AI Engineering Tutorial · Quality and Production · Lesson 25 of 25
Where to Go Next
Courses, tutorials and practice to go deeper into AI engineering.
You've covered
- Tokens, context windows, messages, API calls, parameters and streaming
- Clear prompts, examples, structured output and templates
- Tool calling, agent loops, MCP and retries
- Embeddings, chunking, vector search and a minimal RAG pipeline
- Evaluations, guardrails, cost, caching and logging
Keep going
- Courses: Integrating LLM APIs, AI Agents and MCP in Production, RAG in Production, LLM Evals and Guardrails and Coding with AI Assistants.
- Guides: compare agent frameworks and vector databases in the decision guides.
- Interviews: Native AI Engineering, RAG, Agents and MCP questions in Interview Q&A.
plan = {"week 1": "build a tool-calling assistant with validation and logging",
"week 2": "add retrieval over your own docs with citations",
"week 3": "write a 50-case eval set and compare two prompts",
"week 4": "add guardrails, cost tracking and an MCP server for one tool"}
for week, goal in plan.items():
print(f"{week}: {goal}")
Output
week 1: build a tool-calling assistant with validation and logging week 2: add retrieval over your own docs with citations week 3: write a 50-case eval set and compare two prompts week 4: add guardrails, cost tracking and an MCP server for one tool