Skip to content

Details

Join us for a free live session on what happens once an AI agent is serving real traffic through your API. The session content is drawn from Ali Parandeh's upcoming Manning liveProject series, and the practical follow-on from his FastAPI book (O'Reilly, 2025).

In this talk, Ali will cover the production-reliability problems specific to serving agents through a service layer: tool-calling failures that don't surface as clean exceptions, cost and latency that scale unpredictably once an agent starts making its own decisions, and where guardrails actually belong in the architecture.

This session is designed for engineers building or serving AI systems through FastAPI or similar frameworks who want to go beyond "call the model from your endpoint."

  • Date: Monday 10 August 2026
  • Time: 6:30pm to 7:30pm (1 hour)
  • Location: Online (Free)

We'll cover:

  • Core failure patterns once an agent moves from notebook to service
  • Tool-calling failures and why retries often make things worse
  • Cost and latency at scale, and why agents don't scale linearly
  • Where guardrails belong in your service layer
  • A preview of the upcoming Building Reliable AI Agents Series (Manning, 2026)

No coding setup required, this is a talk with live examples.

Speaker
Ali Parandeh is a Chartered Engineer (CEng) with the UK Engineering Council and author of Building Generative AI Services with FastAPI (O’Reilly, 2025). With a career spanning engineering consultancy, global tech firms, and AI start-ups, he has led teams to design and deploy scalable AI-powered products across transport, finance, education, healthcare, and manufacturing.

Certified by both Microsoft (Azure Developer) and Google (Professional Data Engineer), Ali is recognised for making complex AI concepts practical and accessible. He delivers training for the Institution of Mechanical Engineers and runs Build Your AI, a consultancy focused on getting safe AI adoption right in heavy industry and engineering organisations. He speaks regularly at industry events and is known for pairing real technical depth with practical applications.

Agenda

  • 6:30-6:45pm: Introductions & conceptual overview
  • 6:45-7:15pm: Talk with live examples
  • 7:15-7:30pm: Q&A and closing

Spaces are limited. Registration is free but required to secure your seat.
Register at: https://luma.com/ecyxsgcn

You can learn more about the upcoming series at: https://buildinggenai.com

Related topics

Artificial Intelligence
Artificial Intelligence Applications
Machine Learning Interpretability
Software Engineering
Software QA and Testing

You may also like