Loading pattern preview
TemplatesBasics
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
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: OPENAI_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route 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
