management tool that we use.

This keeps track of that.

And lets me see if basically if an event is green, we're good to go, right?

And the system is gonna bubble up information and next actions for me as we go.

You'll see more of that in a second.

But if I look into January, you can see I've got a bunch of events that we know are coming up or committed, but are not on the public calendar yet.

This is unambiguous.

December.

We're good.

I got work to do for January, which is normal, but like this is.

Such a mental balm to know exactly what's going on here.

And then in any of any of these events, you know, I can click in here and get my details.

And you know, some of these are built out a little bit more so like, for instance.

You know, this one tells me Neil is my collaborator.

And it even keeps track of the difference between the actual event time and what is time for prep and breakdown and links to projects, which we'll come back to in just a second.

The relationship manager part of the tool may be a personal favorite.

what I really wanted, I've always wanted a CRM that was not about sales, but about actual relationship building and more focus on depth than closing.

Right?

And so this doesn't look anything like that.

This is really the, the output of the system because the system.

You should be invisible to, to a large degree.

The system of a relationship manager is keeping track of the people who are or might be the relationships in your life and the points of contact you have with them so that you know, if, if there's a bunch of activity and, and your working together, your communicating and then things fall off, that is a normal thing.

If you want it to be.

But you know, I, I don't wanna lose track of a, a relationship just because we're not actively working together.

And so this thing that can sort of bubble things up, but be smart about who it's bubbling up in different ways.

'cause not every relationship is the same.

There's the people that I work very closely with, the people that I work more peripherally.

The people that I work with more casually the people that I, it's not working with.

But those are my actual friends, my partner, and, and there's, they're all intermixed.

So A CRM never made sense and a personal CRM never made sense.

These are just people in my life and this lets me view and work with all of that.

And so I, while there's not a lot to show you here other than a pretty nice file browsing view and what's unique is it lets me sort by last contact which is helpful in, in a number of ways.

But I can also sort by priority and alpha and searchable.

The cool thing about the search here and just for, you know, data's perspective, I'm not gonna search here 'cause I don't know exactly what it's gonna turn up.

'cause it's not just searching names.

I can search any keyword, anything across all the relationships and it'll filter based on those.

But the real key is that this is tied into everything else.

And you'll start to see how that really fits together.

Remember, the dashboard lets me view sort of the rising and falling of relationships and things that might need a little more nurturing.

Versus opportunity as well as opportunities and connections that it can help surface and things like that.

This does all of that and it does it automatically.

And the relationships database here is really largely the heart of what's happening in the JFDI system.

The meeting system.

Is similar view here.

Although the data that's in it is very different.

Once again, like relationships is basically just a pile of markdown files.

The difference is, is I've got a system now where, you know, I've never been much of a note taker except for when it matters.

And the trouble is, is I don't always.

Know that it matters until after the fact.

And so I'm, I wanted a pro, a more proactive approach to note taking.

And meetings are high value for me.

And so what the system currently does, again, you are not seeing the system, you're seeing the results of the system at work.

The system is invisible and therefore, kind of feels like magic.

But what this does is it looks to my, my personal Google Calendar looks for upcoming events.

It looks at the relationships of the people that I'm in that meeting with makes decisions about what kind of notes and how deep of a note taking I might want to do.

Creates a prep sheet and tells me who's in the meeting, what we're talking about, when was the last time we met, what have we talked about, what preexisting relationships between those people might exist.

Helps me, go in with a snapshot where I can show up fully present, knowing what we're there to talk about and not like having to draw purely on memory every time I sit down, which is getting harder and harder, not only as I'm getting older, that's absolutely a thing, but also just like my network is bigger and, and often I'm, I, I know I can, you know, picture a face, but forget

a name or something along those lines, and this fills in all those gaps for me.

But the most more important part is that after the meeting I press a button, and more specifically, it presents a button that I can choose to press and say, Hey, do you have any notes on that meeting?

I can either go into voice mode and brain dump what I remember, or if I got permission to record that meeting on Zoom or with a voice memo I can just drop that transcript in and it automatically processes the meeting that we had against the plan for the meeting that I prepped with.

And so the file comes out with, at the end the three most important takeaways, decisions that we made, outputs that were created, commitments that were made, so on and so forth.

And in my case, it automatically generates.

Tasks and reminders in the right places for things that I committed to.

It creates reminders for me to follow up on what other people committed to.

Does it all automatically, all I have to do is click a button.

It's, it's amazing.

You know, the knowledge system here is one that was one of the, the first parts of the system that I built.

And one of the cool things, lemme actually see if I can pull up one of the, the actual first notes that I made where I grabbed a podcast link.

It was the Trap Podcast, one of my favorite business podcasts about the music industry for the most part.

And there was a, a, a quote from the guest that I thought was really cool and I was not gonna write it down.

So I grab, I grabbed the link later and I dropped it in the system and I said, the guest on this podcast had a really cool decision making framework or a framework of some kind.

Can you find that?

And help me remember what that was.

And it pulled out exactly what it was, along with all of these awesome examples of the framework and use like better notes that I would've taken for myself.

Pretty amazing.

And so the knowledge system here is kind of like it, it's your standard, second brain type stuff.

The difference is, is it doesn't require all the human labor of figuring out where to put things, where to retrieve things.

That all happens completely automatically.

Because of the Claude Code rule set that I have built.

This gets managed, curated.

It's both part of the filing and the retrieval process.

Connections get made between them.

A really cool thing that happens because of the relationships database is when I drop a link what it'll do is it'll also comb through the, the connections that I have in my relationships and, and potentially identify people who I may want to flag the article for and say, Hey, that would be really interesting to these.

One to three people, do you want to send it to them?

And it does not send it to them.

It creates reminders for me, right?

Helps me be a good friend, helps me be a good collaborator by surfacing those things and sharing them.

And that all happens as a byproduct of saving a thing for myself.

And the last thing is similar, kind of related to knowledge of the Spark file.

Spark file's a thing that I've been doing for a very long time, borrowed from a book called.

" Where good ideas come from" by Steven Johnson, one of my favorite books.

And the idea is that you jot down all these kind of half baked notes and thoughts and ideas and questions, and sometimes it's, it's somebody else's thing.

Sometimes it's your own, whatever it is.

And the point is more that you write, get the habit of writing it down.

And that's what I've, I've very much been in the habit of writing things down.

And then once in a while you go through and you reread all of 'em and you start noticing patterns.

In those things that you think to write down, that's what it's really about.

And so as I started building out the system, I was like, well, I wanna move my Spark file in here because not only can I, I'm, I'm living in here, so it's always one click away.

But also I can maybe start building some tools to help me increase the depth of what I can learn from my Spark file about myself.

That's already starting to happen.

It's pretty cool.

So those are like the main working areas.

I want to go back to the project system, but before we do, I wanna show you the real the real star of this show.

And it is, it's this little chat button.

It's this little chat button.

That's it.

I lemme start a new chat here real quick.

I, this is basically one click away all the time, whether I'm in a browser on my computer, I have a a shortcut on my phone.

This is all mobile friendly.

And this is, the a ergonomic chat UI that I built on top of Claude Code.

So everything I type in here goes to Claude code the same way it normally would.

And then it spits out its answer and it gets presented back here.

So on the surface, this is a pretty wrapper for Claude code.

There's so much more going on in the hood.

And you'll see, so like I can move it into sidebar mode here as well, which I find to be pretty helpful.

I might actually just go back to the homepage and just so it's a little less busy.

And so I can do, anything that I would do from Claude Code, but remember that Claude Code instance has access to everything that we just looked at.

So that, back to the most basic example of knowledge management.

I've got a link to this webinar that I got from one of my contacts at the Philadelphia Revenue Department.

Some stuff they're doing to help small businesses and I wanna remember to both attend this and send this out to other folks.

So you notice I pace this in.

It is suggesting commands.

There's a, not only the standard slash command auto complete, but I have a more, basically a more ergonomic auto complete that ranks it based on the most used slash commands I have the most recently used slash commands, as well as some like fuzzy keyword searching and stuff like that.

So I don't even have to type slash I can just type a few letters for common commands and it will automatically execute them faster.

That's why that's pulling up something that is unrelated.

But as soon as I click space.

Slash command auto complete goes away.

And I could say I wanna attend this and remind others too as well.

In some cases, like I said, I would just drop a link and it would figure out what to do with it.

In this case, I do have a specific thing that I want to do besides file it.

And you can see that it is, you know, processing you know, I don't have it saying the funny little.

I guess there are adverbs or verbs.

Amy is gonna kill me for getting that wrong.

But the little bit of terminology that they, they kind of cycle through in Claude code, I don't have anything that goofy.

But it does show you, you know, tool uses, tool uses get rolled up in these little containers.

If you're someone who doesn't want as much noise about the tool use, you can also collapse that.

But you can see it, read the page, it looks at all the details.

Four free webinars, registration link set up.

Reminder for the first session and to share with others would be great to, oops.

I say, just remind me about the next one on Monday at 10:00 AM and depending on where I am, if I'm on my mobile and I'm not around other people, I use voice mode for this a lot.

You can see there is actually a built-in voice mode that I have that again, has a handful of little, like, cleanup, ergonomics and things like that, that I'm gonna have to do a little more work on it to make it work the way I want it to.

But in some cases it's better than the built-in iOS one or other cases.

It's worse.

Experimenting.

But you can see it created my reminder and that's it.

Ah, so it is an LLM.

Does still occasionally make mistakes.

And I'll tell you the most common mistakes it makes are around dates and times.

If I do something outside of a slash command is where it's most likely to happen.

If we're talking about multiple dates, you have to be a little more specific with it.

Truth is, is I don't think it's any more or less specific than you with a human where they could, you know, accidentally guess the wrong month that we're in, or backwards or forwards, those kinds of things.

The difference is like, as I catch these cases, I can build in rules to make sure it doesn't.

And so in this case, I'm gonna say no.

I mean, a reminder this upcoming Monday, please.

And it'll go ahead and fix that.

I, that being said, the.

Vast majority of what I'm doing in the chat these days is less freeform unless I am brainstorming with it, which is something that I'm doing fairly often where I will brain dump what I want, like what I'm thinking, maybe for an article or a newsletter or I need to like plan a project and instead of trying to get it all outta my head at.

In order I will just kind of brain dump into it and have it reorganize it for me.

That is the most majority of the freeform work that I do in here.

Most of what I do that is not, that is powered by slash commands.

So again, I can come in here.

Very common thing that I'm doing is you know, creating agreements for our community partners, or I'm setting up new projects.

The book room is a fun one.

If I do.

Oops, if I do book room and I say, you know, next hour and then I can either be specific about what room I want to book or I can let it pick from my pre-registered priorities.

This automatically connects to the Indy hall room booking system and logs in as me and.

Takes care of all of that for me.

I'm not gonna do it now, but that is something that I use fairly often.

You know, plan planning an event.

This, this is a good example of one where, you know, I run a slash command and this will basically ask me, it'll look for context clues and ask me for the next step based on those context clues.

So in this particular case, is it a new event or an existing event?

And I could say this is an existing event.

And what it's gonna do then is it hopefully is gonna go look at the database and it's going to pull a list of potential events that we could be talking about that are in progress.

And I may wanna pick up where we left off.

And the cool thing is, is our entire event management workflow is set up.

It's a workflow, it's a set of things that usually happen in a certain order, but things have prerequisites and stuff like that.

And so if I give it an example of, of an event that is in progress it can figure out where we left off and pick up from there automatically.

Another very common one that I'm using is our newsletter.

This might get goofed up.

'cause normally I don't run a bunch of slash commands in one session.

Sometimes that's one of the things that can confuse it.

Sometimes I need to create a clean session just so it's not going out of its way to interpolate facts from previous things that we did that might not actually be related.

And actually here it's pointing out the fact that, hey, you might wanna finish this.

So that's actually pretty great.

We're gonna start a new chat and we're gonna do.

The newsletter command.

'cause this is a pretty cool one.

And it's one that I happen to know is in progress.

Folks may have noticed that the Indy Hall newsletter's really gotten a, a bit more.

Awesome.

As the note that I've been hearing in the last couple of months that is not because this thing is writing our newsletters.

This thing is helping us write our newsletters.

And so I've turned our newsletter production into a workflow where once again, it is doing the annoying.

slow mis and plus process of looking at all of our calendars and making sure that the upcoming events for the current week as well as the ability to look forward are in there.

If we've described them in the past, it can reuse the language that we used rather than generate weird garbage on, on its own.

So on and so forth.

It follows the template.

And what's cool about using an LLM for this is.

You know, you could use a form to put in this information too, but not everyone is identical.

They're like mostly the same, 95% the same, 90% the same.

But the last 10% is where we'd waste a bunch of time trying to like, reshape the template or update the formatting and that introduces errors and blah, blah, blah, blah.

But what's cool here is I think of this process almost like a it's like a Play-Doh.

One factories, you push the Play-Doh through the extruder and it comes out in a funny shape, or maybe a less silly version is like a pasta dye.

My templates, my data structures are like the dye, the shape that it needs to come out in, and, and the data itself gets squished into it.

And the LLM is remarkably good at making sure that all the pieces fit where they're supposed to without losing.

What was there, and that's taken some time to make sure that it knows what not to let go of and what is needs to be preserved.

But it's remarkably good at it once I, I got that under control.

And so things like event preparation and generating agreements and contracts where like.

The vast majority of the contract doesn't change every time, but the places where it changes really matters.

It's been amazing at that sort of thing.

So you can see here where it picked up my newsletter workflow, it figured out for this upcoming Monday's workflow, everything is done except for the essay and the subject line.

And so if I was sitting down to prep for that, which I'll do probably tomorrow or Monday morning I will do that.

And then there's even some subsets of the workflow to help me gather up from a list of our.

Content strategy, ideas of the things that we want to highlight and how, and the stories that we want to tell and stuff.

Basically, instead of sitting down with a blank page every week and saying, what am I supposed to write this week?

I know what we're supposed to write, and this thing helps me stay on track as well as figure out where it all fits in.

So this chat tool whether it's for these prebuilt workflows that are there to make it so that we are more consistent, that we are not wasting time on.

Copying and pasting or copying, and then having to adapt it so that I can paste it into a different system like this is, it's not just shaving time off.

And it absolutely is.

It's just making things easier and more consistent.

Filling in gaps, helping us not drop balls.

Truly, truly a, a game changer.

And again, th.

At the ability to go from newsletter mode to events or events into reminders and all these things be a like, not just technically like data connected, but like the, because the AI systems are kind of wrapped through all of them.

The ability for anyone to affect the others with the very specific intention that I provided is, is pretty amazing.

Before we move on, I want you just a couple of the fun ergonomic things that I built into this chat.

'cause like I said, this is a wrapper on Claude Code.

So the cool thing about that is, is Claude Code is under the hood.

Everything that goes into the chat, every system that I've mentioned, I am not hitting Anthropics API directly for anything.

Everything is going through Claude code, using Claude code headless mode, which shout out to the Claude Code team.

That is a, tremendously cool, and I think massively underutilized piece of the of the technology that you built.

The fact that I can run a single command and it'll just go, or in this particular case, I can.

Send my request in the Claude code, get my response back, but also get back a session ID and then just keep looping.

Basically the next time I call it, include the session ID and it picks up where I left off.

Yeah amazing.

It's enabled so much power in my system.

I'm, I'm grateful for that.

So some of the things that I really like from cloud code, some of the things that I was like, I can add a, a, a little bit extra my own sugar on top.

So like, you know, the to-do list manager is like such a, a, not just a cool, but a smart useful feature.

And so, you know, wrapping my, my ability to see that you've already seen, you know, all the tool calls here happening.

I get visibility there.

I shared this with, with Amy, my partner.

She's like, this is kind of chatty.

And I was like, well, yeah, you can just close the tool call and I might set a preference where that, those close automatically.

And you just see the, you know, the spinner and the count while it's going.

All of those kinds of things.

We talked about slash commands, you know, image uploads is something you can do in cloud code.

What you can't do in cloud code usually is see what images you have uploaded.

So like, you know, I get my little preview strip here.

So I can.

Load in this current moment I have up to four images, but also like a thing that you can't do quite as easily or I guess you can do, but it's not as obvious.

So know I can drag.

That there, that works too.

That's, that's all nice, right?

It's niceness, it's quality of life stuff.

I also have this bar that pops up that lets me the open preview.

This is actually something I built for the, the email newsletter stuff and that lets me see in real time.

Basically, I can chat with the bot to make the changes that I want to make or do my rewrites.

Remind me about this.

Chat is a thing that I feel like Claude Code should implement.

Often I'm in a chat and I wanna come back to it later.

But I gotta go work on something else.

And so just the ability to click this and say, remind me about it later today, tomorrow, next week or, or custom.

Pause is a feature that I built that it's really just, it's a slash command that I've been using since I've been using Claude Code.

It's sort of like compact light where it uses a combination of GIT and GI commits to create a handoff to the next agent, or in this case just a clean session.

So it's not taking all of the context, it's just how much do you need in order to pick up where we left off.

And often it can be done in, in closer to like five or six seconds instead of the, sometimes it takes 30 seconds to a minute or more for a compact to happen.

I can, and I can be even faster, quick versus full.

Those are there.

Quick spark is my SparkNotes entry again, that is basically always just a, a tap or two away.

And then the other things down here at the bottom that are handy, you know, I've got my view of my model.

This whole thing is git backed.

So any changes that are being made to text files, this lets me know what branch we're on.

And, and so on and so forth.

One of the things I'm most proud of is, you know, I, I know that context management is a hard, it's like one of the weirder, harder parts of working with these systems and a lot to get your head around.

And so like having a counter of how many tokens out of the token window for Claude code sessions, is useful, but being able to open it up and see what is contributing to it.

Like Claude code, they have their version of this, but you have to like leave the screen to do it.

And this I can leave open and keep an eye on while, while long running things are happening and things like that.

This auto refreshes every, I think 10 or 15 seconds, something like that.

And these numbers are estimated based on token output from the actual like Claude code.

Like session logs and stuff like that.

So it's not perfect and it does recalibrate periodically, but for a general glance of what's going on.

And also sometimes debugging things where like, why is this chewing through tokens so quickly?

This is sometimes a, a first point of review for me.

And a few other little handy ergonomic things here.

You know, I've got this little dropdown gives me access to, I think it's my last.

It's like eight or 10 sessions you know, sorted by whatever the first thing I posted and the most recent thing is.

But another nice little thing is actually set it up where if I click this little sparkly line, it uses the haiku model to write a better description.

So like this one says, instead of the first sentence of what it was, it says change chat UI from close button to close button from X to minimize, which is this up here.

'cause what that actually does is.

Minimize it down to there.

Anyway.

So all that's there.

You can also rename those chat sessions manually create new ones, so on and so forth.

There's a handful of other things that are, are fun, you know, nice to have quality of life stuff that I've built and, and we'll come back to that in a second.

But the last thing I really want, really wanted to show you is.

How this tool and the combination of custom software integrated with a chat tool that I'm also using to build the system itself resulted in the project management tool.

And so, like I said, I did not set out to build a project management tool.

But once I was in here I was like, well.

Rather than try and have it wrap around another tool that is not actually ideal for my world, which is again, a little bit weird.

You know, what, what would a basic but maximally useful project management tool use.

I built my dream project management tool.

I've been working on this for about a week.

And the, the quick overview here is that you know, it's broken down into three main categories.

There's life 30,000 foot view, project in 10,000 of view and the now view, which is on the ground, and this is one of my favorites.

If we start from the top, the life view, these are my spaces.

Andy is the underlying AI systems that power, JFDI Indy Hall is all the projects related to that, stacking the bricks.

My business with Amy 10,000 Independence project.

Right now we're doing some of this important advocacy work and of course personal project as well.

Those are pretty straightforward, very easy to add new ones.

And ultimately I probably won't be adding a lot of new ones because these, these are really the containers for most of what I'm working on in my life.

I might.

Close one down and open up another one.

But this feels like a, a, a good starting point.

And the work streams section down here is a way for me to sort of thread through projects and tasks and, and people across spaces and, you know, because sometimes I'm working on things that are both Indy Hall and 10K or stacking the bricks and 10 K or all three, or, or Indy Hall and Andy, you know, being able to have those be connected in one unified system where there's

recurring people and collaborators.

There's recurring tasks.

Having those be isolated just into projects or even spaces is limiting in the way that I work.

And, and work streams basically solves that for me.

The project section is really the overview of all the things that I'm working on broken down by, my active focus, on deck down here growing and then on hold as well as, you know, completed projects.

And this just lets me at a glance, skim search sort by default.

My, one of my favorite things, I've, I'm sure this has to exist, but I've never seen it.

By default, this sorts projects by projects with a next action.

So it's looking at not what has the most tasks, it's looking at the next task that needs to be done in that project and it's due date and sorting that to the top.

'cause that's really what you're normally looking for, right?

Actually most often I'm looking for.

And then anything else beyond that is probably just beyond that horizon and sorts appropriately.

But if there is another specific way I wanna sort it, it could be alphabetical based on the pro full project deadline.

Not all projects have to have deadlines that might not be as useful.

How recently it was touched.

Is it overloaded?

Is it stalled?

There's little algorithms in here for each of those variations that I worked on with Claude Code, come up with the rule set and then build this in.

And it is, you know, fast.

Switching between them.

So like I, sometimes I'll just switch between 'em just to see what the world looks like from a different filter view.

Right.

You can see obviously I've got my, the project itself, the, the space that it's based in, whether or not it needs attention and health.

We'll come back to that in just a second.

You know, what percentage of the tasks inside of it are done as well as my little count.

And if the project itself has a due date that will be set where these ongoing things are.

But these all happen to be ongoing projects as well.

You'll notice this little bit under the bottom here.

You know, I found myself going back and forth between a project and its tasks.

And while you can see like it's pretty fast so fast that there's some like re-render glitches that I need to figure out how to, compensate for I don't wanna have to go back and forth just to see that.

So what I have it doing is showing a little stack of the tasks in that project with the first one peeking out, just so at a glance I can see.

But also, if I click this, I get the full list coming out.

We'll talk about what these little colors are in just a second.

A click again, makes that close.

Or I can, you know, click on another one and they expand between them.

It's really handy.

I'm finding for.

having a sense of what I'm supposed to be doing next is really how I think about the, the way we're headed in this project.

We'll go, we'll go into the details real quick.

Again, you've got a lot of the same stuff from that top view at the top here, as well as like things like planning notes and then the tasks themselves.

I mentioned those little color dots.

Those are related to these dropdowns, which are an energy type.

What's cool is these energy types are, are currently being guessed for by the system using I think that's using haiku.

It's doing a pretty good job of bucketing these, where this becomes useful, you're gonna see in a second.

But I find it is a really useful layer on top of the usual priorities, although that is in there as well.

And then of course, the due dates, which you can, you know, clear, I can kick it out seven days or choose a manual date, just the same.

Other projects.

This is a pretty straightforward, and this is like a catchall bucket for indie hall related tasks, but if I come into something that's a little more sophisticated like we could go into something like this advocacy project that I'm working on that is not just buckets, but actually has things broken out into phases.

And then inside of here I've got, you know, my notes and all of those kinds of things.

The other thing that's really cool in here is that event projects are tied to our events.

So, for instance, if I come in here to this project that I just set up for this series, we're gonna be continuing working with our friend.

Marquis And so this shows a link between the project and the event because not every event in our system is a, like a partner but if, if an event does have work to be done around it, we view ourselves not as a, here you pay for a date.

We see ourselves as active collaborators, making sure that event is successful and ideally growing the event.

Its impact and its community together.

And so this.

Becomes the place for that work.

And it gets broken down into phases and, and all of those kinds of things.

But for events, we've got that entire event production workflow that's deeply integrated to this so that every event gets set up, not identically, but correctly for the kind of event or event series that it is super, super helpful.

And then like, you know, if I come into some of our others you can see.

For instance, in this one the agreement, the stage wr as I sent out an agreement, the agreement is sent, and in fact, I happen to know that the agreement here was was paid, but I have not built the system to automatically update that yet.

That is in the works.

So that's, that's sort of the, the overview of how this works.

Again, it's projects, tasks.

Tasks can be broken down into phases.

And again, even within them, you know, you can reorder them.

If I come into one that's got phases I could come into any of these tasks and move a task and do a different phase.

All that is, is there and super useful.

If I wanted to change this from active focus down into one of the other stages, I could do that manually.

You get the drift.

What all this is building towards is my now screen, and this is really where I go to get work done when I've cleared the deck of all the things to react to and it's time to pick the next thing to work on.

This helps me do that now shows for each active project.

So again, every project that is currently an active focus, it shows anything that is overdue or due today.

Followed by up to three undated tasks that I can pick from.

'cause I found that showing just one I'd feel kind of pigeonholed and be like, well, what else is there?

But up to three, any one of those because they're ordered, would be good to do next.

And what's really cool about this is not only does it like zero in on what do you need to be doing right next, I can approach this based on my mood and energy.

So if I'm feeling.

I'm unmotivated, but I gotta get something done up sort by quick win and look for things that I can do there.

If I'm feeling super creative, I can be like, oh, let's, what can I point that at right now?

If I happen to have just completed some deep work and maybe I want to do a little bit more, I come in here and grab that, and so let's me approach the work that needs doing.

Intentionally, that's how work gets done.

And so like this is already starting to really reform how I map out my day and my day used to be very reactive to, to my energy.

And this is now allowing me to be proactive while using my energy as a tool rather than as a constraint.

And it's, it's been, it's been next level.

It's so cool.

There's a bunch of other cool stuff under the hood that I can show you.

Real quickly, you know, in the account settings, this system does have a light mode.

I have been to find myself using it in dark mode, but I even built in a little auto mode so it'll automatically switch into dark mode if you're in light mode.

As things get as the sun goes down, it's tied to actual location data.

I'm gonna keep it in dark mode for now.

Because as you can see, it was pretty glowy.

There is some audio feedback both for the voice mode as well as when the agent is done.

Often I'll have multiple sessions going on in the background.

And a cool little quality of life thing that I have is, it will make a very, very subtle sound that I can also turn off when it, the agent is done and ready with the next action.

But also it flashes a little thumbs up emoji in the tab navigation for the tab that is ready for next action.

And so even if I've got 10 tabs with JFDI doing stuff, I can see who's got a thumbs up.

That agent is ready for my next action.

You may have noticed in the background of the chat these squiggly little lines, if you don't like them, you can make them go away.

You can change them to dots or crosshatch, whatever it is.

This is a fun little quality of life thing to create.

And so on and so forth.

If that wasn't enough.

I got a little nuts with my admin too, 'cause I was spending more time in here and finding myself being annoyed whenever I had to go into a command line.

Especially if I'm on my phone just to see what's going on in the system or maybe debug things.

And I, you know, I still can and I still do, but it's less and less and less because of the tool set that I've built out here.

This includes, you know, at the overview here.

This lets me get a little bit of a health snapshot.

Of all the systems that are working automatically under the hood.

There's a bunch of jobs that are synchronizing data from outside systems. I'm not gonna click into that 'cause I don't necessarily wanna share exactly what I'm syncing with.

But those are monitored in there.

The whole job queuing system, my MCP server health and management happens inside of here.

Stuff is containerized that gets monitored and health and all those kinds of things is super helpful too.

Memory, I was playing with Claude Mem and I liked it, but I'm pretty sure I'm gonna.

Build out my own memory system that is based on the way I work versus something fairly generic that's gonna live in there.

Claude Sessions, I actually clean up the J-S-O-N-L files that Claude uses to manage all of its sessions every week.

But I backfill them directly into the same database that the rest of the system works in so that I can do some analysis and search across them and surface and resurface usable patterns.

So like that is actually the, the first layer of a memory system that I'm just not tapping into quite as much as I, I know I can.

But you know, if I come into this.

It can show me, you know, currently there's only one Claude Code in like actual app instance that is still holding memory and stuff like that.

That's handy.

But this lets me search across all my sessions.

It breaks them down automatically by these types.

That is all automatically done by Claude code.

Like that data was just in there.

And this all, again, is help.

It's more for debug now.

I want it to be part of the memory system going forward.

About a week ago, I got to the point where I was kind of losing track of my token usage, and I had my first like a thousand dollars week of Claude code, max overages, and I was like.

That's fine.

It was worth every penny of what I was spending it on, but it would be useful to know what's going on.

And so I went and I found some open source tools learned from how they work and built my own way of analyzing.

The token usage.

And now keep in mind a lot of the, these numbers, the cost numbers are not accurate because I'm on a Quad Pro max model.

And so like a, I'm pretty sure this estimate is not a hundred percent correct based on a number of other factors.

But even if it is, that's not coming outta my pocket, that is being included in my Claude Pro Max account based on my weekly and daily.

Usage.

But this lets me get a sense of also like what includes are adding up to that token usage.

What tools are adding up to that token usage?

What are some of the most expensive sessions?

And so as I am looking to trim down token utilization, this will be one of the first places that I go to do it.

This is a fun one.

Being able to find sessions that used more tokens than usual.

How much more tokens and why.

And then I mentioned that slash command system that we have earlier.

This is where not only all the slash commands get like registered basically, but also it keeps track of I can see the actual slash command itself.

So you can see my morning overview command.

That one that generates my, my home view, my dashboard, this is the whole thing.

I'm gonna scroll by it really quickly.

But you get the sense, and you can see since I installed this, it has been used 18 times last on the 12th, which was yesterday.

And what's cool is I can sort these by most used, most recently used and all of those kinds of things which is proving itself useful in making me fast in the system.

That I think in just under an hour is a tour of.

One of the coolest things I've ever made for myself, and I think that's the key, is I, I, I made, I made something that I, I had never thought I could make.

And these tools en enabled me to make, and it have, have materially changed how I feel about my, my work and how I moved through my day and pretty soon be able to invite some of my teammates and collaborators into parts of this app as well.

the reason I'm sharing this is because I, I feel like when I see all of the conversations about AI stuff on the internet, it's a lot of like hard lines.

This is good, this is bad.

This is not useful.

This is useful.

There's a lot of hype, there's a lot of hyperbole.

And I've, I just wanted to share my own experience because I, I, I.

Get the sense that in some ways it's unique, but in other ways it might be the thing that makes people take a, a different look at some of this stuff.

Because I'm not in this to build software, the fact that I used to build software, it gave me a set of understanding and skills and tools.

But I hadn't used them in 15 years and Claude Code kind of gave me a renewed, not just ability, but excitement to use those skills again in, in new ways and build something that I'm really proud of and, and I'm excited to use every day.

And I, I can't remember anything, at least not in a long time, that has given me that, that before.

So.

I'm gonna keep working on this because I'm using it every single day and I'm looking for ways to make it better.

I'm looking for ways to integrate it into more parts of my work.

In ways that it doesn't do, like, it doesn't do the work for me, but it helps me do the work better, faster, and more consistently.

It helps me show up for people better and more consistently.

It helps me have better ideas of my own rather than feeling like I need to rely on it for ideas.

It just helps me stay organized and on game and that is what I think a great executive assistant.

Does, in addition to being there as a a, a real person, I still would like to have a person like that in my professional life, but I also have great collaborators in other ways.

So maybe, maybe I don't need that.

I'm not sure.

One of the good news, like parts is like almost everything of meaning that this system does is basically a giant SOP or collection of SOPs and.

I found that it's very, very good at writing instructions better than I've ever been.

And so if I get to a point where I do actually hire an executive assistant, a, I will hope that they will want to use this tool because it will help them be better at whatever it is they're doing for me.

But also I can use this tool and its SOPs to teach someone else how to manage my work and my life.

Which is, I think a big part of the challenge that I had, the previous attempts that I've.

Made it trying to hire an assistant.

So, this has been a learning experience for me across the board.

It's been fun to like get back into software engineering, been fun to learn new tools, been fun to solve my real world, everyday problems. Some of these problems that are solved in the system.

I will say, I didn't just solve them, I super solved them.

And there are problems that I've been complaining about for like.

20 years of looking for a tool to do X, and now I'd only have a tool that does that.

I have it do that, does it in exactly the way that I want it to, and not in isolation of all the other things that I do and need to do and work with and, and so on.

So, I, I don't know, ask me questions and let me know what you think.

Thanks for watching and I hope you have a great day.