korrents

Our readingWhat is a korrent?

User messages, retrieved documents and tool outputs should be treated as untrusted data, and instructions found in them should not simply be executed.

Drawn from what Aishwarya Naresh Reganti said

What these subjects mean

prompt injection Getting an agent to follow instructions it found instead of the ones it was given.

AI agents Agents beyond the editor: software that acts on your behalf, and what independence it should be given.

What Aishwarya Naresh Reganti actually said

  1. Aishwarya Naresh Reganti AI practitioner and researcher who has helped build more…
    Now, user messages, retrieve documents, and tool outputs should all be treated as untrusted data. For instance, just because your system sees an instruction inside a document, it shouldn't just go and execute it, especially once the agent has access to private data and tools that can take actions.

    Watch from 8:17 plays here

    ↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com

    22 Oct 2026 · video · 20m · spoken · machine transcript

    All 15 korrents from this recordingthis one is 7th

Added to korrents 9 Nov 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map