finetuning
Prerequisites
Before starting this workflow, verify:
-
A
use_case_spec.mdfile exists- If missing: Activate the
use-case-specificationskill first, then resume - DON'T EVER offer to create a use case spec without activating the use-case-specification skill.
- If missing: Activate the
-
A fine-tuning technique (SFT, DPO, or RLVR) and base model have already been selected
- If missing: Activate the
finetuning-setupskill to collect what's missing, then resume - Don't make recommendations on the spot. You MUST activate the finetuning-setup skill.
- If missing: Activate the
-
A base model name available on SageMakerHub has been identified
- If missing: Activate the
finetuning-setupskill to get it - Important: Only use the model name that
finetuning-setupretrieves, as it may differ from other commonly used names for the same model
- If missing: Activate the
Critical Rules
Code Generation Rules
More from awslabs/agent-plugins
deploy
Deploy applications to AWS. Triggers on phrases like: deploy to AWS, host on AWS, run this on AWS, AWS architecture, estimate AWS cost, generate infrastructure. Analyzes any codebase and deploys to optimal AWS services.
121aws-lambda
Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use deploy-on-aws plugin instead.
114aws-serverless-deployment
AWS SAM and AWS CDK deployment for serverless applications. Triggers on phrases like: use SAM, SAM template, SAM init, SAM deploy, CDK serverless, CDK Lambda construct, NodejsFunction, PythonFunction, SAM and CDK together, serverless CI/CD pipeline. For general app deployment with service selection, use deploy-on-aws plugin instead.
87use-case-specification
Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. Use as the default first step in any model customization plan. Skip only if the user explicitly declines or already has a use case specification to reuse. Captures problem statement, primary users, and LLM-as-a-Judge success tenets.
59amplify-workflow
Build and deploy full-stack web and mobile apps with AWS Amplify Gen2
58planning
Discovers user intent and generates a structured, step-by-step plan for SageMaker AI model customization workflows (fine-tuning, data preparation, evaluation, deployment). Activate when the user's request relates to these areas or when the user asks to modify the current plan. Handles intent discovery, plan generation, plan iteration, and mid-execution plan alterations.
57