Introducing Zag
AI review agents for iOS, iPadOS, and macOS developers.
Zag runs agents in real Apple developer environments with Apple Silicon, Xcode, simulators, and your complete toolchain.
Describe agents in TypeScript or Swift that do code review, QA, security, or App Store compliance, and run them on every PR.
LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
The first wearable AI for pets and their humans.
See their world. Relive every moment.
Messages from your pet, like you’d get from a friend.
Videos. Memories. Real connection.
Petpin AI drops May 12 on @Kickstarter!
Over the last month, we’ve built, tested, trained, filmed, and most importantly, listened.
Demand for @petpinai has officially outpaced our first two batches.
Big news drops next week. You helped make it happen.
You’re not “doing” something; you’re moving with it. Ideas don’t feel forced, they just flow in the right direction. It’s not about pushing, it’s just time, and things start expressing themselves.
Been in a subtle state lately. Heard a podcast mention Maslow’s peak experience, and it resonated.
It’s a state of deep integration . No inner conflict, no tension. Sharp focus, but deeply relaxed. Everything,
body, mind, actions, aligned and humming on the same frequency.
Every pet deserves to be remembered.
We’re almost there—the first batch is on its way.
Can’t wait to see the world through their eyes.
#PetpinAI#ForEveryPet
Your pet’s about to go full-on influencer mode.
Smart video capture, automatic friend alerts, and more.
First batch is locked in — next drop coming soon.
Let’s make pets the main characters they truly are.
The most advanced pet wearable is almost here.
The first batch is spoken for. If you’re approved, your device ships in a few months.
Got questions? Drop a comment.
Excited to share the first @petpinai demo!
We're building wearable AI that captures your pet's world through their eyes. See what they see, even when you're apart.
This is just the first glimpse. Real pet testing is coming next!
🐶🌁 Bay Area pet parents! We’re building the ultimate wearable AI for pets, so you never miss a moment.
Want early access? Join our community for beta tests, meetups & first dibs on @petpinai 🐾
🔗 Sign up here: ⬇️
100 interviews. 100 conversations. 100 ways to make https://t.co/dfV6ueYiP8 even better.
This week, I’m diving deep into what pet owners really need—because building the best pet tech starts with listening. 🐶🐾
If you’re in SF, let’s connect!
We’re going all in this week: 100 interviews with SF pet owners! The goal? Refine the Petpin AI device and app to make it the ultimate tool for pets and their people.
Want to help? DM me, or find me at your local dog park. Treats on me! 🐶