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
Transitioning from Text Generation to Typed Decisions
- Understanding the output of decision models.
- Distinguishing System One decisions from reasoning LLMs.
- Analyzing the cost and latency profiles of bounded decisions.
The Landscape of Open-Weight Decision Models
- Overview of AWS Labs' Strands Decider 2B.
- Exploration of the JEV and GEV open-weight families.
- Introduction to Pplx-Decider, Liquid D1, and Clef.
- Differences in licensing and deployment requirements.
Architectural Insights
- The use of an LLM torso without a standard language modeling head.
- How the pointer head scores candidate options.
- Origins of the confidence score.
Implementing Your First Decisions
- Local configuration on CPUs and consumer-grade GPUs.
- Formulating questions and defining option sets.
- Processing multiple questions in a single pass.
- Managing thresholds and fallback behaviors.
Evaluating Decision Quality
- Utilizing JevBench and other decision benchmarks.
- Balancing accuracy against calibration.
- Applying the Brier score to assess confidence reliability.
- Recognizing tasks where decision models are ill-suited.
Requirements
- Fundamental knowledge of Large Language Models and prompt-based 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 agentic workflows.
- Software developers looking to substitute open-ended LLM calls with bounded decisions.
- Solution and platform architects structuring agent architectures.
- Technical product managers reviewing decision model capabilities.
