korrents
Aishwarya Naresh Reganti

What Aishwarya Naresh Reganti thinks about prompt injection

@aishwarya-naresh-reganti · 48 positions · On ppll ↗

AI practitioner and researcher who has helped build more than 50 enterprise AI products at companies including OpenAI, Google, Amazon and Databricks; founder of LevelUp Labs and author of over 40 research papers.

Aishwarya Naresh Reganti did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

1 dated position, 2026, in their own words. Our reading of what Aishwarya Naresh Reganti has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

  1. 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.

    ↗2,000+ Hours of Learning Agentic AI System Design in 20 Minutesyoutube.com 7th of 15 in this recording