Session: 2 for 1: Building Reliable AI Workflows / Leveraging AI Agents to Return Joy to Maintainers
Building Reliable AI Workflows – Rasam Tooloee
Building reliable AI agents is challenging—many teams struggle with bugs, hallucinations, and unpredictable behavior when deploying these systems. At Vellum, we’ve found that companies adopting test-driven development (TDD) approaches tend to achieve better results with their AI implementations.
In this practical session, Akash will share actionable strategies and real-world lessons from working with some of the most seasoned teams in AI development. The session will focus on:
- Demonstrating how to adapt TDD principles specifically for AI agents
- Sharing practical, battle-tested strategies for enhancing system reliability
- Breaking down different categories of agentic behavior and their applications
- Showcasing what’s achievable today and previewing emerging innovations in the field
For teams working to build dependable AI-powered workflows that deliver consistent results, this session offers essential insights and techniques you can implement immediately.
Leveraging AI Agents to Return Joy to Maintainers – Justin Dorfman
The open source community plays a crucial role in modern software development but encounters significant challenges, including maintainer burnout, sustainability issues, and supply chain vulnerabilities. This presentation will examine how AI agents are transforming open source development by addressing these urgent concerns.
Maintainers often face repetitive and tedious tasks. AI agents can automate these spirit-breaking tasks, such as code reviews, bug triaging, and code migration, allowing maintainers to focus on creating new innovative features and solving, similar to when they first started the project.
This session will adopt a vendor-neutral approach, encouraging the audience to explore ways to leverage AI agents to develop a more robust, sustainable, and secure the open source supply chain that benefits every human.
