Put Resolve on-call so you can: - sleep - ship new features for customers - knock out your backlog - or whatever else you choose to do with your newly acquired free time. Our new website and brand have launched, but our mission remains the same: Machines on-call for humans.

Hosted by @baseten, Spiros Xanthos (@spirosx) from @resolveai and Greylock's @CorinneMRiley sit down to talk what it takes to out-execute the labs in the full SDLC. 💙 + 💛 + 💚🩷

ICYMI: we're giving away a limited amount of Hero of Prod shirts! Share a story on LinkedIn or X of a someone who's answered the late-night page to keep production running, and we'll send you both a limited-edition Hero of Prod shirt. Once posted, share the link and your shirt size here: resolve.ai/heroes-of-prod Machines on-call for humans.

the most interesting thing happening in AI x code today? speaking with @spirosx about production engineering, AI SREs, and how @resolveai has been out-executing the labs in the SDLC thanks @baseten for hosting luma.com/baseten-8li0

The systems we use and rely on daily are supported by engineers who answer the late-night page and go to heroic lengths to keep prod running. They tend to go by titles like SRE, production engineer, or simply on-call engineer. At ResolveAI, we prefer Hero of Prod. Introducing our inaugural Heroes of Prod cohort! They represent the thousands who keep the world’s software running every day. And we don’t want to stop there: If you know an engineer who’s gone to heroic lengths to keep production running, nominate them as a Hero of Prod below 👇️ resolve.ai/heroes-of-prod

Machines on-call for humans. Nearly two years ago, we introduced the idea to a market still in its infancy. Fast forward to today, that idea is taking off from concept to reality with some of the largest enterprises deploying Resolve into production and on-call rotations weekly. Try out Resolve today: resolve.ai/

What makes a founding team worth betting on? For Unusual’s John Vrionis: a technology inflection, deep customer empathy, domain expertise, rapid learning, and the conviction to pursue something fundamentally different. John has known @resolveai’s @spirosx for nearly 20 years and worked with him and @maynkag across three companies. We believe their technical depth, humility, and non-consensus conviction make them exceptional founders. We’re grateful to partner with them.

LLMs are extremely good at generating large volumes of knowledge, but ensuring that knowledge is useful is where the real value lies.

Listen to our very own @swaritjoshipura describe why a production agent is DOA if it lives inside a single or limited number of tools, and why Resolve queries your stack live at runtime instead of ingesting it.

Evals. Evals. Evals. Hillclimb. Hillclimb. Hillclimb. -Dhruv Mahajan, Chief AI Scientist at Resolve AI Don't fall for the 80% trap. With a production agent, the hard part is the last 20%. You need a loop to keep those models improving, and that loop requires evals built against your own production. Creating the right evals is a core ML problem: easy to get wrong, easy to make too easy, and hard to know what you should be climbing toward. It's not a project you finish, and most teams aren't staffed or ready for that.

What does it take to let an agent take action in production? Listen as Claire articulates the significance of guardrails and governance for agents -- especially those like Resolve that are taking actions in prod.

Why are evals on production agents so much more difficult than evals on coding agents?

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

don't mind us