• Skip to primary navigation
  • Skip to main content
  • Skip to footer
HAMK - Häme University of Applied Sciences

Digipedagogical guidelines

  • Suomi
MENUMENU
  • Home
  • Planning
  • Teaching and guidance
  • Content production
  • Content sharing

AI agents at HAMK


Kuuntele

AI agents at HAMK

bannerikuva, jossa vasemmalla teksti tekoäly ja lamppuikoni. Oikealla lähikuva kädestä, jossa abstrakti tekoälykuvio.

Article sections


    Kuuntele

    An AI agent is an AI application designed for a specific task. It operates based on a predefined role, instructions (prompts), and data sources. Unlike other generative AI applications, such as ChatGPT, an AI agent is not a general-purpose chatbot.

    Use agent, when you want to:

    • reduce the need for repetitive guidance (FAQs, instructions, processes).
    • provide 24/7 support to staff or students.
    • ensure that the answers are based on the agreed-upon sources.

    HAMK staff can create agents using tools approved by the organization, such as Microsoft Copilot and Google Gemini. Agents can be shared via a link with HAMK staff and students.

    How do I create an agent?

    Before creating an agent, it’s a good idea to consider what problem the agent will solve, who it’s intended for, what data sources it will need, who will be responsible for its content and maintenance, and whether it’s a solution for an individual, a team, or the entire organization.

    The exact technical steps for creating an agent depend on the tool used, but generally the process goes like this:

    1. Define the purpose: What does the agent do, and who is it intended for?
    2. Define the scope: What can and cannot an agent do?
    3. Write a basic prompt: define the role, tone, and parameters.
    4. Add data sources: instructions, documents, links.
    5. Test and refine: if necessary, share with other testers and users.

    In addition, be sure to update the agent whenever necessary, as it does not update automatically. Remember to check, for example, that your data sources are up to date.

    Learn more about building agents

    See also Frequently Asked Questions About AI Agents (Educational Technologies Staff – Teams, HAMK Internal)

    • Copilot Chat
      • Instructions: Building the Copilot Chat Agent (University of Tampere)
    • Google Gemini
      • Instructions: Building a Gem Agent for Google Gemini (Google Help Center)
    • Copilot Studio (for more advanced use and the publishing of agents at the organizational level)

    Deepen your knowledge

    If you’d like a deeper understanding of agents, check out these resources, for example:

    • Microsoft Copilot Chat / Agent Builder -learning path
    • Microsoft Copilot Studio sertificate PL-7008
    Last Updated: 1 week ago
    in Artificial Intelligence
    Tags: agent, AI agent, artificial intelligence, Copilot, Google, Google Gemini, microsoft copilot
    Oliko artikkeli hyödyllinen?

    Related Articles

    • How to enhance your work with the help of AI
    • AI — FAQ
    • Examples of Using the Arene Traffic Light Model
    • How to recognize text created with artificial intelligence
    • Generative AI (artificial intelligence)

    Footer

    Häme University of Applied Sciences
    (HAMK) / PO Box 230 13101 Hämeenlinna Finland
    03 6461
    HAMK@HAMK.FI

    Privacy policy
    Cookies
    Takedown request
    Accessibility summary
    Site map

    cc-lisenssi

    This material is CC licensed Attribution-ShareAlike 4.0 International.

    Our site uses cookies to track the use of the site and to develop our service. You may decline or accept these cookies.