
Building your own AI agent in Microsoft 365 Copilot
In this hands-on workshop you build an AI agent in Microsoft 365 Copilot, set up for one of your work tasks. You start by describing your work tasks and, with the help of AI and the trainer, choose one task. You then create the agent, add the information sources it needs and reusable work instructions (Skills), and test the solution. We introduce the features you need as we work through the task. For example, the agent might compile a morning work overview from agreed sources, or draft an email based on a document.
By the end of the course you will have a Copilot agent created and tested for one work task, the data sources it needs and at least one reusable work instruction. The agent carries out the chosen task based on an agreed example and is ready to be used with new input. If the task needs doing every day, you set up a scheduled task in Cowork to do the same work and test it separately. If there is no daily need, you run the agent yourself from then on.
Course structure
Tap a module to see its contents
- The participant describes their main work tasks to AI and answers clarifying questions.
- We compare how often the task recurs, how available the necessary information is and how easily the result can be checked.
- We choose one clearly defined task whose solution can be completed within the day.
- We describe what information the work starts from, what steps need to be taken and what the result should look like.
- We add an example of a good result and specify when the AI must ask for more information or for human confirmation.
- We choose the Microsoft 365 sources the agent needs and the materials available through existing Copilot connectors.
- We check whether the agent finds the right information and whether the participant has the right to use it.
- No new connection to a company system is developed during the workshop.
- We create an agent in Agent Builder for the chosen work task.
- We add its goal, knowledge sources, output requirements and the limits it must work within.
- We specify when the agent must ask for more information or for human confirmation.
- We have the agent work through the task from start to finish with one example.
- As we work, the trainer shows the techniques needed, such as finding information in work files, comparing sources or formatting the result.
- We refine the instructions where the result needs improving.
- We turn the working procedure into one or more work instructions (Skills) and add them to the agent.
- We describe when to use the instruction, which steps to follow and how to handle missing information.
- We test whether the agent uses the instruction with a new example.
- We test the solution with a new example and in a situation where some information is missing.
- We check whether the result meets the agreed requirements and whether the AI stays within the limits of its task.
- We improve the instructions and try again.
- The trainer shows how to create, change and pause a scheduled task in Cowork.
- If the chosen task needs to be done every day, the participant sets up a scheduled task to do the same work.
- We add the work instructions it needs and check access to the data sources; we test the action separately from the agent.
- If there is no daily need, the participant does not schedule their action.
- We write down how to run the solution and check the first results.
Personalised and immediately applicable
The greatest strength of the training was personalisation. Every lesson built on our company's real situations and processes, not textbook examples. The balance of theory and practice and the concrete tips helped us quickly adopt new working methods. The training gave us tools that can be applied immediately, not knowledge that ends up in a drawer.

ENN LAMP
Fiskostar OÜ
CEO
Learning outcomes
What you'll be able to do:
describe your work tasks to the AI and choose one of them for which an AI assistant can be built;
use permitted data connections to give the AI assistant access to the materials needed for the work;
create a Copilot agent in Agent Builder and define its task, the requirements for its output and the limits it must work within;
create a reusable work instruction (Skill) and add it to a Copilot agent;
test the AI assistant with a new example and with missing information, and improve the instructions based on the result;
assess whether daily scheduling is needed and describe how to set up, change and pause a scheduled task.

KAIA SALUMETS
NG Investeeringud OÜ
Chief Accountant
Encouraging and practical
We gained the courage to experiment and to see how to make our work easier. A start has been made and I am very grateful for it. I especially liked the practical examples. At the same time, I understand that consolidating skills and deepening knowledge requires a lot more practice.
Good to know
Before the training
Scope of the training
The workshop produces one Copilot agent that performs a clearly defined work task. We use existing data sources and connections, and set up the agent and its work instructions in plain language. Developing new connectors, complex Copilot Studio workflows, using Code and automating work processes that span several departments require separate training or development work.
Duration and format
Before each stage of the work, the trainer demonstrates the technique needed. The participant applies it straight away to their own task and gets feedback. Over the course of the day, we develop the same solution further step by step.
Six academic hours equal 270 minutes of instruction. Breaks are added on top of this time. The course can be held online or on site; on-site teaching lets the trainer guide participants’ practice more directly. The course is taught in Estonian or English.
Prerequisites
Every participant needs a computer with an internet connection, a Microsoft 365 work or school account and a suitable Microsoft 365 Copilot licence. The organisation must have Agent Builder, adding custom work instructions to agents, Cowork and scheduled tasks enabled. We prepare the required Microsoft 365 data sources, existing data connections and user permissions with the client before the course. Participants bring a list of their main work tasks and sample material suited to their work. We use data permitted in the organisation or sample data.
Do you have any questions?
Anna can help with registration, how the training is organised and applying for the Töötukassa training grant.
Training provider contact and details
- Training organiser
- Tehisintellekt OÜ
- Registry code
- 16967299
- Economic activity notice no.
- 259383
- Contact person
- Anna Borovikova
- Phone
- +372 5886 9046
- info@tehisintellekt.ee