Cisco AI has developed FAPO, an open-source system designed to autonomously optimize multi-step LLM pipelines. FAPO uses Claude Code to evaluate, classify failures, propose variants, and iterate on prompts to achieve target accuracy. In evaluations, FAPO outperformed the state-of-the-art prompt optimizer GEPA on most benchmarks, demonstrating significant gains, especially when structural pipeline changes were involved. AI
IMPACT This tool could streamline the development and deployment of LLM applications by automating prompt optimization and failure analysis.
RANK_REASON This is a new tool/framework release from a company, not a frontier model release from a major AI lab.
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
