Agents That Write Their Own Tools at Runtime — Sandhya Subramani, AWS

Summary

This talk introduces meta-tooling, a capability where AI agents can write, load, and use their own tools and even create sub-agents at runtime, without needing to be explicitly programmed for every function. Using the open-source Strands Agents SDK, the speaker demonstrates how an agent can dynamically create tools (like a math calculator or character counter) and handle complex tasks, such as planning a multi-stage itinerary. For production use, the talk emphasizes the necessity of robust guardrails, including sandboxed execution, constrained permissions, and comprehensive evaluation (evals) to ensure reliability and prevent undue damage.

Technical details

• Meta-Tooling Implementation 644s

  The Strands Agents SDK enables meta-tooling using a system prompt and three foundational tools: `editor`, `shell`, and `load_tool`. This allows the agent to dynamically generate and utilize custom tools at runtime.

• Agentic Patterns 1103s

  Three primary patterns for multi-agent systems are Swarm (parallel task execution), Graph (sequential dependency), and Handoff/Workflow (combinations of the above).

• Agent Evaluation (Evals)

  Reliability requires evaluating: 1) End goal achievement (Did it book the flight?), 2) Trace level (Was the answer helpful/correct?), 3) Tool access (Was the right tool/parameter used?), and 4) Inter-agent dependency (Was the correct sequence followed?).

• Security and Guardrails

  Essential guardrails include sandboxing the code execution environment, constraining permissions, and maintaining observability to prevent the agent from causing undue damage.

Mentioned resources

• Strands Agents (SDK)
• Strands Agents (GitHub) (Repository)
• Strands Agents tools (Repository)

Channel & topics

• AI Engineer
• AI Agents
• Meta-Tooling
• Generative AI
• Software Engineering
• Self-Healing Systems
• Agentic Workflow
• Strands Agents
• Strands Agents (GitHub)
• Strands Agents tools