Agents That Forge Their Own Tools: Self-Modifying AI in the Wild
Sandhya Subramani
- When
- Thursday, July 212:05 PM – 12:25 PM · 20 min
- Where
- Expo Stage 4 SESan Francisco, CA · imported from ai.engineer's public schedule feed
About this session
What happens when your agent decides its existing tools aren't good enough and writes new ones? Self-modifying agents can generate, test, and deploy their own tool implementations at runtime, adapting to problems they weren't explicitly programmed to solve. In this session, we'll demo a live agent that forges its own tools on the fly, discuss the safety boundaries you need, and explore where this pattern makes sense (and where it absolutely doesn't).
Speaker
Senior Developer Advocate, GenAI, Amazon Web Services
Sandhya Subramani is a Sr. Developer Advocate at AWS with 8+ years of experience in Applied AI Research, specializing in Large Language Models and agentic AI systems. She has developed and deployed AI solutions at organizations including Amazon, Warner Bros, and Fidelity Investments.
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.