• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Reaction

    Four levers to try for agentic app cost and performance

    Sharing notes from OpenAI DevDay, a user recommends prompt caching, reasoning effort, programmatic tool calling and batch requests.

    EL
    1 Source, 2h ago, first seen 2h ago

    TLDR

    A user sharing notes from OpenAI DevDay recommends four starting points for optimizing agentic apps: prompt caching, reasoning effort, programmatic tool calling and batch requests. They advise measuring the results with evals.

    Combined views

    3.1K

    1 Source, first seen 2h ago

    likes

    Combined views

    3.1K

    1 Source, first seen 2h ago

    14 likes
    14
    9 comments
    13 saves
    2 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    9 comments
    13 saves
    2 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @omarsar0Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, these are 4 of the most important levers you absolutely must try: - prompt caching - reasoning effort - programmatic tool calling - batch request The OpenAI dev docs have plenty of information, but these alone are good starting points for optimizing your agentic applications. Familiarize yourself with these and measure them with evals.2h