AI Agents: Making speed, quality, and cost work at scale

Now that we’re all adopting AI agents, hard questions are emerging. Token costs are climbing. Output quality is inconsistent. And as the shine has worn off, our teams are growing irritated by the constant babysitting and back-and-forth loops. The next wave – background and cloud agents that run autonomously – will only compound the issues.

Join us in San Francisco for an exclusive dinner with VPs of Engineering navigating this inflection point. We'll dig into what it actually takes to extract lasting value from AI agents at scale:

1. Making the economics work

AI spend scales fast and the bill doesn't always correlate with results. Model routing, caching, prompt optimization, better context… there are a dozen levers. Which ones are actually moving the needle for your team, and where are you still experimenting?

2. From demo speed to team speed

Agents can generate code fast, but shipping fast is a different problem. It involves review cycles, integration, trust, and knowing which tasks to hand off in the first place. What has actually changed your team's throughput versus what just shifted the bottleneck?

3. Quality at scale, especially without a human in the loop

When an agent has a developer reviewing every output, quality is manageable. But the industry is moving toward background agents that run autonomously to handle tickets, CI pipelines, migrations. What does your quality bar look like for agent-generated code today, and how does that change when there's no one watching?

This invite-only event is designed to create an intimate space for you to meet with a small peer group of high-caliber engineering executives to discuss challenges, exchange best practices, expand your professional network and more.

We hope to see you there!

Questions? Contact [email protected]