Using context graphs instead of prompts for complex agent rules
can miss instructions when many complex rules are placed into one long prompt. The problem gets worse when rules depend on each other, apply only under certain conditions, or must happen in a strict order. A restaurant staffing task can include rules such as adding another cook for VIP guests, staying under a weekly budget, assigning leads before support roles, and checking costs after the schedule is built.
Nanonets uses a instead of a flat prompt: rules become nodes, and between rules become edges. The method checks nearby constraints rather than asking the model to handle every rule globally at once. It reportedly scored 45% on Surge AI’s instruction-following benchmark and beat the listed best result.
The approach is still being tested and needs more proof in real .
Key points
- Long prompts can cause models to drop, repeat, or misorder complex rules.
- A represents rules as nodes and rule as edges.
- The approach targets conditional, budget-limited, and step-by-step agent tasks.
- The reported score is 45% on Surge AI’s instruction-following benchmark.
- The main cost lesson is to structure rules before simply adding more prompt text.