Starts November 13
Build AI agents businesses are willing to pay for
Course AI Agent Engineer
Learn to build AI agents in Python: programs that choose their next step, use tools, and remember their progress. You build one by hand and understand how it works inside.
Private Discord community
19 exercises, tests and a capstone
AMAs and live-coding streams
Lifetime access and updates
CourseStart with the included Python Basics course, which refreshes the language all the course code is written in. Then see how the model answers through the Responses API and build the agent loop with tool calls by hand. Next, give the agent a context packet and memory, hybrid search with citations and honest refusals, tracing and evals with an LLM judge, prompt-injection defenses and writes behind approval. Then teach the agent long tasks, cover multiple agents, MCP and the Agents SDK, take the agent to production and into company processes, and in the capstone assemble the corporate wiki agent in full.
- See what the model receives on every call and build the agent loop by hand on the Responses API
- Describe tools with strict schemas and teach the agent to return errors to the model as data
- Assemble a context packet within a token budget, compress the history and add memory
- Build hybrid search over the wiki and answers with citations that code verifies
- Protect the agent from prompt injection: permissions in code, writes only after approval
- Measure the agent with an eval set, graders and an LLM judge, and set a release gate
- Take the agent to production and into company processes, and assemble it in full in the capstone
AI Agent Engineer
Who this is for
New
Developers who want to see how a controlled agent is built around LLM calls
Pro
Python and backend developers who already call models through APIs and are ready to build their own agent loop
AI engineers who want one coherent approach to context, tools, RAG, memory, safety, traces, and evals
Technical founders and architects who set autonomy boundaries and calculate the cost of a run
Developers who want to understand agent mechanics before adopting an SDK
The manager already has your details
We’ll get back to you shortly.
Have questions?
We’ll reply within 15 minutes
Or contact
Curriculum
12 modules, 19 interactive Python exercises and a capstone. Python is covered by the included Python Basics course. You build the agent loop by hand on the Responses API, look at MCP and the Agents SDK, and finish by taking the agent to production and into company processes.
01
Agent and Workplace
02
The Model Through the API
03
Tools and the Agent Loop
04
Context and Memory
05
Search and Grounding
Show more
Learning Platform
Short lessons, practice, quizzes, and a glossary live on one platform. Sign in with an email link, no password.
- Email Sign-inEnter your email and get a sign-in link; no password. Pick up where you stopped on a computer or a phone.
- Short LessonsLessons are split into small blocks. Complete one in a short session, then resume from the same point later.
- Practice ThroughoutAssignments apply the material right after a lesson. In larger programs, separate outputs build toward a final project or capstone.
- One WorkspaceLessons, quizzes, assignments, and course materials stay together. Technical tasks can use the editor and syntax highlighting.
CommunityYou can complete the course at your own pace. Each of the 20 exercises is Python code in an in-browser editor: project files, checks, three hints, a solution after your attempt and an AI review of your code. You do not need an API key: the model in the exercises is replaced by recorded responses. Module tests also bring back topics from earlier modules. In the capstone, you assemble the corporate wiki agent in full and take it through a ten-case acceptance run plus three cases of your own. You can discuss code and architecture in Discord, which also hosts periodic AMAs and live-coding streams about building agents.
Streams and Community
01
Agent Live Coding
Instructors build agents live, from the first API call to tools, state, and evals.
02
Discord AMAs
Periodic AMAs discuss the stack, architecture decisions, and the practice of building agents.
03
Exercise Discussions
Ask questions about code and compare solutions with other community members.
What You Will Build
The code of 19 exercises and a corporate wiki agent that passes acceptance.
Agent Parts from 19 Exercises
An API adapter, tools and the loop, a context packet and memory, hybrid search, citation checks, an eval with an LLM judge, a write gate, a plan with a critic, a pause for approval, an MCP server, a service with a model gateway and an authority map.
Corporate Wiki Agent
An agent that searches the wiki, answers with citations, refuses without support and writes to the wiki only after approval.
Eval Set and Release Gate
Cases from real failures, graders and an LLM judge that show whether a new version of the agent is better.