Agentic AI Engineering
Design, build, evaluate, and deploy production-grade AI agents
10 phases. 51 lessons. 51 labs. 3 capstone projects. From LLM APIs through multi-agent systems, MCP, computer use, memory, production infrastructure, and evaluation. You build and ship real agentic systems that qualify for AI engineer roles.
- Lessons: —
- Labs: —
- Projects: —
- Level: Beginner
Curriculum
- LLM Fast Track — LLM APIs (OpenAI, Anthropic, Gemini), prompt engineering fundamentals, function calling, embeddings & semantic search
- Advanced Prompt Engineering for Agents — System prompt architecture, few-shot for tool use, chain-of-thought & ReAct, prompt versioning, adversarial prompting
- Tool Design & Function Calling — Tool schema design, error handling in tool execution, async parallel tool calls, streaming responses, tool safety & validation
- Agentic RAG — Agentic vs standard RAG, chunking strategies, hybrid search & reranking, RAG evaluation, GraphRAG
- Multi-Agent Systems — When to go multi-agent, orchestrator-subagent pattern, communication protocols, parallel execution, swarm patterns, reflection loops
- Model Context Protocol (MCP) — MCP architecture, building MCP servers, resources & prompts, authentication, real-world integrations
- Computer Use & Browser Agents — Computer use API, browser agents with Playwright, reliable GUI interaction, safety in computer use
- Agent Memory Systems — Memory taxonomy, conversation management, external semantic memory, memory consolidation, user profiling
- Production Agent Infrastructure — Async architecture, tracing & observability, cost monitoring, guardrails, fine-tuning for tool use, deployment patterns, incident response
- Agent Evaluation & Observability — Eval frameworks, LLM-as-judge, benchmark design, CI/CD for agents, red teaming
Skills You Will Learn
- Agents
- Multi-Agent
- RAG
- MCP
- Evals
- Production
Related Courses
Browse all courses · View pricing · DeVenture Academy