Claude AI Engineer
Software engineers and backend developers who want to build with Claude — from first API call through production agents
Completion Badge
Comfort reading and writing Python. Basic familiarity with REST APIs and JSON. No prior LLM experience required.
AI Engineering Foundations with Claude Coming Soon
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.
Prompt Engineering with Claude Coming Soon
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.
Evaluations and Observability for Claude Apps
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.
Claude Vision and PDF processing
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.
Streaming, batching, and cost optimization at scale
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.
Production Claude Application Capstone
Ship a production Claude application. Environment config, observability, safety layers, deployment patterns (canary, feature flags), incident response runbooks, and the final end-to-end Orion assistant capstone that brings together every technique from CLD-AI-101 through CLD-AI-111.By the end of this course you will have built, deployed, and instrumented a production-grade Claude application for Orion Analytics one you can point at as your portfolio piece and reference architecture.