News
Agent Architecture: Why Enterprise AI Needs More Than a Model
18+ hour, 9+ min ago (602+ words) Build or buy? See where eng teams are landing We are used to the excitement when frontier models get better at generative tasks. We speak fluently about tokens, context windows, and benchmark scores at every release. On the flip side,…...
AI On-Call Agents That Triage and Investigate Alerts
14+ hour, 58+ min ago (1215+ words) Build or buy? See where eng teams are landing During on-call rotations, dealing with the volume of alerts fills the shift. You assess alerts as they come in, rule out the noise, and dig into the few that are real....
Software reliability in the age of AI-generated code
21+ hour, 11+ min ago (870+ words) Build or buy? See where eng teams are landing Software reliability is the probability a system runs without failure over time. Why AI-generated code strains it, and why keeping systems reliable now needs AI. When software creation was deterministic, reliability…...
What is an AI incident management platform?
6+ day, 21+ hour ago (1036+ words) Build or buy? See where eng teams are landing An AI incident management platform uses AI to handle production incidents, from coordinating the response to investigating systems and finding the root cause. An AI incident management platform is software that…...
AI Tripled Our Code Velocity. Here's What It Did to On-Call.
1+ week, 6+ day ago (487+ words) Build or buy? See where eng teams are landing By Jeff Aronhalt, Principal Backend Engineer, Gametime Gametime is a last-minute live event ticketing platform where reliability isn't just an engineering concern - a degraded purchase flow during a sold-out game is…...
What to consider in AI SRE Tools
3+ week, 5+ hour ago (940+ words) Learn how always-on agents run our prod backlog A guide to AI SRE tools: categories, capabilities, real user reports, and implementation considerations for engineering leaders. AI SRE tools have moved from experimental to essential in production environments. The shift represents…...
AI Incident Management Tools: Complete Evaluation Guide
3+ week, 13+ hour ago (758+ words) Learn how always-on agents run our prod backlog AI incident management tools change this dynamic by investigating across your entire production stack simultaneously. Instead of alerting engineers to problems, these platforms actively investigate issues by correlating signals across multiple systems,…...
Behind the Build: Agents and engineers, on-call together
1+ mon, 6+ day ago (213+ words) Get an exclusive look at how we built Agent Teams + Workbench What does it actually look like when agents and engineers work the same incident together? Most on-call time goes to figuring out what's happening before anyone can fix it....
Product overview | Resolve AI
1+ mon, 1+ week ago (257+ words) Launching Agent Teams, Workbench, MCP, and more AI agents drive your on-call, incidents, and daily operational tasks in production. Engineers step in to direct and take action Agents for on-call, incidents, and operational tasks. Built on a platform that plugs…...
Custom agents | Resolve AI
1+ mon, 1+ week ago (264+ words) Launching Agent Teams, Workbench, MCP, and more Compose Resolve AI primitives into your own agents and existing workflows. Use context, investigation, and remediation without rebuilding them Resolve is exposed as MCP, API, and Skills. Your agents call Resolve for production…...