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 structure of decision models.
- Comparing System One decisions with reasoning LLMs.
- Analyzing the cost and latency profiles of bounded decision tasks.
The Landscape of Open-Weight Decision Models
- Overview of Strands Decider 2B from AWS Labs.
- Introduction to the JEV and GEV open-weight model families.
- Exploring alternatives such as Pplx-Decider, Liquid D1, and Clef.
- Distinguishing between licensing models and deployment requirements.
Architectural Deep Dive: Inside a Decision Model
- Examining the LLM torso without a traditional language modeling head.
- Understanding how the pointer head scores candidate options.
- Tracing the source and derivation of confidence scores.
Practical Application: Running Your First Decisions
- Setting up local environments on CPU and consumer-grade GPUs.
- Structuring effective questions and defining option sets.
- Processing multiple queries in a single inference pass.
- Configuring thresholds and defining fallback behaviors.
Evaluating Decision Quality
- Utilizing JevBench and other decision-specific benchmarks.
- Balancing accuracy against calibration metrics.
- Interpreting Brier scores to assess the reliability of confidence levels.
- Recognizing tasks where decision models are not the appropriate tool.
Requirements
- Familiarity with the fundamentals 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 workflow integration.
- Software developers looking to replace open-ended LLM calls with bounded decision logic.
- Solution and platform architects designing robust agent architectures.
- Technical product managers evaluating decision model options for product strategy.
