Sakhanda Wire
NVDA $153.75 -1.53% MSFT $506.06 -2.30% GOOGL $279.99 -1.31% META $621.17 -0.84% AMZN $257.88 +0.05%
← Back to the news

New decision models aim to automate actions by AI agents

Cloudflare has released Clef and Clef-flash, two decision models designed for AI agents. Instead of generating extended text, they assess an input against predefined answer choices and return probabilities. Software can use those results to route support tickets, start an escalation, or transfer a case to a person.

Cloudflare reports median response times of about 39 milliseconds for Clef-flash and 209 milliseconds for Clef, compared with just over 524 milliseconds for TypeSafe AI’s Jev, across the company’s benchmarks. Both models support text and images, run on Workers AI, and are available on Hugging Face under the Apache-2.0 license. Clef has a 64,000-token context window.

Clef is based on Qwen3.8-27B and Clef-flash on Qwen3.5-9B. Cloudflare trained additional components with synthetic data and a variant of Reinforcement Learning for Calibrated Decisions, while leaving the base models unchanged. Customers can initially work with Cloudflare engineers to fine-tune the systems; a self-service option is planned. The company is also testing Clef for website classification and plans to use the models for abuse reports, support requests, and bot assessment.

Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.

Originally published by The Decoder on

Read the original on The Decoder ↗

The reporting and the image belong to The Decoder and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news