Product @subtextdev by @fullstory. https://xitter.cf/t.co/i9H6VbGSr2 OSS maintainer. Head over heels for @laybabylay
Atlanta, GA, USA
Joined March 2008
- Tweets920
- Following467
- Followers280
- Likes399
There's so much noise on X about the newest 3 month old startup that "killed" some other company/category. It's exhausting.
If I want to know if a product is good, I just go look at who's using them. If Mercury, Cursor, Ramp, Sierra, Factory, Warp, and others are all using Namespace, there's probably a good reason why.
Welcome, @mercury.
The fintech more than 450K ambitious companies and entrepreneurs trust with their finances, now running builds on Namespace.
Chip Lay retweeted
if you think @useblacksmith is good, wait until you try @namespacelabs 👀
@sequoia is leading our Series C at a $1B valuation.
Since January, we’ve gone from running 5M CI jobs a week to over 90M. Agents are writing an order of magnitude more code, and all of it still needs to be built and tested before it ships.
I’m here for this new wave of “just-in-time UIs”.
I predict we'll see most SaaS products (that continue to have some form of UI) adopt this type of pattern over the next 6-12 months.
Wabi 2.0 is live!
personal agents are one person, one chat. but the parts of life that matter run on more than one person
Wabi is an agent you use together. you talk to it, it does stuff, builds the apps you need, and anyone can join the thread - your partner, your best friend, the preschool moms groupchat
school changes pickup time → Wabi updates the family calendar, everyone sees it.
a show you’d both love → Wabi finds a night that works, gets the tickets.
the trip everyone keeps talking about → Wabi picks the dates, builds the itinerary, books it
go start a thread with your people 👇
🪰🧠
Spinning up 100 Namespace Devboxes, each simulating a 166,700-neuron male fruit fly connectome playing DOOM.
I selectively silenced neurons across the connectome to test how targeted lesions alter motor output and survival. 100 fly brains, 100 neural perturbations, One last fly standing.
Full write-up in the comments.
I’m a few weeks into using @bot and it keeps surprising me with new use cases.
Bots handle my wife’s day-to-day business operations, manage our family calendar and kids school schedule, create personalized interactive courses when I want to learn a new topic, and so many more.
I have one meta bot, Agent Smith, that keeps things running smoothly and safely behind the scenes: x.ai/bot/JcFj23aaufNWkuiiJTX…
Simulations need ground truth from real user trajectories. If you want to hack on a DIY project in this space, try this:
1. Add Subtext on your site/app (headless Fullstory, free to try)
2. Have Claude build out a Sightmap (oss spec and tools, MIT) to document and check-in the current state space of your apps runtime
3. Have Claude routinely “watch” all your sessions to discover/document user personas and jobs to be done, make it a durable wiki/db.
4. With every new change/hypothesis, have Claude simulate the learned persona groups against the specific JTBD using the sightmap browser CLI
There are more sophisticated models that cost lots of money, but this is an easy and free way to experiment with simulation testing.
Trend I'm following: Teams using AI "simulations" to quickly test product ideas and flow tweaks.
Products like @simile_ai, @primitivelabsai, @syntheticusers, trytenera.ai, Seldon.com, and others.
If you've tried something like this, how'd it go?
Looks great, missing the map: sightmap.org/blog/building-i…
Excited to test drive this!
Very excited to have this out the door.
I started to notice that Actions were a big bottle neck for us a few months ago. We’re pretty big power users.
From the beginning we built this on the git protocol so that we would have flexibility on where repos could exist. A lot of times we have work that we’d prefer to live silod off and now we can do exactly that.
The other thing is that b/c the underlying providers can handle massive concurrency you don’t really need a queue.
Much much more to come of course.
Chip Lay retweeted
Fullstory and Cursor users, have I got some fun to you.
Chasing a bug report? Ask Cursor to pull the sessions instead of guessing repro steps.
Scoping a fix? Ask Cursor how often that failure path gets hit before you decide how urgent it is.
A couple clicks and you are live.
“The last remaining bottleneck is context on customers”
Well, it used to be before we shipped Subtext.
Give your Linear (or any) agent tools to efficiently “watch” every meaningful user session.
subtext.fullstory.com/docs/r…
first the execution is the bottleneck, then reviews (@linear diffs), now CI.
And the end the last remaining bottleneck is the context on customers, product and your understanding of it.
Attach a session replay url to all of your Sentry errors and alerts, then agents can triage and root cause with deeper understanding of the real user impact. Screenshots, a11y trees, network req/res bodies, stack traces.
No need to sample when session capture is cheap.
.@sentry is a great tool to monitor the health of your products. But I don't remember the last time I've actually opened the website.
I just have sentry cli installed, and every morning an agent reads through the issues and flags P1s and P0s for me.
And with sightmap/sightkick (open source, MIT) you can have an agent map your app and codegen WebMCP tools automatically in a few minutes. Try it out!
There's two use cases for WebMCP I've seen:
1. Enabling non API only products to work over MCP. An example of this is a design tool like @paper and how they have a ton of canvas rendering required
2. WebMCP enables just a single engineer to get a product accessible over MCP
This is one of the most important things imo, as shipping a full MCP is significantly larger amount of work than reusing your existing auth and deployment
While it's not the ideal solution, someone can ship it overnight, show usage metrics, and then convert to a real one later
It's a middle ground between computer use and regular mcp
This looks incredible. Can't wait to test it out with sightmap and sightkick (webmcp tool gen) for turbo-mode browser use and automated testing.
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
For Linear fans, don’t forget to add real user sessions to ground your loops: subtext.fullstory.com/docs/r…
New capabilities for Linear Loops:
• Trigger from project, initiative, cycle, and issue changes
• Edit documents automatically
• Send tailored Slack updates
🔗: linear.app/changelog/2026-09…
Product factories need product context. A consistent stream of real user experience data as a production feedback loop.
Do you have a way for your agents to review and distill every user session into actionable product context?
