“We have done internally... expose traditional machine learning algorithms and models as tools to an LLM... you can have your Python script for a machine learning algorithm and then invoke that”

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 51:22
51:22

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

What was described

Expose traditional machine-learning models as callable tools for LLM agents, using Python scripts stored in the agent’s scripts folder

Said nearby on the same subject

“Claude downloaded every single model, every single tool we use, FFmpeg, all the Python scripts that it's using to do all the editing”
♫
Said on YouTube Creators Hub
Automation Share this moment
“‘You have a hook… you can bring a Python script in your agent skill that will always be invoked if you want to do math.’”
OS
Omar Santos
Security & GRC Decoded ·
How they work Share this moment
“The agent has access to a tool for reading a file, another for searching the code base, another for running tests. Those tools are exposed to the model, along with information describing what they can do and how they can be used.”
SP
Sowjanya Pandruju
Software Engineering Radio - the podcast for professional software developers ·
“We build a lot of tooling just to mask all that data before it gets exposed to the agent”
♫
Said on Founder Mode
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.