Introducing the SOP-driven LLM agent frameworks

Summary

Grab introduces an LLM agent framework that uses Standard Operating Procedures (SOPs) to guide enterprise automation and improve consistency in complex processes. It represents SOPs as trees of action and decision nodes, while a planner uses Depth-First Search, prompt generation, and backtracking to direct an LLM-powered worker agent; context compression and limited APIs are used to address hallucination and efficiency concerns. An SOP editor, plugins for APIs, Python, and SQL, workflows, a GRAG pipeline, playground, multilingual user agent, and state stack extend the framework’s capabilities. Reported evaluations include over 99.8% accuracy, an Account Takeover Investigations bot automating 87% of cases and reducing investigation time from 23 minutes to three, and fraud investigations cutting AHT by 45% and saving over 300 man-hours monthly.

Takeaways

1. 1

   SOPs are represented as trees that support sequential execution and conditional branching, with an editor that lets non-technical users define and visualize workflows.

2. 2

   The planner uses Depth-First Search and backtracking, while the worker agent dynamically updates its understanding; context compression and limiting available APIs are used to mitigate hallucination and improve efficiency.

3. 3

   The reported ATI bot automated 87% of cases and reduced investigation time from 23 minutes to 3, while the fraud investigation use case reduced AHT by 45% and saved over 300 man-hours monthly; both reported a 0 false rate.