Claude AI Engineer

Modern software increasingly means calling large language models from your own code, and Claude is among the most capable in production today. In this beginner course you will learn what a large language model actually is, how the Claude model family (Haiku, Sonnet, Opus, and Fable) differs in cost, speed, and capability, and how to make your first calls to Claude from Python. By the end you will be able to call Claude from a Python program, read a token and cost bill, and choose the right model for a task.

You have called Claude from Python now learn to shape its output on purpose. This course teaches the prompt-engineering techniques Anthropic itself recommends: XML tag conventions for structured input and output, few-shot examples that transfer patterns, chain-of-thought scaffolding for reasoning tasks, and prompt caching for real cost and throughput wins. By the end you will be able to write, iterate, and cost-optimize a Claude prompt ready for production.

Learn how to turn Claude from a one-shot chat model into an autonomous agent that reasons about tools, calls them, reads their outputs, and continues toward a goal across many steps. You'll build tool-calling loops from scratch using the Anthropic Messages API tool_use protocol, add multi-step orchestration, wire in production-quality error handling and retries, produce structured JSON outputs safely, and evaluate agent behavior on real tasks. Uses the Anthropic Python SDK inside a PythonAI-container VS Code lab with the Claude API proxy handling authentication for you.

Learn how to ground Claude in your own data using retrieval-augmented generation (RAG). Build vector-search + full-text hybrid pipelines, chunk documents for optimal retrieval, add reranking for precision, and evaluate whether Claude answers are faithful to sources. Uses the Anthropic Python SDK plus lightweight in-process vector search (no external DB required) so students can focus on RAG mechanics rather than infrastructure.

Learn Model Context Protocol (MCP), the open protocol Anthropic developed so Claude clients can discover and call external tools + data sources without custom integrations. Understand the JSON-RPC-over-stdio-or-HTTP shape, the three primitives (tools, resources, prompts), how to connect to existing MCP servers from Python, and how to build a multi-server MCP client. This course is the plumbing story; CLD-AI-106 covers building your own servers.

Ship your own Model Context Protocol servers. Use the official Python `mcp` SDK to build servers that expose tools, resources, and prompts to any MCP-compatible client (Claude Desktop, Claude Code, custom apps). Cover stdio and HTTP transports, packaging + distribution, and testing patterns. Course pairs with CLD-AI-105 (client side) to complete the MCP story.

Design and build systems where multiple Claude agents collaborate. Cover orchestrator-worker patterns, agent handoffs, shared state, parallel agent execution with debate/vote consensus, and specialization (each agent has focused tools + system prompt). Uses the tool_use loop from CLD-AI-103 as the foundation.

Deep dive on producing schema-valid, downstream-ready structured output from Claude. Cover tool_use as JSON forcer (from CLD-AI-102 L7), Pydantic + JSON Schema patterns, extraction pipelines for real-world documents (emails, PDFs, HTML), streaming structured outputs, and error recovery patterns when validation fails.

Build eval harnesses that catch regressions before they ship: test-bank design, LLM-as-judge patterns, tracing + structured logging, cost + latency monitoring, and CI integration for prompt changes.

Process images and PDFs with Claude chart extraction, receipt/invoice OCR, form understanding, multi-page document reasoning, and structured JSON extraction from visual sources. Learn the vision content-block shape, PDF beta, cost/latency tradeoffs, and when to route to Haiku vs Sonnet vs Opus.By the end of this course you will be able to build a document-intelligence pipeline for Orion Analytics that ingests scanned invoices, extracts line-items, validates totals, and hands off structured data to downstream systems.

Ship Claude at production volume. Server-sent event streaming for perceived latency, Message Batches API for 50% cost savings on non-interactive workloads, prompt caching at scale, rate-limit and retry patterns, and end-to-end cost optimization playbooks.By the end of this course you will be able to cut Orion Analytics's daily Claude spend by 40-60% without changing feature scope through routing, caching, batching, and streaming techniques you'll apply directly.