# Build Production AI Applications

AI applications need reliable retrieval, tool use, cost controls, and monitoring to work in production. This skill provides patterns and templates for RAG, agents, vector databases, streaming, and observability.

## Install

```bash
npx skillstore add ai agent hub/ariegoldkin-ai-native-development
```

## Metadata

- - Slug: ariegoldkin-ai-native-development
- - Version: 1.0.0
- - Author: AI Agent Hub
- - GitHub username: ArieGoldkin
- - License: MIT
- - Repository: https://github.com/ArieGoldkin/ai-agent-hub/tree/main/skills/ai-native-development
- - Ref: main
- - Supported tools: Claude, Codex, Claude Code
- - Risk level: medium
- - Risk factors: scripts, network, filesystem, env\_access, external\_commands
- - Quality score: 50
- - Quality tier: warning
- - Public page: https://skillstore.pages.dev/skills/ariegoldkin-ai-native-development
- - Manifest: https://skillstore.pages.dev/api/skills/ariegoldkin-ai-native-development/manifest

## Capabilities

- Explains RAG architecture, document chunking, retrieval, citations, and answer validation patterns.
- Provides TypeScript templates for RAG pipelines and agentic workflows.
- Covers vector database setup patterns for Pinecone, Chroma, Weaviate, and Qdrant.
- Describes OpenAI and Anthropic function calling loops, tool schemas, and streaming tool use.
- Includes observability, token tracking, cost monitoring, and evaluation guidance.
- Supplies an implementation checklist for AI application readiness reviews.

## Use Cases

- Launch a support knowledge assistant: Design a RAG chatbot with citations, retrieval validation, streaming responses, and cost tracking.
- Add tool use to an AI workflow: Structure function schemas, agent loops, tool execution, and error handling for controlled automation.
- Review AI production readiness: Use the checklist to evaluate monitoring, prompt quality, retrieval quality, security, and operating costs.

## Prompt Templates

### Plan a Basic RAG App

```
Use the AI-native development skill to outline a simple RAG application for my documents. Include chunking, vector storage, retrieval, answer generation, and citations.
```

### Choose a Vector Database

```
Compare Pinecone, Chroma, Weaviate, and Qdrant for my use case. Consider scale, hosting, filtering, latency, operations, and cost.
```

### Design Safe Tool Calling

```
Design a function calling workflow for this task. Include tool schemas, validation, authorization checks, error handling, and confirmation for side effects.
```

### Audit an AI System Architecture

```
Review my AI application architecture for retrieval quality, prompt injection risk, observability, token cost, latency, model fallback, and deployment readiness.
```

## Limitations

- Some code is illustrative and needs hardening before production use.
- The skill does not provision cloud services or vector databases automatically.
- Model names and vendor APIs may need updates as providers change versions.
- Security controls such as authorization and secret rotation remain the implementer responsibility.

## Best Practices

- Treat retrieved documents and tool outputs as untrusted context in prompts.
- Require validation, authorization, and logging before executing model-selected tools.
- Track retrieval quality, answer quality, latency, and token cost from the first prototype.

## Anti Patterns

- Copying example agent tools into production without permission checks.
- Using eval or unrestricted interpreters for calculator or automation tools.
- Sending secrets, private records, or raw debug prompts into model context.

## Security Audit

- - Safe to publish: true
- - Audited at: 2026-06-28T10:29:20.761\+00:00
- - Summary: Static analysis reported many high-risk patterns, but most are false positives from Markdown code fences, template strings, API documentation links, and normal SDK environment-variable configuration. No prompt injection attempt, malicious exfiltration, or hidden command execution intent was found. The main residual risk is unsafe copy-paste sample code, especially an eval-based calculator tool and broad autonomous-agent tool templates.

## Stats

- - Views: 240
- - Downloads: 5
- - Favorites: 1
- - Popularity score: 0