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
- The nature of outputs returned by decision models.
- Distinguishing System one decisions from reasoning LLMs.
- The cost and latency characteristics of bounded decisions.
The Open-Weight Decision Model Ecosystem
- AWS Labs' Strands Decider 2B.
- The JEV and GEV open-weight model families.
- Other models such as Pplx-Decider, Liquid D1, and Clef.
- Differences in licensing and deployment requirements.
Architectural Deep Dive into Decision Models
- Utilizing an LLM torso without a standard language modelling head.
- Implementing a pointer head to score candidate options.
- The source of confidence scores in decision outputs.
Executing Your First Decisions
- Setting up local environments on CPUs and consumer-grade GPUs.
- Formulating effective questions and option sets.
- Processing multiple queries in a single pass.
- Configuring thresholds and defining fallback behaviors.
Evaluating Decision Quality
- Reviewing JevBench and other decision-specific benchmarks.
- Balancing accuracy against calibration.
- Understanding the Brier score and the reliability of confidence metrics.
- Recognizing scenarios where decision models are ill-suited for the task.
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 necessary.
Target Audience
- AI engineers assessing decision models for agent workflows.
- Software developers integrating bounded decisions in place of general LLM calls.
- Solution and platform architects designing robust agent architectures.
- Technical product managers evaluating the viability of decision model options.
