Finale
Portfolio Projects and Career
Five capstone projects pull the whole course together: a ChatGPT-style assistant, a chat-with-any-document app, a Perplexity-style search engine, a Lovable-style app builder and a fair, human-reviewed AI interviewer. Three closing lessons then show you how to choose AI problems worth solving, present your work so it gets you hired, and keep learning in a field that never slows down.
By the end of this module you can
- combine chat, retrieval, tools and memory into one deployed assistant with measured cost and quality
- build grounded systems that cite sources, verify their own quotes and abstain when the evidence is missing
- design multi-agent pipelines that run generated code safely in a sandbox and fix their own errors
- build AI systems that affect people with consent, rubrics, bias testing and human review designed in from the start
- judge which AI features are worth building using the mistake grid, cost per task and a success metric
- present your projects, answer AI engineering interview questions and evaluate new models on your own golden set
Lessons
8 in this module- 01Project: ChatGPT-style chatbot platformBuild and ship a ChatGPT-style assistant with a streaming Streamlit UI, saved conversations, rolling summaries, a ChromaDB knowledge base, web search and long-term memory of each user.
- 02Project: Chat with any documentBuild a ChatPDF-style app where every answer cites its page, every quote is verified against the source by code, tables and scans carry honest caveats, and the app says "not in this document" instead of guessing.
- 03Project: AI search engine like PerplexityBuild a conversational search engine that plans its own searches, reads real pages, ranks passages with hybrid search and a reranker, streams answers with inline citations and measures its own faithfulness.
- 04Project: AI web app builder like LovableBuild a prompt-to-app system where planner, coder and reviewer agents ship a working React app, with an offline Docker sandbox, a safe file-system layer, automatic error feedback and a live preview you refine by chatting.
- 05Project: AI interviewer like MercorBuild a voice-based structured interviewer with consent first, rubric scoring in Pydantic backed by verified quotes, consistency checks, counterfactual bias tests and a hiring report where a human always makes the decision.
- 06AI product thinkingChoose AI features worth building by placing them on the mistake grid, designing for wrong answers and perceived latency, computing cost per task and defining a success metric before you write code.
- 07Portfolio, resume and interviewsPresent your projects so a reviewer sees your judgement in ninety seconds, write resume bullets with defensible numbers, and handle AI engineering interviews from fundamentals to system design and STAR stories.
- 08Staying current without drowningKeep up with a fast field by separating lasting ideas from fast-changing details, testing every new model or tool on your own golden dataset, spotting hype, and keeping a small weekly habit you can sustain for years.