Try before you buy
Download free samples to see the quality, structure, and depth before you commit.
Available previews
OpenAI to Anthropic Migration Kit
A concept map + tested neutral adapter for migrating between (or supporting both) the OpenAI and Anthropic APIs: system prompts, required max_tokens, tool calling, stop reasons, streaming.
Prompt-Injection Defense Kit
Layered, tested defenses against prompt injection for LLM apps and agents: input isolation, a heuristic injection detector, an action gate, and 16+ attack tests proving what each layer stops.
MCP Server Conformance Test Kit
A black-box conformance suite for remote MCP (Streamable HTTP) servers: verifies initialize, tools/list schema validity, tools/call contracts, and error handling. CI-ready, self-tested.
RAG Pipeline Framework
Complete retrieval-augmented generation pipeline with document ingestion, chunking strategies, vector store integration, and evaluation.
LLM Prompt Engineering Kit
Prompt template library, chain-of-thought patterns, few-shot examples, prompt versioning system, and A/B testing framework.
AI Agent Framework
Multi-agent orchestration system with tool calling, memory management, planning loops, and human-in-the-loop patterns.
Vector Database Toolkit
Setup guides for Pinecone, Weaviate, ChromaDB, and pgvector with indexing strategies, hybrid search, and benchmarking scripts.
LLM Evaluation Framework
Automated evaluation harnesses, custom metrics, human feedback collection, regression testing, and quality monitoring dashboards.
Fine-Tuning Pipeline
LoRA/QLoRA fine-tuning scripts, dataset preparation tools, training monitoring, model merging, and deployment automation.
AI Safety & Guardrails Kit
Input/output filtering, toxicity detection, PII redaction, hallucination detection, and content policy enforcement scripts.
LLM Cost Optimizer
Token usage tracking, model routing for cost/quality tradeoffs, caching strategies, batch processing, and budget alerting.
Conversational AI Templates
Chatbot frameworks with context management, multi-turn conversation handling, intent classification, and escalation workflows.
Document AI Toolkit
PDF/document parsing pipelines, OCR integration, table extraction, summarization chains, and structured data extraction.
AI API Gateway
Unified API for multiple LLM providers, rate limiting, fallback routing, response caching, and usage analytics dashboard.
MCP Server Starter
Production-shaped remote MCP server starter — Streamable HTTP on Cloudflare Workers, stateless + stateful patterns, typed tools, discovery, rate limiting, and Vitest tests.
Agent Commerce Integration Pack
Add safe commerce to an MCP server or agent API: trusted catalogue reads and server-side price resolution with price-tampering and unaudited-product guards. Buyer authorizes payment; no autonomous charging.
Agent Tool Schema Design Patterns
Field guide and runnable examples for designing reliable tool/function schemas for LLM agents (MCP, OpenAI, Anthropic): descriptions, constraints, flat inputs, error contracts, annotations, and idempotency.
MCP / Agent Server Security Checklist
Audit-ready security checklists and a STRIDE threat model for remote MCP servers and agent-facing APIs: auth, input validation, rate limiting, secrets, payments, and data-exposure controls.
Agent Tool Eval Harness
Dependency-light evaluation harness for agent tools and MCP servers: golden cases, matchers, a runner with latency metrics, and console + JSON reporters for CI regression gating.
Agent Discoverability Kit
Generators that make a product or site discoverable to AI agents: llms.txt, .well-known/ai-plugin.json, an MCP-registry server.json, and valid schema.org Product JSON-LD.
Why download samples?
See the quality
Get a real look at the content structure, depth, and quality before purchasing.
No strings attached
No email required, no signup, no tracking. Just download and evaluate.
Make informed decisions
Ensure the product fits your needs and skill level before buying.
Risk-free exploration
30-day guarantee — but samples let you decide with confidence first.