Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 7 hours
Course Outline
From Text Generation to Typed Decisions
- Understanding what decision models return
- System one decisions compared to reasoning LLMs
- The cost and latency profile of bounded decisions
The Landscape of Open-Weight Decision Models
- AWS Labs’ Strands Decider 2B
- The JEV and GEV open-weight families
- Pplx-Decider, Liquid D1, and Clef
- Differences in licensing and deployment
Inside a Decision Model
- The LLM torso lacking a language modelling head
- The pointer head scoring candidate options
- The origin of the confidence score
Executing Your First Decisions
- Local setup on CPUs and consumer GPUs
- Crafting questions and option sets
- Processing multiple questions in a single pass
- Managing thresholds and fallback behavior
Evaluating Decision Quality
- JevBench and other decision benchmarks
- Accuracy versus calibration
- Brier score and confidence reliability
- Identifying tasks where decision models are not the right tool
Requirements
- Fundamental knowledge of large language models and prompt-based applications.
- Proficiency with command-line interfaces and Python scripting.
- No prior machine learning training experience is required.
Target Audience
- AI engineers assessing decision models for agent workflows.
- Software developers integrating bounded decisions in place of LLM calls.
- Solution and platform architects designing agent architectures.
- Technical product managers evaluating decision model options.
