Your Agent Evolved. Your Evals Didn't.

Official Schedule Context

Knowing which generation your agent is in, which failure modes your current evals are blind to, and

what to build next is the difference between shipping with confidence and flying blind. Agent

architectures have evolved through six generations; prompt, chain, ReAct loop, workflow graph,

modern agent loop, AI harness. And each one quietly breaks the eval strategy of the generation

before it. A prompt-quality rubric won't catch a bad tool call; a trace scorer won't catch memory

poisoning. Using a single SRE incident response agent threaded through every generation, this talk

shows exactly where each architecture outgrows its evals and what you need to close the gap.

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

Pending transcript synthesis when an official recording or confirmed matching video is available.