![[Qwen Meetup] Function Calling Harness: From 6.75% to 100%](/_next/image?url=https%3A%2F%2Fmedia2.dev.to%2Fdynamic%2Fimage%2Fwidth%3D1200%2Cheight%3D627%2Cfit%3Dcover%2Cgravity%3Dauto%2Cformat%3Dauto%2Fhttps%253A%252F%252Fdev-to-uploads.s3.amazonaws.com%252Fuploads%252Farticles%252Fsu879sgv93l2uxjjbuy5.jpg&w=1200&q=75)
[Qwen Meetup] Function Calling Harness: From 6.75% to 100%
π Qwen Meetup Korea Β· 2026-03-26 Function Calling Harness: From 6.75% to 100% Jeongho Nam Β· Wrtn Technologies π₯ Download Slides (PPTX) TL;DR AutoBe β AI backend auto-generation agent Production-grade backend from natural language conversation 4 AST types + 4-tier compiler validation + self-healing loops Schema specs are the new prompts Typia β The infrastructure that turns 0% into 100% A single type automates schema, parser, validator, and feedback generator Lenient JSON parsing + schema-based type coercion + precise validation feedback Combined with AutoBe to complete harness engineering In Praise of Function Calling Types eliminate ambiguity; schemas constrain through absence Model-neutral, mechanically verifiable, deterministically convergent Applicable to all engineering domains with validators β semiconductors, chemical processes, control systems, etc. Qwen β Why small models are the best QA engineers Smaller models are better at exposing system vulnerabilities R&D cost reduction,
Continue reading on Dev.to
Opens in a new tab




