Give agents clear roles
Decide what each agent in a system is responsible for, so no job falls between two of them.
Partners and press
Overview
An agent that can do anything is a risk. This course teaches how to direct one.
Design and Build Agentic Systems is a free, self-paced 110-minute course, the longest in OpenAI Academy’s API pathway. It covers designing reliable agents: clear roles, controlled tools each may call, and safe handoffs between agents. It ends in an assessment with an 80% pass mark, and OpenAI says its badge is not a certification.
6Modules
10–20Questions
110Minutes
7Roles
What it covers
Learn all the way down.
Learn all the way down.
Perform when it matters.
Control the tools
Limit which tools each agent may call, so a mistake cannot reach further than it should.
Hand off safely
Design how work and context pass from one agent to the next without being lost or distorted.
Keep it predictable
Put these together into a system that behaves the same way in production as it did in testing.
Course outline
Agents with clear jobs,
Agents with clear jobs,
limited tools and safe handoffs.
We design this course ourselves. OpenAI issues the credential, and LUNARTECH is independent of OpenAI.
More autonomy brings more cost and more ways to fail. You learn the test for when a fixed workflow is enough, when one agent serves, and when the job really needs several agents working together.
- Workflows, single agents and multi-agent systems
- What the agent loop does at each turn
- When a fixed sequence is the better choice
- The cost of added autonomy
- Starting simple and adding agents on evidence
You build An architecture decision for a real use case, with the reasoning written out.
Agents that share a job tend to drop it. You define each agent’s responsibility, instructions and success condition, so that every task has one owner and nothing falls between two agents.
- Writing a role as one clear responsibility
- Instructions: goal, rules and output format
- Avoiding overlap and gaps between agents
- Choosing specialists or generalists
- Naming the agent’s success condition
You build A role sheet for each agent in a small system.
Tools are where a mistake becomes an action. You give each agent only the tools its role needs, define each tool tightly, and validate what the agent sends before anything runs.
- Defining tools with clear names and schemas
- Least privilege: only the tools a role needs
- Validating arguments before execution
- Keeping read-only and write tools apart
- Requiring approval for risky actions
- Handling tool errors the agent can act on
You build A tool permission table that maps each agent to the tools it may call.
Work passes from agent to agent, and context can be lost or twisted on the way. You decide what each handoff carries, who decides when to hand off, and how the receiving agent confirms what it got.
- Handoff and manager patterns compared
- Deciding what context travels with the work
- Passing structured data, not loose summaries
- Keeping a path back open
- Stopping loops and ping-pong between agents
- Testing a handoff on its own
You build A handoff design for a three-agent workflow, with its context and failure paths.
A system that works in a demo can still be pushed off course by odd input or a bad tool result. You add checks on input and output, limits on loops and cost, and clear behavior for when something fails.
- Input and output guardrails
- Limits on turns, time and spend
- Resisting instructions hidden in tool results
- Fallbacks and safe stops
- Escalating to a person
You build A guardrail layer, tested against bad inputs and tool failures.
Predictability comes from testing and visibility. You trace what each agent did, run evaluations on whole runs, version your instructions, and compare production behavior with what you saw in testing.
- Tracing every agent step and tool call
- Evaluating whole runs, not just single replies
- Versioning instructions and tool definitions
- Spotting drift between testing and production
- Rolling out changes gradually
You build A traced, evaluated multi-agent system with a record of how it behaves.
Issued by
Certifying body · Independent of LUNARTECH
OpenAI
A certification in early pilot, and free Academy courses across Foundations, Codex and the API. OpenAI says its Academy badges and certificates of completion are not certifications, and don’t guarantee eligibility for one. Availability is still changing, so check OpenAI’s own pages before planning around any of these.
How you get there
Top-tier roles go to people who can do the work.
Top-tier roles go to people who can do the work.
Here’s how you get there.
Know where you start.
API pathway level. Check OpenAI’s official page for what it expects before you begin.
Work through the course.
Six modules, designed by LUNARTECH, at your own pace.
Earn it with OpenAI.
OpenAI issues the credential, so you earn it directly with them.
Support
Support at every stage.
Support at every stage.
You won’t be working through this alone.
Before you start
Try it first.
A 3-day free trial opens a selection of the content. Your card is only charged once it ends.
While you learn
Mentors within reach.
Stuck on a concept? Reach out to a mentor whenever you need help.
While you learn
One-on-one sessions.
On the yearly plan, one-on-one sessions give you dedicated support.
Any time
A team behind you.
Write to info@lunartech.ai at any point, from your trial onwards. If your employer is funding you, we’ll set it up with them directly.
All the way through
A schedule that fits around your life.
Your own paceFrom anywhereAt any hour
After the last lesson
Stay in the network.
Your alumni network stays with you: ongoing support, opportunities and industry insight.
Career support
Career support, past the last lesson. Coaching, a sharper resume, real interview preparation and the people to know.
Career direction
Tailored coaching helps you decide where to aim and how to get there.
Strong portfolio
Hands-on projects become work you can show, not just claim.
Resume and profile
Personalized refinement, so what you send says what you can actually do.
Interview preparation
Preparation for the questions that decide it, so you walk in ready.
Network and search
Connections with industry leaders, and an alumni network that stays with you.
Reviews
Real stories from the community.
LUNARTECH Academy has been the most empowering learning experience of my life, giving me a clear, structured path from the absolute basics to building real-world AI systems with confidence.
Your page is fantastic. As a bachelor’s student in Data Science now accepted for a master’s at UConn, your work has been a real source of motivation.
The programme’s clear, bite-sized content and practical projects dramatically improved my speed from fuzzy idea to MVP and my ability to communicate AI value. I followed the system, and it works.
I really appreciate your teaching style and the way you break down complex topics. It has been incredibly helpful.
After years working mainly with R for econometrics, I found your Python machine learning course a refreshing and engaging way to learn Python.
As a Data Science graduate, I want to thank you for the effort you put into making videos to support growing data scientists.
I’ve been following your work since taking your machine learning course, and I’m impressed by your practical approach to applying AI.
Why choose us
Built around how you actually learn.
One standard behind every course, from the first lesson to long after the last.
Hands-on practice
Apply every idea to real problems, so it becomes something you have used, not only seen.
Industry-aligned curriculum
We keep courses current with the tools, techniques and skills the field asks for.
Flexible learning
Study at your own pace, from anywhere, at any hour.
Certificate of completion
Finish the course and earn a certificate that shows what you have learned.
Focus on your success
Personalized learning plans and support structures carry you through the hard parts.
Lifetime alumni network
Stay connected after you finish, with ongoing support, opportunities and industry insight.
Your certificate
It doesn’t raise its voice. Neither will you.
Finish a LUNARTECH course and its certificate is issued in your name, under our signature. OpenAI’s credential comes from OpenAI.
Certificate of completion
Your Name
Design and Build Agentic Systems course
LUNARTECH RISE Academy
Pricing
This course comes with the membership.
This course comes with the membership.
So does everything else.
One membership opens every course, certification, workshop and masterclass in the Academy. Every plan starts with a 3-day free trial. OpenAI issues the credential.
3 days free, then $29.97 a month. Your card is only charged once the trial ends.
Included in every plan
- Every course in the Academy
- Every certification course
- Workshops and masterclasses
- A certificate of completion
- A 3-day free trial
- Learning at your own pace
- The lifetime alumni network
- Upgrades at any time
In practice
Seven roles.
Seven roles.
One credential across them all.
No single job owns it. Here’s where each role leans hardest, and where its work ends up.
- 01Roles
- 02Tools
- 03Handoffs
-
Agent systems fail where roles overlap. Clear roles and tools prevent that.
Roles, Tools, Handoffs
AI product teams, Enterprise IT
-
A tool an agent can call is a risk surface. Handoffs are where context gets lost.
Tools, Handoffs
Software development, Enterprise IT
-
Multi-agent designs need clear lines of responsibility. Handoffs are the interfaces to get right.
Roles, Handoffs
AI product teams, Enterprise IT
-
Each tool an agent calls is an endpoint with a contract. Handoffs pass state the next agent depends on.
Tools, Handoffs
Software development
-
Controlled tools limit what a misled agent can do. Least privilege applies to agents as it does to users.
Tools
Enterprise IT
-
Agents share infrastructure, queues and credentials. Clear handoffs keep one failure from spreading.
Tools, Handoffs
Enterprise IT
-
Clear roles make an agent system easier to own. You can tell which part failed and who fixes it.
Roles
AI product teams, Software development
- AI product teams
- Software development
- Enterprise IT
AI Engineer
Agent systems fail where roles overlap. Clear roles and tools prevent that.
Over 10,000 students trust LUNARTECH
LUNARTECH gives you the skills
to learn, build, create and lead.
Engineers
Understand systems all the way down. Build the ones others rely on.
Scientists
Understand what the data says. Build models that hold up.
Researchers
Understand the papers. Build on them, and take the work further.
The field
Anyone can use AI.
Anyone can use AI.
Few can engineer it. This is where that starts.
+340%growth in open roles requiring AI skills
Roles and pay
~35,000 open roles right now
Open roles: Built In, Greenhouse, LinkedIn.
Typical salaries: Glassdoor, Levels.fyi, Payscale, Indeed, Ravio, JobRise, U.S. BLS. Military: 2026 U.S. basic pay, drone officers with aviation incentive pay.
Updated November 2026.
FAQ
Frequently asked questions.
Need help? These answers cover most of what people ask before they start.
No. OpenAI issues it. LUNARTECH is independent of OpenAI, and its names and marks belong to it. When you finish a course of ours, you earn a LUNARTECH certificate of completion for that course.
No. We design this course ourselves, around what the credential covers. OpenAI has no part in it, and you still earn the credential directly with OpenAI.
10–20 questions, 110 minutes, online, self-paced. The passing score is 80% on the assessment.
We last reviewed it on 5 November 2026, from excerpts of OpenAI’s official pages, because its site doesn’t accept automated readers. Details change, so check the official page before you book.
Our 3-day free trial gives you access to a selection of content in the bootcamps, courses and materials, so you can experience the value of our content first-hand. This includes comprehensive learning materials and interactive sessions. You won’t be charged during this period, though we require your credit card details at the start to ensure a seamless transition should you choose to continue.
Yes, entering your credit card details is a necessary step to begin your free trial. The process is entirely secure, and we ask for it to provide a seamless transition to a paid subscription if you decide to continue beyond the trial. You will only be charged after the trial period ends, with full access to our content based on the plan you choose.
After your 3-day free trial you gain access to the full breadth of our content, depending on the subscription plan you choose. We offer free trials for our monthly, bi-annual and annual plans, and each plan provides a different scope of access and benefits.
If your employer has agreed to fund your learning, in part or in full, please contact us at info@lunartech.ai. We’ll work with you and your employer to set up everything needed for your subscription.
Yes. Our support remains strong both during your free trial and after you subscribe. Reach the team at info@lunartech.ai with any question, whether you’re onboarding, navigating your trial, or need help as a member. Subscribers to the yearly plan also receive dedicated support in one-on-one sessions.
You can upgrade your plan at any time during your subscription. Downgrading is not available for bi-annual or annual plans, but you can cancel and then choose a new plan that suits you better. For bi-annual and annual plans we also offer payment in instalments; please reach out to learn more.
The course
Build the skills behind Design and Build Agentic Systems.
Learn to design agents that stay predictable in production. Start with a free trial, or enroll in a plan and work through the course at your own pace. OpenAI issues the credential.
LUNARTECH is independent of the vendors and certifying bodies listed here. Their names, exam titles and marks belong to them, exams are run by them, and credentials are issued by them. Reviewed 5 November 2026. Catalogues change often, so confirm the details on the official page before you book.
