Build vs. Buy is top of mind for every team, but when does it make sense to truly build and maintain an AI product? Join Dave and Ed on Thursday June 18th to hear what they've seen across companies who've gone through Build vs. Buy. They'll cover where internal builds make sense, where teams underestimate the long-term cost, and where composing pieces wins.

don't lose a 9 this summer bag more 9s with Resolve AI

Every day, engineers spend hours on work keeping production healthy: monitoring deployments, analyzing anomalies, generating reports, reviewing resource usage. This work eats real engineering time and requires someone to always be on hand to run it. Resolve AI's new background agents handle it continuously. They run on a schedule, on event triggers like deployments or alerts, or on demand. With the new chat experience, engineers can spin up a background agent in a single prompt and follow up on findings in the same conversation to debug live or trigger ad hoc workflows. You start your day with a prioritized list of what's already been investigated, including verified findings and recommended next steps. Execution happens in the background, and you step in to review, debug, or approve. Background agents are a new surface for us, and we'll keep expanding what they can do as more engineering work moves into the always-on pattern.

Up next: you can now build custom agents on Resolve AI. Resolve AI capabilities are now available as an MCP server, a public API, and composable Skills. Engineering teams can plug Resolve into their existing agent ecosystems, and the AI systems your team already uses can call Resolve's investigation capabilities directly. Resolve agents tap into your internal skills and knowledge so investigations run with the full context of how your systems actually work. Codifying your team's expertise into Resolve makes every agent a multiplier on the rest of your work. Your expertise plus Resolve's agent infrastructure (models, harness, context, governance) gets you the best agent for the job. Engineering effort moves to where it's differentiated. Zscaler is already taking advantage: "For server-side investigation, my team uses Resolve AI. I built the classifier, the error code mapping, the probe logic for our customer journeys, and Resolve AI runs the investigation across our code, infrastructure, and telemetry." - Mike, Senior Staff SRE

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.

Code is shipping at 10x velocity yet production complexity is growing right alongside it. Mayank lays out our vision for AI for prod and the four properties any effective system has to have: → Own the workflow end to end, from investigation through resolution → Run continuously, catching problems before they page anyone → Learn your specific environment and retain team knowledge across on-call handoffs → Coordinate across engineers, agents, and surfaces without dropping context

AI is helping you write the code, but who is helping you run the software? Now more than ever, engineering teams need agents to run and fix software in production.