“‘We’re using other models for static analysis because it’s a waste of tokens…’”

Omar Santos · Security & GRC Decoded · The Agents Ran All Weekend. They Came Back With Zero Days. ft. Omar Santos, Distinguished Engineer, AI Security @ Cisco

Play from 30:41
30:41

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

Replaced expensive LLM-based static analysis with cheaper models and deterministic rules generated by AI agents

Said nearby on the same subject

“That same analysis says content with proper schema shows 30 to 40% higher visibility in AI-generated answers. Most website platforms have plugins and free generators exist.”
♫
Said on AI for Small Business
Tool content with proper schema shows 30-40% higher visibility in AI-genera… Share this moment
“You can't load it to general and artificial intelligence that doesn't have sufficient confidentiality restrictions in it”
♫
Said on Bloomberg Law
Why it worked Share this moment
“We use things like risk-based guardrails instead of just static rules. They adjust for things like inflation or market performance and even your spending needs.”
♫
Said on Retire Right Radio
Why it worked Share this moment
“It combines robotics, artificial intelligence, data collection and performance analysis… you can program it up how you want it to be… it tells me how good I am at it”
♫
Said on Tech Talk with Mathew Dickerson
Why it worked Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.