AI Teammates: how monday.com runs production AI agents on Amazon Bedrock

<p>AI Teammates are agentic AI on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>, and few engineering organizations run them in production at the scale that <a href="https://monday.com" target="_blank" rel="noopener">monday.com</a> does. Nine in ten Builders use AI coding tools every month, up from roughly half a year ago. Per-engineer PR throughput is up by more than half. Every figure in this post comes from monday’s own internal production data.</p> <p>In this post, we share the architecture behind those numbers, the retrofits that made it work in a decade-old code base, and the confidence-scored merge play closing the gap to full autonomy.</p> <h2 id="this-is-not-a-greenfield">This is not a greenfield</h2> <p><a href="https://monday.com" target="_blank" rel="noopener">monday.com</a> is a decade-old code base, millions of paying users, hundreds of microfrontends and microservices, hundreds of Builders (Engineers, PMs, Analysts, and Product designers). Every PR an agent opens goes into a system millions of users expect to keep working through the next deploy. Greenfield demos are straightforward. Running agents inside an enterprise SaaS with real on-call, customers, and compliance is the work.</p> <h2 id="three-levels-of-ai-engineering">Three levels of AI engineering</h2> <p>You can frame the journey as three levels:</p> <ul> <li><strong>L1, the assistant.</strong> Engineers use AI as a pair programmer. Cursor for the fast reflexive work, <a href="https://www.anthropic.com/claude-code" target="_blank" rel="noopener">Claude Code</a> for the heavy lifts. Adoption has nearly doubled year over year.</li> <li><strong>L2, skills and sub-agents.</strong> Teams build reusable agents for repeated work, engineers in the driver’s seat. This is where most of monday runs today, and where per-developer PR throughput stepped up by more than half.</li> <li><strong>L3, multi-agent.</strong> Fully agentic. Agents own delivery end-to-end while engineers orchestrate, taking tasks from boards, talking in Slack and monday, shipping code alongside humans.</li> </ul> <h2 id="agents-are-teammates-not-jobs">Agents are teammates, not jobs</h2> <p>Sphera is monday’s internal agent system. The first thing you see isn’t a job queue, it’s a Teams page: a mix of humans and agents, each with a profile, a manager, a scope, and a performance score. Atlas, the agent at the center of this post, is one of them: role: Software Engineer. Job: pick up tickets, write the PR, ship the feature. IDE: none. Same backlog as everyone else.</p> <p>This isn’t decoration, it’s the schema. Every agent has a stable identity that flows through Slack, GitHub, and monday, so a human tags, assigns, code-reviews, or deactivates them like any other teammate. The agents that move the needle live on real teams, doing real work, accountable for the result.</p> <p><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/14/ML-21226-1.jpg" alt="Sphera Teams page listing humans and agents together, each with a profile, manager, scope, and performance score" width="800"></p> <h2 id="the-architecture">The architecture</h2> <p>Here is how the system fits together, from the inboxes an agent listens on to the AWS services that carry each event.</p> <h3 id="three-inboxes-one-agent">Three inboxes, one agent</h3> <p>A monday-built agent has three first-class inboxes: a Slack <code>@mention</code>, a monday item assignment, a GitHub PR review request. All three hit the same agent session, with the same memory and workspace on disk: three flavors of the same event, same queue, same path. We don’t run three agent systems. We run one.</p> <h3 id="the-architecture-in-one-diagram">The architecture in one diagram</h3> <p><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/07/14/ML-21226-2.jpg" alt="Architecture diagram tracing an event from Amazon SNS to p