Rethinking CI & CD for Agentic Workflows

As LLMs evolve rapidly and every product team rushes to deliver agile workflows, traditional CI & CD pipelines are no longer sufficient. To make agents and the Model Context Protocol (MCPs) truly successful, the software supply chain must adapt and provide the right capabilities.

In practice, this means supporting deployment into ecosystems such as LangGraph and AgentCore, where multi-agent workflows, orchestration, and runtime behaviors introduce additional layers of complexity. Validating agents within these broader environments ensures that quality signals remain reliable even under real-world conditions.

At Adobe, we are reimagining our CI & CD stack around deployment models and focusing on integrating evaluation frameworks (Evals) that will measure not only correctness, but also reliability, performance, trust, and safety. Our pipelines are being designed to validate agents not just in isolation, but also to ensure that signals from Evals translate directly into production readiness.

We will begin by showing how to bootstrap Evals for your agent, covering the generalized aspects that every agent must be vetted against, and then extend this to guidance on tailoring Evals for your specific use cases.

This session will share how we redesigned pipelines to balance speed with depth, introduced Always-On Evals in production, and established a Continuous Improvement Pipeline that keeps agents aligned as models and ecosystems evolve.

We’ll also discuss how to optimize execution and provide tips on test intelligence for selecting the right Evals based on run context, ensuring that tests are both fast and reliable. Finally, we’ll cover how to use these signals to drive decisions in CI & CD pipelines that help ensure your agent succeeds in the real world.

Attendees will walk away with practical strategies to modernize their pipelines and ensure success in the agentic era.

Zero Downtime, Maximum Impact: Migrating Artifactory Database at Scale

How do you migrate a mission-critical Artifactory database with zero downtime—while supporting thousands of developers? Join adobe's Vishal Raina, Kevin Patterson and Rahul Srivastava as they share their real-world experience executing a seamless migration from MySQL to PostgreSQL in a high-scale, multi-geo enterprise environment.

You'll get a behind-the-scenes view into the planning, tooling, and validation strategy that enabled a risk-free migration. We’ll cover how the team identified legacy system limitations, aligned cross-functional stakeholders, and executed the cutover with precision—all without impacting developer velocity. You'll also hear practical lessons learned on operational resilience, automation, observability, and post-migration optimization.

Whether you're preparing for your own DB migration or modernizing your artifact infrastructure, this session will equip you with actionable insights to reduce risk, improve reliability, and elevate the developer experience.

https://swampup.jfrog.com/session/zero-downtime-maximum-impact-migrating-artifactory-database-at-scale/

Self-service Diagnostics for Developers at Adobe

Developers at Adobe leverage Ethos multi-tenant and multi-cloud compute platform, based on Kubernetes. This platform is leveraged across Adobe by various product teams to host their solutions. As time has progressed, the complexity of services has increased which in-turn has required investment into solutions beyond the core observability stack. To address these challenges, Ethos has built capabilities centered around diagnosing issues and identifying root causes. The focus is to provide self-service capabilities to development teams to detect root cause and remediate issues. This has helped in reducing MTTR for various incidents and improved overall reliability. These tools have also been integrated with "Get Help" workflow and is a key capability of Adobe's Internal Developer platform (IDP). In this session, attendees will learn about Adobe's observability stack and self-service diagnostics capabilities offered by Ethos.

https://pages.awscloud.com/GLOBAL-event-T3-open-source-symposium-2022-confirmation.html

The Supply Chain of Intelligence: Building Trustworthy Agents

As LLMs evolve and agentic systems become central to modern products, traditional CI & CD pipelines are no longer enough. The future of software delivery will depend on re-architecting the software supply chain to support intelligent agents, multi-agent workflows, and dynamic runtime ecosystems like LangGraph and AgentCore.

At Adobe, we’re envisioning a new generation of CI & CD, one that integrates evaluation-driven validation (Evals) into every stage of the lifecycle. These pipelines will continuously measure not just correctness, but also reliability, performance, trust, and safety — ensuring that agents succeed not only in isolation but within the complex environments where they operate.

We’re designing for continuous improvement loops, always-on evaluations, and intelligent test selection where CI/CD evolves into a living system that learns from production signals. This approach will help teams ship agents that remain aligned and resilient as models and ecosystems evolve.

https://web.cvent.com/event/4aed8a6e-0e6d-4f55-abd5-f42b3f45d096/summary
https://www.linkedin.com/posts/stacy-drumm-3848951_loved-the-spirited-discussions-at-yesterdays-activity-7386791069293862915-MC-K?utm_source=share&utm_medium=member_desktop&rcm=ACoAAA6W_HMB9plUWoOfIc9Zq4dlZCfKBhSpHbs