Back to Blog

    Agentic AI

    Eight practices for better prompts at work

    A clear task, bounded context, examples and criteria: eight practices for better prompts, and how to compare prompt versions with test cases.

    January 19, 20261 min read
    Patrick Trapp

    Patrick Trapp

    Solution Architect

    patrick.trapp@cnext.ch
    CNEXT
    In this article

    A good prompt describes the task and the output you want. The practices below are starting points; a comparison on recurring examples shows whether they work for your tasks.

    Eight practices

    1. 1Name the task: Say what should be created, compared or extracted.
    2. 2Bound the context: State the relevant audience, purpose and approved sources. Avoid unnecessary confidential data.
    3. 3Describe the output: Specify language, length, structure and fields where they matter.
    4. 4Give examples: A short example can clarify format or tone. Check whether it also introduces unwanted patterns.
    5. 5Name the criteria: Explain how to recognise a useful answer, for example completeness and cited sources.
    6. 6Allow uncertainty: Ask the model to name missing information instead of filling gaps.
    7. 7Break tasks down: In multi-step work, separate steps are easier to check.
    8. 8Iterate with test cases: Compare several prompt versions on the same representative examples and assess errors, not just style.

    What prompts cannot do

    A prompt guarantees neither correct facts nor higher productivity; results still need human review. Role instructions add context, but they do not give the model real professional experience or additional facts. Likewise, “think step by step” is not a reliable way to force correct conclusions; do not treat the reasoning a model outputs as proof. Whether a prompt saves time only becomes clear when you measure it in the actual workflow.

    Maintaining a prompt library

    For a prompt library, record the task, model, date, test cases, known limitations and the person responsible. Remove outdated examples when the model or the process changes.

    Sources: OpenAI: Prompt engineering · Microsoft Learn: Prompt engineering for Azure OpenAI

    Agentic AIBest PracticesSchweiz
    Teilen:

    AI tools may have supported the creation of this article. CNEXT is responsible for the published content. Product features and prices can change; check the linked primary sources for current details.

    Patrick Trapp

    Patrick Trapp

    Solution Architect

    Discuss prompting with CNEXT

    Talk to us about how your team can build and test prompts for recurring tasks.