Loading pattern preview
PatternsSDK API
AI SDK Prompt Few-Shot Editor
AI SDK Prompt Few-Shot Editor
Create and test prompts with few-shot examples. Evaluate AI responses and tune model performance through experimentation.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Author few-shot prompts with editable input/output examples
- Generate improved example sets with structured AI suggestions
- Test extraction and classification prompts against sample cases
- Step through setup, examples, improvement, and evaluation
Use cases
Products and workflows this pattern is designed to support.
- Few-shot prompt workshops
- Support ticket classifier prompt design
- Structured data extraction prompt tuning
- Teaching example-driven prompting with the AI SDK
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Install from the preview toolbar
Copy the install command above and run it in your project — Pro patterns include a short-lived token.
- 2
Add environment variables to .env.local
OPENAI_API_KEY
- 3
Customize the agent and tool files
Adapt prompts, tools, and stop conditions for your product — Copy for AI in the toolbar helps seed that work.
- 4
Run your dev server and open the pattern route
Install dependencies if needed, then start the app and verify responses.
Environment variables
OPENAI_API_KEYGet key
Files added
4 filesapp/page.tsxapp/layout.tsxapp/actions.tsxlib/rate-limit.ts
Dependencies
19 totalnpm packages
10AISDK@hookform/resolversUpstashlucide-reactNext.jsReactreact-hook-formshikisonnerZod
Registry components
badgebuttoncardformlabelprogressscroll-areasonnertooltip
Critical files
app/actions.tsxCore AI pipeline: uses generateObject and generateText with OpenAI to evaluate few-shot prompts (scoring consistency/relevance/quality) and generate improved examples.
lib/schema.tsDefines Zod schemas that drive the AI structured output: evaluationResultSchema, improvedExamplesSchema, promptFormSchema, and default example sets for extraction/classification/summarization tasks.
Requirements
- Complexity
- Intermediate
- Setup time
- ~15 minutes
