Skip to content
Hacker News · AI·· 2 h agoAI score58

PacketSnitch builds a small AI tool router on Qwen2.5 models with documentation lookup

Teaching PacketSnitch to Use Its Own Documentation: Build a Small AI Tool Router

AI summary

PacketSnitch developer describes building a natural-language tool router that uses the app's own pregenerated documentation index instead of loading every function into the prompt. A 0.5B Qwen2.5-Instruct model handles straightforward intents, while application logic escalates complex or invalid outputs to a 1.5B model, and the author reports roughly $40 in training compute and a 153ms response on one test case.

Source:Hacker News · AI · packetsnitch.com