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 produced by decision models.
- System one decisions compared to reasoning LLMs.
- The cost and latency characteristics of bounded decisions.
The Ecosystem of Open-Weight Decision Models
- Strands Decider 2B from AWS Labs.
- The JEV and GEV open-weight model families.
- Overview of Pplx-Decider, Liquid D1, and Clef.
- Key differences in licensing and deployment strategies.
Internal Architecture of Decision Models
- Utilizing an LLM torso without a traditional language modeling head.
- Scoring candidate options via the pointer head mechanism.
- Understanding the derivation of confidence scores.
Executing Initial Decisions
- Local setup procedures for CPU and consumer-grade GPUs.
- Effective phrasing of questions and structuring option sets.
- Processing multiple questions within a single inference pass.
- Managing thresholds and defining fallback behaviors.
Assessing Decision Quality
- Reviewing JevBench and other decision-focused benchmarks.
- Balancing accuracy with calibration.
- Interpreting Brier scores and the reliability of confidence metrics.
- Recognizing tasks where a decision model is not the appropriate tool.
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 agent workflows.
- Software developers seeking to replace LLM calls with bounded, structured decisions.
- Solution and platform architects designing agent-based systems.
- Technical product managers evaluating options for decision modeling.
