Speaker
Description
Agentic AI systems can plan actions, call tools, analyse logs, and trigger real automation. While this enables powerful operational workflows, it also introduces serious risks: hallucinated decisions, loss of control, escalating costs, and unclear accountability. This presentation introduces Saz, a self-hosted agentic workflow engine designed to embed AI into operational environments through structured workflows, human-authored instructions, strict policy enforcement, and a dual-agent safety model where a verifier agent evaluates the planner agent’s output before execution. The session presents practical patterns for adopting AI-driven workflows that remain controlled, auditable, and firmly human-governed.
What will the TNC audience take away from your talk?
This presentation targets engineers, architects, automation specialists, SREs, and technical leaders exploring the use of AI in operational workflows. It is suitable for audiences familiar with infrastructure automation and service orchestration but does not require prior AI expertise.
The session will run for 25 minutes and include architectural explanations and concrete workflow examples. The focus is on transferable design patterns, risk mitigation strategies, and governance models rather than vendor-specific technologies.
| Are you a first time speaker at TNC? | Yes |
|---|
