LangGraph Helps AppFolio Double Agent Accuracy and Save 10 Hours a Week

Описание и применение

LangGraph улучшил точность решений агентом AppFolio вдвое и сэкономил более 10 часов в неделю, а Uber автоматизировал генерацию тестов без потери состояния.

Задача

AppFolio needed more accurate agent decisions and reduced latency for property managers, while Uber required durable multi-step test generation without state loss.

Результат

AppFolio doubled agent decision accuracy and saved over 10 hours per week; Uber automated unit test generation with stateful resilience.

Рабочий процесс

• 1. Model agent execution as a directed graph with nodes and edges.
• 2. Add deterministic steps (validation, data retrieval) and LLM-driven nodes in the same graph.
• 3. Enable checkpointing after each node to preserve state.
• 4. Integrate LangSmith for tracing, evaluation, and real-time debugging.
• 5. Deploy with a distributed backend (e.g., ScyllaDB) for multi-region durability.
• 6. Use LangGraph Studio for visual debugging and time-travel inspection.

Доказательства

AppFolio doubled agent decision accuracy and saved property managers more than 10 hours a week.

Источник

Uber automated unit test generation without losing context mid-run.

Источник