The CisionOne AI Assistant is your all-in-one AI support for Media Monitoring, Social, and Outreach. It brings together all AI-powered features into a single experience with no need to switch between tools.
Based on the selected task, the assistant guides you through a smart, conversational flow, asking the right follow-up questions and delivering tailored responses.
From drafting media outreach and social posts to suggesting optimal send times, building Mention Streams, or summarising coverage, this assistant helps PR professionals move faster and stay focused with less effort.
Find out more about Cision's AI Assistant in this video.
To get started, click on the Cision AI icon which appears at the top right of the screen.
You'll then have the following options:
Create a Boolean Query
This assistant helps users write precise Boolean queries through guided conversations. It reduces the user learning curve and speeds up the setup of targeted Mention Streams.
Click on a template button. For example, “Create a Brand-Focused Boolean Query” and the AI begins by asking for key brand terms and topics of interest.
Here's an example of a brand focussed Boolean query. We'll be presented with the Boolean query with options to:
Expand or Refine the query
Use the Boolean query
Start Over
Mention Stream Summarisation
This feature allows you generate concise summaries of content within any Mention Stream, helping them quickly grasp the core themes without manually reading through each article.
This saves time, highlights core themes faster, and lays the foundation for PR responses or reporting.
After selecting a Mention Stream and date range, we organise the Mentions into topics which which are later analysed by the AI to create summaries for each topic using the articles’ information. It then returns:
3-5 topic summaries
Articles chosen for each topic
Hover over the AI icon at the top of each Mention Stream.
Click Summarise.
The summary will be shown on screen with options to:
Change the date range
Open in AI Assistant
Copy the summary
Mention Stream Suggester
This feature helps you build smarter Mention Streams by suggesting relevant keywords based on terms used during he Mention Stream creation process.
When you enter a starting keyword or brand name, the AI analyses associated content and recommends:
Related terms for inclusion
Irrelevant or high-noise terms for exclusion
Write my Social Post
This option lets you describe social post content to the AI Assistant. Once you've entered a description of the topics, target audience, platform info etc - the AI Assistant will present different examples and options for the post.
When should I post my Social Content?
This option lets us provide information on a post in terms of its content and target audience. Once we've provided this info, the AI Assistant will provide suggestions on when to post.
Write my Media Outreach
This option lets us provide information on a press release/pitch in terms of its content and target audience. Once we've provided this info, the AI Assistant will provide suggestions on when to post.
When should I send my Media Outreach?
By giving the AI Assistant information on our outreach content, it'll suggest the best time for
FAQ
What AI technology powers the CisionOne Assistant?
The feature is powered by Google's Gemini 1.5 pro model and has been specifically optimised for CisionOne Tasks.
How does the AI handle different languages?
The assistant can understand and respond in multiple languages. However, it may occasionally default to English instead of the intended language.
Are my chats and feedback data stored?
Yes. This includes your user ID, input, output, feedback response (thumbs up/down with reason) and search date. We use this data solely to observe and optimise the model's performance. This data is archived after a certain period.
What happens if there is an error?
If an error occurs during the AI response process, you'll see an error message with details that something went wrong. Simply try your search again, and if the error persists, contact Technical Support and submit a ticket via Jira for assistance.
Are the AI results tailored to individual clients or trained on client-specific data?
No, the AI model is not client specific and does not provide results tailored to individual clients. A single model is used for all clients, and any feedback provided helps improve the overall model for everyone. This ensures consistent, unbiased performance across all clients.
How does the feedback get processed to update the AI model?
All feedback is sent to the product team for review. The team uses this input to assess performance and make any necessary adjustments to improve the model over time.
How often is the AI model updated or adjusted?
The AI model is regularly reviewed based on feedback submitted in the platform to ensure results remain accurate and relevant. There is no set cadence for these reviews but updates will be made as necessary to maintain performance.
How does the AI model handle sensitive or inappropriate content?
Google’s Gemini Vertex AI uses four configurable safety categories — Hate Speech, Harassment, Sexually Explicit Content, and Dangerous Content — to evaluate whether an input is classified as Safe or Unsafe. We have set the model to the highest safety levels for most categories, meaning that most content falling into these categories will be flagged as sensitive and show the appropriate error message. Additionally, we’ve implemented safeguards within the prompt to prevent the AI from generating responses that include sensitive content.