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
- What a decision model returns
- System one decisions versus reasoning LLMs
- Cost and latency profile of bounded decisions
The Open-Weight Decision Model Landscape
- Strands Decider 2B from AWS Labs
- JEV and GEV open-weight families
- Pplx-Decider, Liquid D1 and Clef
- Licence and deployment differences
Inside a Decision Model
- LLM torso without a language modelling head
- Pointer head scoring over candidate options
- Where the confidence score comes from
Running Your First Decisions
- Local setup on CPU and consumer GPU
- Phrasing questions and option sets
- Asking several questions in one pass
- Thresholds and fallback behaviour
Judging Decision Quality
- JevBench and decision benchmarks
- Accuracy versus calibration
- Brier score and reliability of confidence
- Tasks where a decision model is the wrong tool
Requirements
- A foundational understanding of large language models and prompt-driven applications.
- Proficiency with command-line interfaces and Python scripting.
- No prior experience in machine learning training is necessary.
Target Audience
- AI engineers assessing decision models for agent-based workflows.
- Software developers looking to replace broad LLM calls with bounded decision logic.
- Solution and platform architects crafting agent system architectures.
- Technical product managers evaluating various decision model capabilities.
