Creative track
AI Creator
Images, cinematic videos, digital characters, and campaigns. Turn your ideas into a creative portfolio.
Explore modulesMake extraordinary visuals. Build intelligent applications. Take your work into production.
03 courses. Real projects.
Creative track
Images, cinematic videos, digital characters, and campaigns. Turn your ideas into a creative portfolio.
Explore modules
Engineering · Part 1
Build a voice AI agent on your laptop, from your first streaming response to grounded answers and safe tools.
Explore modules
Engineering · Part 2
Deploy your agent on AWS or Azure. Add secure business tools, knowledge graphs, monitoring, and recovery.
Explore modulesFrom your first prompt to a complete creative portfolio. The same curriculum, projects, and bonus modules featured on our homepage.
Explore the full AI Creator experienceAssignment: Complete all preparations for the course.
Assignment: Generate an AI moodboard for your niche with 15–30 images. Portfolio project 1.
Assignment: Generate a campaign shoot with real objects and a character. Portfolio project 2.
Assignment: Create a dynamic video for an advertising campaign. Portfolio project 3.
Assignment: Create a character-based photo/video case study. Portfolio project 4.
Assignment: Create your digital avatar and record a short video of up to 15 seconds. Create a lip-sync video or song with a generated character. Portfolio project 5.
Assignment: Create a video for a brand. Portfolio project 6.
Assignment: Create your final course video. Portfolio project 7.
Assignment: Set up your profile and publish your first 10 social media posts.
Assignment: Create a portfolio from your case studies and find your first orders. Portfolio 1.
Build a voice AI agent entirely on your laptop with Python and Docker Compose. Learn LLMs, voice, retrieval, tools, evaluation, safety, and human handoff.
Before you start: read basic Python and use a terminal. No cloud account needed. Model API usage is separate from tuition.
Friday How an LLM produces an answer
Saturday Build a testable LLM service
Sunday Test it, add CI, and demo
Friday How a voice AI turn works
Saturday First voice turn
Sunday Measure, test, and demo the voice turn
Friday Design knowledge you can search and measure
Saturday Build the knowledge base
Sunday Measure retrieval, test, and demo
Friday From search results to a grounded answer
Saturday Grounded answers in text and voice
Sunday Source cards, the golden set, and demo
Friday How an agent decides what to do
Saturday Tools and combined answers
Sunday Route safely, test, and demo
Friday Measure honestly and think like an attacker
Saturday Build the evaluation
Sunday Attack your own agent, and demo
Friday Bring a person into the loop, and ship safely
Saturday Hand off to a person
Sunday Ship it
A 10-minute local demo from a clean clone, a tested GitHub repository, published Docker images, and a two-page README report. Build the foundation for the Production & LLMOps course.
Take an AI application from your laptop to an operated cloud system. Build around a real order-support case with retrieval, authorized tools, voice, and recall investigations.
Before you start: complete Foundations or pass a short entry check in Python, Git, and Docker. Choose one AWS or Azure account. Model and cloud usage are separate from tuition.
Trace the buyer’s damaged-order and recall question, map where private data lives, and make the first application boot from a clean clone.
Friday Map the buyer journey, system boundaries, failure cases, and AWS or Azure path.
Saturday Build the Python API and browser page; run Docker Compose, a health test, CI, and a Terraform plan.
A reviewer can boot the stack, see the passing GitHub Actions check, and inspect the infrastructure plan.
Learn tokens, inference, context, prompting, latency, usage, and why a model can sound certain without knowing a fact.
Friday Compare model responses with and without evidence; define when the app should answer or abstain.
Saturday Stream a server-side model response, test timeout behavior, publish a versioned image, and deploy it.
Show a streamed answer, a graceful failure, a passing CI run, and a rollback to an earlier image.
Learn how documents become chunks and vectors, and why a close match is a candidate source rather than proof.
Friday Compare keyword, vector, and hybrid retrieval; define expected sources for ten test questions.
Saturday Ingest versioned documents, build a search view, test access filters, and update the cloud stack.
Find an exact passage and its version, then rebuild a deleted search index from the source documents.
Connect the reviewed Week 3 index to an agent decision path. A spoken question can retrieve policy and produce a short sourced answer.
Friday Add a browser audio room, short-lived access token, agent participant, transcription, and speech output.
Saturday Add the policy search tool, source cards, refusal and handoff logic, and a golden question set.
Demonstrate a cited policy answer and an unsupported question that produces an honest abstention.
Combine live order facts with approved policy while keeping one organization’s records invisible to another.
Friday Create Postgres tables and migrations; bind the signed-in buyer to read-only order lookup.
Saturday Route order and policy questions, draft a support case after confirmation, and hand uncertain cases to staff.
Show a valid order answer, a denied cross-organization lookup, an evaluation result, and a human handoff.
When a supplier recalls a lot, identify affected customer orders and show the exact shipment path. Learn to model relationships, query the graph, check data freshness, and protect each buyer’s records.
Friday Model supplier, lot, shipment, product, and order relationships in a knowledge graph.
Saturday Add a permission-checked recall tool and combine graph facts with approved recall policy.
Trace a seeded lot to affected orders and explain what happens if the graph is stale or unavailable.
Find why an answer is slow or wrong, then demonstrate that another engineer can operate the complete system.
Friday Follow one request through transcription, routing, retrieval, databases, model response, and speech.
Saturday Deploy pinned images, trigger an alert, restore a backup, rebuild derived data, and rerun the tests.
Show the live app, a trace, a dashboard, a safe failure path, and a completed restore runbook.
A working repository, cloud deployment, evaluation report, monitoring dashboard, and operating guide. Demonstrate sourced answers, safe order lookup, recall tracing, and recovery from failure.
Engineering cohorts meet Friday through Sunday, with 8–10 hours of total work per week. Foundations runs first, followed by Production & LLMOps. Next cohort dates will be announced soon. Payment agreements are available; ask about terms before enrolling.