Wrangling Wild Agents // Ezo Saleh & Aisha Yusaf // AI in Production
Speakers

Ezo is co-founder of Orra, building production-ready multi-agent applications. A tech veteran with over 20 years of experience at BBC R&D, JP Morgan Chase and various startups, he's been deep in Applied AI and DeepTech since 2017. His sweet spot? Making complex systems work better - from distributed systems to Kubernetes tooling used by thousands of developers.

Aisha is co-founder of Orra, a platform for production-ready multi-agent applications. Previously, she developed an AI-powered children's camera game and a podcast audience insights platform. A Central Saint Martins and London Business School graduate, she thrives on making the impossible possible through multi-disciplinary collaboration.
SUMMARY
Like brilliant but untamed minds, agentic applications in production present a unique challenge: they solve problems in revolutionary ways but can be wildly unpredictable. The art of deploying these free spirits requires a delicate balance between autonomy and reliability. At Orra, we've developed a "glue layer" that acts as a skilled wrangler, ensuring reliability while preserving the agents' freedom in production environments. We'll explore its architecture including our approach to adaptive execution planning, and how we enhance domain understanding.
CONTENT & TRANSCRIPT

