“We have some templates and some examples of security review agents in the open source... you can actually incorporate as roles in your harness to then do that end-to-end security review”

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 47:14
47:14

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

What was described

Integrate open-source security review agents (CodeGuard) as roles in an agent harness to perform end-to-end code security reviews

Said nearby on the same subject

“I have my own security agent that reviews the code. And it's like, well, Claude just created the code. But then Claude is now with its security app going, well, that code is insecure.”
GK
George Kurtz CrowdStrike executive
No Priors: Artificial Intelligence | Technology | Startups ·
Automation Share this moment
“We can literally have every single line of code on every commit reviewed by a security expert.”
PM
Peter Mattis
The Pragmatic Engineer ·
Why it worked Share this moment
“We check for security and code reviews are still done by a human... you can generate tests on top of it and additional documentation.”
♫
Said on Me, Myself, and AI
How they work Share this moment
“Agents can be better at structured extraction than humans… if you have a harness where the agent is not only extracting the information but correcting itself, reviewing its outputs, you kind of get to unbalance that in the favor of perfect accuracy”
♫
Said on The a16z Show

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.