Jason Steving

AI @ Temporal

[Jason Steving @JasonSteving]

Monty is one of the most impressive pieces of software. Agentic code mode made so so easy. Built the Temporal Agent Harness's code mode on this excellent foundation. Excited to upgrade to Monty V1!

[Samuel Colvin @samuelcolvin]

Fuck it, still early but here goes ...

We've just released Monty v1 - a Python sandbox that starts in 1 millisecond, not 1.5 seconds.

I just ran 10k sandboxed scripts in 674ms, something that would take a cloud sandbox > 3 hours.

This removes the biggest drawback of letting agents write code. The future is fast.

Even better, it's open source, you can install it from PyPI, npm or Crates now.

Serviced platform coming soon. Please get in touch if you want to be a design partner!

Who should try it?

⚡ if you care about startup time, use Monty
⚡ if you care about long-lived sessions, use Monty - Monty can be dumped and resumed at any external function call
⚡ if you care about accessing functions in the agent/host, use Monty - Monty makes it trivial to expose local functions into the sandbox
⚡ if you care about scale, use Monty - Monty workers use as little as 2MB of memory, meaning you can run thousands of concurrent sandboxes on a single machine
⚡ if you care about security, use Monty - we've run 3 rounds of bounty program and thousands of researchers have tried to break into our sandbox, meaning it should be secure to run untrusted code

Who should avoid it?

🚫 if you like to take a coffee break while waiting for sandboxes to start, DO NOT use Monty
🚫 if you enjoy the challenge of routing API requests from sandboxes through your corporate network to access state in your agent without exposing secrets to the sandbox, DO NOT use Monty
🚫 if your agent really needs to install packages from PyPI, Monty won't help you yet (spoiler: it probably doesn't)

https://t.co/avO8TWY5gJ

[Jason Steving @JasonSteving]

https://t.co/YvXWmyHrOP

[Jason Steving @JasonSteving]

Really excited about this new wave of decision models. Models like Jev (or Laya, or even some small LLM) plug in perfectly to the Temporal Agent Harness as an auto mode evaluator. Define your approval criteria, opt your tools in, and you can flip on auto mode.

[Jason Steving @JasonSteving]

Jev powered "auto mode" in the Temporal Agent Harness is such a natural fit. Jev is a big unlock for efficient agent oversight. Very excited to see how straightforward it was to integrate along existing harness seams. More to come here for sure.

[Jason Steving @JasonSteving]

https://t.co/nsSiAw7noq

[Jason Steving @JasonSteving]

Getting access to agents from Slack + Discord was super straightforward thanks to https://t.co/KgDvYcCiHs! Was able to roll a chat server to route these chat app interactions to Temporal Agent Harness agents super easily.

[Jason Steving @JasonSteving]

https://t.co/Hjxoaod2EI

[Jason Steving @JasonSteving]

Jev powered "auto mode" in the Temporal Agent Harness is such a natural fit. Jev is a big unlock for efficient agent oversight. Very excited to see how straightforward it was to integrate along existing harness seams. More to come here for sure.

[Jason Steving @JasonSteving]

@jssmith @temporalio https://t.co/rbnByuiDOw

[Jason Steving @JasonSteving]

@josevalim I just have a tiny workflow that literally just says "sup" to Claude Code every morning at 7:30am using my oauth token so the session windows automatically start/stop at a time that lets me make better use of it lol.

[Jason Steving @JasonSteving]

@thorstenball This is roughly how my weekly "blog" is generated. Throughout the week I use various MCP tools I made for Claude to take notes that sync to a centralized duckdb database, and then at the end of the week have a GitHub actions workflow to generate the site https://t.co/jjAJUpc0VZ

[Jason Steving @JasonSteving]

@sawyerhood This is amazing! I recently built https://t.co/ozDW01Yv5X a site that's fundamentally built around digging into US congressional activity by understanding YouTube videos of committee hearings. I'd be fascinated to know how our approaches to video understanding differ!

[Jason Steving @JasonSteving]

@adamgordonbell I built an AI agent to solve the #AdventOfCode problems for me this year, and so far it's working! https://t.co/mtSA6ue3jy #AgentOfCode

[Jason Steving @JasonSteving]

@ziyamomin_ @_buildspace Incredibly impressive! 👏🏾

[Jason Steving @JasonSteving]

@AaronPeddle @_buildspace @_nightsweekends This is incredibly impressive, man! Once the frame rate improves even a little bit this is gonna be a super cool space to explore

[Jason Steving @JasonSteving]

@adamgordonbell Hey, sometimes we just gotta make work a bit fun. Nobody's gonna die if this inconsequential web app delivers a month or three late, but there may be a chance I actually stay at XYZ boring company longer if I'm actually enjoying myself lol

[Jason Steving @JasonSteving]

@awesomekling You're an inspiration! And I'm hoping to follow in your footsteps! Currently ~4 months into a year off to work fulltime on a programming language I've been building for almost 2.5 years and I've never felt more fulfilled - one day I hope to find a way to make this sustainable lol

[Jason Steving @JasonSteving]

@contextfreeinfo I'm signed up! Really hope it comes together

[Jason Steving @JasonSteving]

@nick_s_drew @_wilfredh Gotcha. Feels like even just having "enhanced for loops" gives the same thing. But I hear where you're coming from

[Jason Steving @JasonSteving]

@nick_s_drew @_wilfredh Genuine question as I'm not extremely familiar with "everything is an expression" languages - could you share an example of "control expressions" allowing tighter variable scope?

[Jason Steving @JasonSteving]

@smartereveryday Destin's PhD Thesis: Flaming Prince Rupert Drops