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
- The output structure of a decision model.
- Contrasting system one decisions with reasoning LLMs.
- Cost and latency characteristics of bounded decisions.
The Open-Weight Decision Model Landscape
- Strands Decider 2B from AWS Labs.
- JEV and GEV open-weight model families.
- Pplx-Decider, Liquid D1, and Clef.
- Differences in licensing and deployment strategies.
Inside a Decision Model
- The LLM torso architecture minus the language modelling head.
- Pointer head scoring across candidate options.
- The origin of the confidence score.
Running Your First Decisions
- Local setup on CPUs and consumer-grade GPUs.
- Formulating questions and option sets effectively.
- Processing multiple questions in a single pass.
- Configuring thresholds and fallback behaviours.
Judging Decision Quality
- JevBench and other decision benchmarks.
- Balancing accuracy against calibration.
- Using the Brier score to gauge confidence reliability.
- Identifying tasks where a decision model is unsuitable.
Requirements
- Fundamental understanding of large language models and prompt-based applications.
- Proficiency with command-line interfaces and Python scripting.
- No prior experience in machine learning training is required.
Target Audience
- AI engineers assessing decision models for agent workflows.
- Software developers looking to substitute LLM calls with bounded decisions.
- Solution and platform architects designing agent architectures.
- Technical product managers evaluating decision model options.
