NGS-1033-2027-01
Program In Agentic AI and Retrieval
Where and when
- Sat, Jan 9, 2027 — Sun, Jul 18, 2027
- Sat–Sun · 9:00 AM to 12:00 PM
- Virtual (Eastern Time)
- Live online, or onsite in the GTA · source zone America/Toronto
$2,400
Long courses · Live online, or onsite in the GTA
A model that only talks is a demo. The work is a search that can name its page, and an agent that is allowed to act. You build the search in plain code before a framework is allowed in the room. You write one agent by hand before you are allowed a second.

Each date shows the trainer, the session times, and the enrol or waitlist control. Pick London to see GMT or BST on the clock. Refund and transfer terms.
NGS-1033-2027-01
Where and when
$2,400
Price
Program In Agentic AI and Retrieval. For Software engineers. 168 hours. Next open date 9 January 2027 – 18 July 2027, Live online, or onsite in the GTA. 16 seats left. Class $2,400. Practice $3,600. Mentor $4,800.
Prices and the next date were checked on 19 November 2026. A date that has started is not bookable.
Pick a package, then add this course. The price is the package you select. The next date is Jan 9 — Jul 18, 2027.
Class · CAD 2,400 · Jan 9 — Jul 18, 2027
A model that only talks is a demo. If the search cannot name the page, the agent does not get to act. You build the search in plain code before a framework is allowed in the room, and you write one agent by hand before you are allowed a second.
Live weekends for seven months. Saturday and Sunday, three hours each. You keep a score from the first week: did the task finish, did it invent, did the search hit, did the tool work, what did it cost, how slow was it.
You leave with the system you framed in week one, built through the months, and shipped in the last fortnight. The certificate is for finishing this program. It is not a university degree.
Course journey
Eight blocks. The last one ships the system you framed in the first.
Start
Then
Then
Then
Then
Then
Then
Finish
Quick overview
Engineers and technical leads who already write code.
Live, Saturday and Sunday, three hours a day, for 28 weeks.
168 hours in the live room. The work between weekends sits outside that count.
Code you already write. A degree, or a diploma and years of building.
The live weekends, the work between them, and a certificate of completion for this program.
A university degree. Model and cloud accounts.
Why this work, now
A chat window can draft. A company needs a system that can find the right page and then take a next step without inventing the rest. Teams are trying to buy that. The figures below are published estimates. They are not a job, a raise, or a promise from us.
80%
A 2025 Deloitte report said most businesses it surveyed were looking at agents that can carry a multi-step job.
Deloitte
$40B
One market note projects the retrieval market near forty billion dollars by 2035, up from under two billion in 2025. That is their forecast.
Research and Markets
Not a raise
Salary write-ups have claimed higher pay for people who can tie a model to a company's own files. An offer you receive will not match a percentage on a slide.
Published salary notes
The path
01
Search, a longer window, or an agent. You write down which one you refused, and why.
02
Python that waits and logs. A small API. A model call with a price and a timeout.
03
You build the path in plain code. Load, cut, store, find, answer. No framework yet.
04
A hard question, a private detail that must not leak, and a week where you cause the failure.
05
A loop, two tools, a stop, and a test for the way it fails. A library comes after that, not before.
06
You write the reason one agent is not enough. If you cannot, you do not add one.
07
Other software can call in. You can see the path. You can say what a week of use costs.
08
The last fortnight is not a new idea. It is the system you have been building, shipped.
After the program
Kinds of work, not a placement. Finishing the program does not confer a title, a salary, or a seat on a team.
The portfolio
The same system, growing. Not a stack of disconnected demos.
The last fortnight
You scoped it at the start. You added the search, the agent, the stop, and the bill as the months went. At the end you ship that system, and you can defend every part.
You try three ways of asking. You keep the one the score supports, not the one that sounded clever.
Load, cut, store, find, answer. You can point at each step because you wrote it.
It names the page, or it says it does not know. It does not get more confident.
It may look something up and it may calculate. It may not wander, and a person can halt it.
Planner, worker, reviewer, only after you wrote why one agent could not finish the job.
A live source sits behind a server you run. You can say what seven days of calls cost.
How a class runs
A live class. You see the move, you try it on your own work, and you hear what is wrong before you leave.
The instructor shows the idea on one picture before anyone opens a tool.
A roster, a story, a shot, a backlog. Not a case written for a slide.
You try the step while the instructor is still in the room.
You get a correction on your work, in the class. Not a score from a quiz.
What you made is what you use on Monday. The recording is there if you need the hour again.
Why this school
A live class, practice before it counts, and a recording for 90 days. The last two are the reason most people finally book.
The hours on this page are spent in class. This is not a video you are left to finish alone.
You do the work in the room. Where the course leads to an exam, you also sit a timed practice before the real clock.
The live hours are recorded for 90 days. That replay is included. A second live seat is a new booking.
After you enrol, the chapters for this course stay on this site. There is not a second system to learn.
Class, Practice, and Mentor. Practice adds a set you can redo. Mentor adds one private session and a written plan.
Exam courses follow that exam's outline, including the hours you can show on an application. Every other course follows the job in its title.
A film someone can watch. An agent that does one job you already do. A plan you can take into Monday's meeting. Or a practice score that tells you whether to pay for the exam. You leave with a result, not a certificate.
You have already thought about this long enough. The date on this page is the moment you stop postponing it.
Other people are doing the same hard thing, on the same day. You can ask the question you would never type into a video.
On Google
These people wrote about the AI classes. Their words, from Google. Not a promise about your result.
“I learned business analysis, project management, change management, and some uses of AI tools. I joined while I was still an undergraduate.”
Trushil Patel
Google review
“I do not come from a technical background. The AI for business analysts course and AI for Delivery Professionals helped me learn the subject and move toward AI leadership.”
Mohit
Google review
“The AI Transformation for Business Leaders course exceeded what I expected. I already knew generative AI and prompt engineering. I wanted the rollout: stakeholder dynamics, ethical frameworks, and how an AI strategy sits inside platforms such as ERP and CRM.”
Mayur Parekh
Google review
“I could finally tell the roles apart: business analyst, change manager, project manager, product manager, and release train engineer, including how that work meets current AI. I also got one-to-one help with job hunting and interview preparation.”
Krishna Singh
Google review
“I completed AI for Delivery Professionals. I was already a Scrum Master. The course covered generative AI, agentic AI, agents, RAG pipelines, and workflow automation. After it, I built agents that automated backlog creation.”
Preena
Google review
Benefits
What is in the seat. The skills you leave able to use are under Outcomes.
Seven months of live weekends. Six hours in the room, and the work between.
A search you built before a framework was allowed in.
One agent you wrote by hand, and a second worker only if you can justify it.
A score you kept from the first week: hits, inventions, cost, and speed.
A certificate when you finish this program.
What you will be able to do when the course ends. This is not the list of things you take home. That list is Benefits.
You can choose search, a longer window, or an agent, and say which one you refused.
You can build retrieval in plain code, harden it, and then break it on purpose.
You can write one agent loop, name its tools, and test the way it fails.
You can refuse a pile of agents when one would do.
You can watch the system, price a week of calls, and ship it.
Curriculum
Search, a longer window, or an agent. You write down the one you refused.
Python that waits and logs. A small API. A model call with a price and a timeout.
You build the path in plain code before a framework is allowed in the room.
A hard question, a private detail, and a week where you cause the failure.
A loop, two tools, a stop, and a test for the way it fails.
You write the reason one agent is not enough. If you cannot, you do not add one.
Other software can call in. You can see the path. You can say what a week costs.
The last fortnight is the system you have been building, shipped.
Who can attend
You will get the most from this ifSoftware engineers, data engineers, and technical leads who already write code and will own the system.
What to bringYou already write code. A degree, or a diploma and several years of building software. A laptop you can install tools on. The model and cloud accounts are yours.
Instructor
Founder · Lead Trainer
CBAP, PMP, PgMP, PMI-ACP, CSM, CSPO, CSP, Prosci Change Management, SAFe PC
Delivery practitioner who built NGSB so working adults in the GTA could see a clear path into BA, PM and agile roles — without guessing the next step.
With this course
These are the extras mapped to this course. An admin chooses them. Nothing here is tied to the course by name.
168 live hours, the recordings, and the work from class. The seat price is above, not on this card.
A certificate of completion for these hours. It is not the exam credential.
About this instructor and this programme. A person replies.
Every published course, under the school it belongs to.
The programmes people open first on this school.