Resolve AI

AI for prod: resolves incidents and runs production

[Resolve AI @resolveai]

don't lose a 9 this summer

bag more 9s with Resolve AI

[Resolve AI @resolveai]

Bag your own Bag More 9s bag:

https://t.co/TpyXxNAhtj

[Resolve AI @resolveai]

We asked you to share a time you "fumbled a 9," and you delivered.

From first-time on-caller horror stories to debugging a SEV2 two drinks in on vacation, one thing was abundantly clear: bagging more 9s ain't easy.

But with Resolve AI, we help make it easier than ever. If you want to learn how, or want to share your own story, check out the link below and we'll send over your very own Bag More 9s bag.

[Resolve AI @resolveai]

Read the ebook here:

https://t.co/xs4BoauGu1

[Resolve AI @resolveai]

A frontier model can produce a thousand coherent answers. An incident needs exactly one correct one.

That is the hard part of running AI in production. When you generate a line of code or draft an email, any plausible output can work. With an incident though, there's only one root cause. Miss it, and the confident wrong answer is the expensive one.

Frontier models will not fix this. The work is in the harness around the model.

We laid out exactly what that harness actually requires in our full ebook below 👇️

[swarit @swaritjoshipura]

very very cool hosting a group of engineering leaders @MLCricket, and hearing the universe boss @henrygayle stop by & talk shop 🏏 w/ @resolveai

[Resolve AI @resolveai]

don't mind us

[Resolve AI @resolveai]

Come learn where homespun AI for production most often cracks and crumble👇️👇️

https://t.co/LT9iRzCeNM

[Resolve AI @resolveai]

To build, or not to build, that is the question.

You cannot entrust your on-call rotation to a frontier model chained to a few MCPs. Those who build it themselves meet with answers spoken proudly yet false, invoices swollen past all reckoning, minds that keep no memory from one investigation to the next, and agents let loose upon your production realm, ungoverned and unguarded.

[Resolve AI @resolveai]

Find us next week in Alamo Sq Park 😉

https://t.co/TpyXxNAhtj

[Resolve AI @resolveai]

Artificial
Gelato
Intelligence

#AGI

[Annalise Krueger @annalisekrueg]

bag more 9s @resolveai

[Resolve AI @resolveai]

Who doesn't want their Sundays back?
For the next three Sundays, we're taking over SF parks with our custom Humphry Slocombe flavor: Matcha Cookies & Cream. Free scoops on us, this Sunday, Delores Park, 1-3pm. 🍨

[Resolve AI @resolveai]

You shipped twice the code this quarter. Something still has to watch it run.

The reason that work never gets automated isn't the task. It's the context only your engineers carry. Justin breaks down the four daily jobs where that finally changes:

https://t.co/OjWNPyEYL2

[Resolve AI @resolveai]

BREAKING NEWS: you can now get your own Bag More 9s bag on our website, free of charge.

At AWS Summit NYC and AI Engineer's World Fair our Bag More 9s bags were a fan favorite. Now, you can get your own Bag More 9s bag on our website, shipped directly to your door!

Just share a time you fumbled a 9 and we'll send you the limited edition bag 👇️

https://t.co/dEvnjlCZNp

[Resolve AI @resolveai]

Gametime's post-incident review was about to close on the wrong root cause. The real one was a code change 3 days earlier in an upstream service, 2-3 degrees from the symptom. Resolve AI traced it through the dependency graph and found it first. 📖 👇️

https://t.co/CG8k172bnq

[Resolve AI @resolveai]

Come bag your Bag More 9s bag at the AI Engineer World's Fair and learn why Silicon Valley's best engineering teams are trusting Resolve AI to help run prod.

Our team is here today through Thursday and we'll be demoing and taking questions all week long.

[Resolve AI @resolveai]

@_shreya_s @GreylockVC Watch the full session below:

https://t.co/C6hc1b2Trz

[Resolve AI @resolveai]

Last week, Sean Bell, our RL Research Lead for Resolve AI Labs, presented to a room full of engineers at our HQ as part of the SF Systems Reading Group presented by @_shreya_s at @GreylockVC

Sean focused on the paper "The Art of Scaling Reinforcement Learning Compute for LLMs," and went deep on topics like loss functions and train/inference mismatches to the challenge of building reliable environments and rewards for real-world agents. He also connected the research directly to Resolve AI's work: building domain-specific, multi-agent systems for production incident response.

[Resolve AI @resolveai]

Why does AI struggle at investigating production?

Listen to Steven as he walks through 4 key culprits 👇️

[Resolve AI @resolveai]

join us: https://t.co/Fw8MOamuLH

[Resolve AI @resolveai]

We had a horrible time.