Jess Martin
banner
jessmart.in
Jess Martin
@jessmart.in
🛠 Tools for a better tomorrow
🧠 Architect-philosopher
💼 Building https://worksquared.ai
🏠 https://jessmart.in
📍Fuquay-Varina, NC
friggin' love Conductor.build
November 5, 2025 at 5:31 PM
cursor composer zoom zoom 🏎️
November 4, 2025 at 8:49 PM
Nice office and even nicer guy!

Recommend 🅰️➕➕➕
i'm hiring a 'growth engineer' to work side-by-side with me at val.town in brooklyn

we're a small team on a mission to spread the joy of programming

we're looking for someone self-directed, loves talking to users, write english & typescript, and own projects end-to-end

if this is you, reach out!!
October 28, 2025 at 4:04 PM
oh right, it's that one weird week where the US and Europe diverge on daylight savings time
October 28, 2025 at 4:03 PM
90% of the time when an LLM fails to do a thing for you, it's a lack of proper context, not model capability.
October 21, 2025 at 10:24 PM
Reposted by Jess Martin
rooms are where life happens. we create, workshop, collab, party, veg out, bring up our kids... in rooms

and we do it together

why would I want a computer strapped to my face? instead: a computer we can walk into... and walk out of

I am all-in on augmented environments.
October 17, 2025 at 1:43 PM
Why does Claude Code operating directly on files in my Obsidian vault feel so much better / different than Claude Desktop + an Obsidian MCP server?
October 10, 2025 at 12:56 PM
I finally did the thing: pointed Claude Code at my Obsidian Vault's markdown files.

Oh. My. Goodness. This is great!
October 9, 2025 at 2:57 PM
I think this succinctly explains the rapid adoption of LLMs in a variety of domains.

There's something tipping point for accuracy where the generality wins become more important than 100% deterministic predictability.
My hunch is that humans will be able to accept a surprising amount of nondeterminism once error rates reach acceptable levels. We accept a lot of nondeterminism from other humans, and understand that 100% reliability comes at the cost of flexibility.
October 9, 2025 at 12:24 PM
I'm finding it's more valuable lately to spend my time on "build the software factory" than to actually build the software directly.

Improving the quality of work and parallelization across my AI agents is a huge force multiplier.
October 8, 2025 at 1:39 PM
🎥 Tomorrow 10am ET/7am PT

Continuing to evaluate using the Claude Agent SDK with @livestore.dev on a livestream.

Come hang out!

youtube.com/live/bOVeT-s...
Coding With Jess: LiveStore and the Claude Agents SDK, Part 2
YouTube video by Coding with Jess
youtube.com
October 6, 2025 at 8:30 PM
🎥 Starting now!

I'm livestreaming building a LiveStore app that uses the Claude Agents SDK as the "agentic loop" and interacting with the LiveStore app through custom tools.

Should be fun! Come hang out.

www.youtube.com/live/5-1TF51...
Coding With Jess: LiveStore and the Claude Agents SDK
YouTube video by Coding with Jess
www.youtube.com
October 3, 2025 at 3:00 PM
Probably gonna livestream building a LiveStore app with the Claude Agents SDK.
October 3, 2025 at 1:41 PM
Reposted by Jess Martin
LiveStore Hands-on #1: Work Squared

Friday, Sept 26 @ 5pm CEST / 11am ET (tomorrow)

Watch @schickling and @jessmartin hands-on with a real LiveStore app:
▪︎ Architecture review
▪︎ LiveStore best practices
▪︎ Live debugging
▪︎︎ Source available

luma.com/4s7qev78
LiveStore Hands-on #1: Work Squared · Luma
Real-time code review of Work Squared built on LiveStore. Framework creator Johannes pairs with app author Jess to debug, refactor, and share best practices.
luma.com
September 25, 2025 at 5:49 PM
Reposted by Jess Martin
Book-to-soundtrack experiment - a projector setup where I send the book image off to an LLM for recommendations and then play with Spotify.

Meant to be kind of like putting on a record but for objects. (I clipped out the loading times.)
September 25, 2025 at 2:50 PM
I'm demoing worksquared.ai and how I'm using livestore.dev to build it in about 40 minutes.

Sync engines are awesome!

luma.com/dp4j8a3e
LiveStore Office Hours #5 · Luma
Ask questions and get feedback on your LiveStore usage. Please submit your questions/topics ahead of time via this form. (Note: The event will be livestreamed,…
luma.com
September 4, 2025 at 2:19 PM
Bless you, Conductor
September 4, 2025 at 1:01 PM
The definitive UI paradigm for AI has already been established.

It's Chat.

It's unfortunate. But thems the Facts.

Just like you can't reinvent the steering wheel when designing a car, you can't escape Chat.
August 28, 2025 at 6:23 PM
@danversfleury.bsky.social and I are walking this path of pain together and trying to build our way out of it.

It's so... fun?
August 25, 2025 at 3:04 PM
I've made a *lot* of @tldraw.com's over the years, but these two might be my most favorite, ever

#nocontextwhiteboards
August 20, 2025 at 3:35 PM
At @sociotechnica.org we've been working on an "agentic environment" called Work Squared for a few months and it's starting to feel truly useful!

youtu.be/1yfpGT6B50w

Core concepts:
- Agents and humans can collaborate on all of the work products
- Make it visual - see everything that's happening
Work Squared - Product Demo - 2025-08-16
YouTube video by Coding with Jess
youtu.be
August 18, 2025 at 2:40 PM
A horror story, in 6 words:

Your branch and 'main' have diverged.
August 14, 2025 at 6:31 PM
AI advantages existing platforms.

The more data/tools you have, the more AI can do. Incumbents will sherlock every innovation.

Yet AI also requires rethinking software from scratch.

What will prevail: platform dominance vs startup disruption?

notes.jessmart.in/Lab+Notebook...
AI advantages existing platforms - Jess's Lab Notebook
AI advantages existing platforms AI fundamentally benefits from aggregation—of data, tools, and user context. This creates a powerful gravitational pull toward existing platforms. The more comprehens…
notes.jessmart.in
August 13, 2025 at 1:27 PM
I'm running the same experiment: using our own AI tool to help me get my life in order.

Excited to see where this goes.
Good news: In my pursuit of work life balance, the scale is balanced at 50 / 50.

Bad news: The scale can't handle this much weight.

Can all the latest AI model breakthroughs now save me from myself?

WorkSquared Labnote #5: sociotechnica.org/notebook/ove...
Can AI Cure My Addiction to Overcommitting?
Exploring how AI can help manage the balance between work and life when you're overcommitted to both.
sociotechnica.org
August 7, 2025 at 9:08 PM
@danversfleury.bsky.social you should check this out - you'd like it
Loved the article and agree Anthropic, in particular, ought to add a more critical “Be honest…” style as an option.
And no, users shouldn’t have to do the heavy lifting, so I asked Claude to:
claude.ai/public/artif...
Improved Critical Thinking Style Prompt | Claude
Sharpen your critical thinking with this rigorous AI prompt that challenges assumptions and exposes logical gaps. Built with Claude AI at Claude.ai
claude.ai
August 6, 2025 at 1:15 PM