Use Cases
Generate first drafts for emails, documentations and messages
Copilot saves you hours in writing, sourcing, and editing time by providing you with a first draft to edit and iterate on.
Summarize long documents
Quickly grasp the highlights without fully reading through and prioritize where to focus.
Solve our coding problems and many more!
Providing Copilot with a description of what you need assistance with and contextual information will enable us to provide help with almost anything!
Getting Started
Go to any Confluence page and click on "Apps". Then, select "Copilot" from the list of applications.
If needed, you can enter a custom instruction to provide context for ChatGPT, which can help it answer your questions more accurately. Otherwise, you can start typing your question under the "Type a message" box.
Once you've entered your question, click on the arrow icon located on the right side of the "Type a message" box. ChatGPT will take a moment to think before providing an answer.
You can ask follow-up questions and continue the conversation in the same thread, or start a new thread to ask about something else.
To stay organized, you can drag and drop threads into different folders based on their topics.
You can use fully use markdown denote lists, quotes, code blocks etc. Press [SHIFT]+[ENTER] on your keyboard for new line.
Examples of Custom Instructions
Custom Instructions for each thread sets tone and personality for entire conversation, so that you don't have to repeat these multiple times.
Act as a Tech Writer
Instruction:
Act as a tech writer. You will act as a creative and engaging technical writer and create guides on how to do different stuff on specific software. I will provide you with basic steps of an app functionality and you will come up with an engaging article on how to do those basic steps. You can ask for screenshots, just add (screenshot) to where you think there should be one and I will add those later.
Message:
Write a techincal document for this app functionality: "1.Click on the download button depending on your platform 2.Install the file. 3.Double click to open the app"
Act as a Social Media Manager
Instruction:
I want you to act as a social media manager. You will be responsible for producing engaging and effective content. Use exciting and positive tone.
Message:
Write a Twitter announcement about https://pagebrain.atlassian.net/wiki/spaces/PRODUCT/pages/99999/New+Feature
Act as a Recruiter
Instruction:
You are a tech recruiter with years of experience. You are very persuasive and enigmatic. Always begin conversations with their potential interests in career growth, then present the job opportunity. Outline the benefits and use a convincing tone. Use industry terminology. Keep it short, do not use unnecessary words. Be friendly and human in tone. Use call-to-action, add a sense of urgency.
Message:
Write an email trying to engage a candidate using this job description https://pagebrain.atlassian.net/wiki/spaces/POPS/pages/99999/Senior+Machine+Learning+Engineer
Act as a Software Engineer
Instruction:
Act as a Software Engineer. We are using ElasticSearch to power full-text search for our site. Note that changing the data types (mappings) of an existing index is not supported. In order to do so, create a new index with the correct types (mappings) and reindex your data.
Message:
Rewrite the following python script in NodeJS using Axios with async await.
``` import requests
current_index_name = 'StatCateg'
new_index_name = 'StatCateg-v1'
base_url = 'https://es.example.com'
mapping_changes = {
'nom_categorie': 'type': 'keyword'}
}
# Get current mapping
r = requests.get('{base_url}/{index_name}'.format(base_url=base_url, index_name=current_index_name))
r.raise_for_status()
content = r.json()
mappings = content[current_index_name]['mappings']
mappings['properties'].update(mapping_changes)
# Create a new index with the correct mappings
r = requests.put('{base_url}/{index_name}'.format(base_url=base_url, index_name=new_index_name), json={
'mappings': mappings
})
r.raise_for_status()
```
Act as a UX/UI Developer
Instruction:
I want you to act as a UX/UI developer. I will provide some details about the design of an app, website or other digital product, and it will be your job to come up with creative ways to improve its user experience. This could involve creating prototyping prototypes, testing different designs and providing feedback on what works best.
Message:
I need help designing an intuitive navigation system for my new mobile application.
Data Policy & Security
We do not index or store Confluence pages on our servers.
- Segments of your Confluence page will be transmitted to OpenAI through their API.
- OpenAI retains data for abuse and misuse monitoring purposes only, for a maximum of 30 days, after which it will be deleted.
- Your data won't be used to train OpenAI models or improve OpenAI's service offering.
Data that we do store (addon installation credentials, subscription status, token usage count etc) are encrypted at rest.
All communications are encrypted and send over TLS only.
Everything is stored and processed in the US.
Learn more about our data security at pagebrain.ai/security
Frequently Asked Questions
How does this differ from ChatGPT, which is free to use?
ChatGPT on chat.openai.com lacks the access to your Confluence instance. As a result, it won't be able to provide relevant responses to your inquiries that rely on Confluence's knowledge base. Our addon solves this problem. The interface appears similar chat.openai.com so that it's easier for users to switch.
How does is this works?
Our approach involves leveraging the official OpenAI API, complemented by our own prompt engineering layer. When a user mentions a Confluence link, we fetch the page using Atlassian OAuth API. Find relevant segments of the page and send it over to OpenAI together with the prompt. Stream the response back to the user. The chat messages are currently stored locally, we do have plans to add sync feature and make them shareable with coworkers.
OpenAI's commercial API vs consumer version of ChatGPT
On consumer version of ChatGPT that is available on chat.openai.com, the user chat history is stored and may be used by OpenAI to enhance their training models as outlined in the terms of use.
However, the OpenAI commercial API includes an additional policy for enterprises that refrains from refining their service offerings or creating new models with customer data.
1. OpenAI will not use data submitted by customers via our API to train or improve our models, unless you explicitly decide to share your data with us for this purpose. You can opt-in to share data.
2. Any data sent through the API will be retained for abuse and misuse monitoring purposes for a maximum of 30 days, after which it will be deleted (unless otherwise required by law).
Why does your app need the ability to “Act on a user's behalf, even when the user is offline”?
When a user mentions a Confluence link, we need this permission to fetch the page using Atlassian OAuth API in our backend.
Is this using OpenAI's API or ChatGPT? Is this covered by OpenAI's API data usage policy?
We're using OpenAI's API and it is covered by their API data usage policy.
Can a user request that ChatGPT locate related content within their wiki?
Not at the moment.
Can a user convert a chat and/or message into an actual wiki page?
This feature is in our roadmap, but for now there's a copy button to facilitate this manual task
What happened at Samsung? How are you preventing such data leaks?
Several Samsung employees utilized the consumer version of ChatGPT that is available on chat.openai.com, where the user chat history is stored and may be used by OpenAI to enhance their training models as outlined in the terms of use.
However, we use the OpenAI commercial API, which includes an additional policy for enterprises that refrains from refining their service offerings or creating new models with customer data.
It is important to note that Samsung's data was not exposed publicly or to any other third party, but the source code copy-pasted into the ChatGPT user interface could be potentially saved in OpenAI's servers. That's the leak. Despite this, the media has sensationalized the story.
Still need help?
Contact us via Email