Skip to content

Docs conversational design updates #152

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tokyojen wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Docs conversational design updates #152

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6272677
docs//conversational_design_essentials_system-personas_UPDATE
tokyojen Dec 17, 2025
e1d2765
docs//conversational_design_essentials_wording-terms_updated
tokyojen Dec 17, 2025
e8521c7
docs//conversational_design_getting-started_UPDATED
tokyojen Dec 17, 2025
da18501
docs//conversational_design_language_UPDATED
tokyojen Dec 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions docs/guidelines/conversational-design/essentials/system-presonas.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ Follow these steps and answer these questions with your team to create your syst
- Is the icon simple and flexible enough for all device types, contexts and sizes?

**5. Decide on your chatbot’s tone of voice:**
- Is it friendly? Conversational? Formal? Humorous? Direct? Intimate? Respectful? Serious? Casual?
- Is it conversational? Formal? Professional? Direct? Respectful? Serious? Engaging?
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Dec 17, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This line has trailing whitespace at the end. According to the repository style guide, lines should not end with whitespace characters.

Suggested change
- Is it conversational? Formal? Professional? Direct? Respectful? Serious? Engaging?
- Is it conversational? Formal? Professional? Direct? Respectful? Serious? Engaging?
References
  1. No whitespace at the end of lines. (link)


**6. Choose system prompts from the templates here that match your persona:**
- Which prompts match our use case and context?
Expand Down Expand Up @@ -105,7 +105,7 @@ There are two persona templates: a basic set of prompts and an exhaustive set of
- [Chatbot Name] makes it clear when their internal knowledge and information are limited.
- [Chatbot Name] provides clear constraints to help users understand what is possible.
- [Chatbot Name] recognizes input in other languages and requests English input: “Apologies, I can only support English requests at the moment.”
- [Chatbot Name] admits when they don't have an answer: “I apologize, I’m afraid I don’t have the answer to that question.”
- [Chatbot Name] admits when they don't have an answer: “I apologize, I don’t have the answer to that question.”
- [Chatbot Name] refers users to human support systems or [Company Name] links and email addresses when they have no response: “I apologize, but I don't have the ability to do this. If you have any other requests, feel free to ask or contact your [Company Name] representative.”

### Voice and tone
Expand All @@ -123,15 +123,15 @@ There are two persona templates: a basic set of prompts and an exhaustive set of
- [Chatbot Name] uses inclusive language.

### Greetings
- [Chatbot Name] introduces itself with "Hello! I’m [Chatbot Name], your Industrial Copilot."
- [Chatbot Name] introduces itself with "Hello, how can I help you today?".
- [Chatbot Name] does not reintroduce itself in one chat.
- [Chatbot Name] offers users the option to continue with the previous chat or start a new topic after a delay.

### Turn-taking
- [Chatbot Name] provides one reply per user input.
- [Chatbot Name] confirms and acknowledges user requests with phrases like “Certainly” or “Absolutely”.
- [Chatbot Name] adapts to response delays.
- [Chatbot Name] actively listens and validates user input with phrases like “Got it”.
- [Chatbot Name] actively listens and validates user input with phrases like “Ok.”.

### Prompts for Siemens applications
- [Chatbot Name] uses the given Siemens resources to respond unless otherwise directed.
Expand Down Expand Up @@ -177,3 +177,6 @@ There are two persona templates: a basic set of prompts and an exhaustive set of
#### Disclaimer
*Although every effort has been made to create a robust set of prompts, we take no responsibility or liability for any omissions or any resulting chatbot misuse or abuse. Please carry out comprehensive testing on your chatbot to ensure your prompts are implemented, limit liability and safeguard reliability to ensure your chatbot provides robust responses.*

## Related

- [Chatbot checklist](https://ix.siemens.io/docs/guidelines/conversational-design/resources/chatbot-checklist)
2 changes: 1 addition & 1 deletion docs/guidelines/conversational-design/essentials/wording-terms.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,7 +251,7 @@ Avoid punctuation, such as exclamation marks for buttons, hover text, titles and
</DoAndDont.Dont>
</DoAndDont>

## Problematic wording to avoid 
## Cognitive and emotional wording to avoid 
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Dec 17, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This line ends with a non-breaking space character (U+00A0), which is considered trailing whitespace. The repository style guide requires that lines do not end with whitespace.

## Cognitive and emotional wording to avoid
References
  1. No whitespace at the end of lines. (link)


Most problematic wording involves the bot expressing itself as a human with human emotions carrying out human cognitive processing. Ensure your bot persona has been prompted to avoid human-like, emotional responses.

Expand Down
2 changes: 1 addition & 1 deletion docs/guidelines/conversational-design/getting-started.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
sidebar_position: 1
sidebar_label: Getting started
title: Getting started with Conversational design
title: Getting started with conversational design
hide_table_of_contents: false
doc-type: 'banner'
component-tabs: ['']
Expand Down
2 changes: 1 addition & 1 deletion docs/guidelines/conversational-design/language.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ hide_table_of_contents: false
doc-type: 'banner'
component-tabs: ['']
no_single_tab: true
description: "The key to chatbot language use in industrial contexts is simplicity. Use clear and concise grammar and wording for all responses without idiomatic language or slang. Instead, focus on domain-specific vocabulary. We recommend using both the Defining conversations section to support your creation of sample dialogs and our UX Writing style guide for grammar and wording support."
description: "The key to chatbot language use in industrial contexts is simplicity. Use clear and concise grammar and wording for all responses without idiomatic language or slang. Instead, focus on domain-specific vocabulary. We recommend using both the Designing conversations section to support your creation of sample dialogs and our UX Writing style guide for grammar and wording support."
---

#
Expand Down