Usage
Pre-LLM¶
For immediately before the prompt is sent to the model
Pre-tool¶
For immediately before a tool is invoked by an agent
️💡 Refraction
Validate and repair tool call sequences using classical AI planning ️⚡️ SPARC
Evaluate the static and semantic elements tool calls before execution
Validate and repair tool call sequences using classical AI planning ️⚡️ SPARC
Evaluate the static and semantic elements tool calls before execution
Post-tool¶
For immediately after a tool response is received
📚 JSON Processor
Dynamically extract data from large and complex JSON objects 📄🛠️ RAG Repair
Use domain documentation to repair tool call errors ️💬 Silent Review
Useful for correcting tool calls where errors are not explicit in the response
Dynamically extract data from large and complex JSON objects 📄🛠️ RAG Repair
Use domain documentation to repair tool call errors ️💬 Silent Review
Useful for correcting tool calls where errors are not explicit in the response
Pre-response¶
For immediately before the agent returns a response to the user