8️⃣ ITONICS PRISM: Auto-create elements, ratings, texts, and images
Let the Innovation OS do the job for you by leveraging machine intelligence. Let it craft context-specific elements, ratings, descriptions, and images. See automatichow trends and technologies change over time.
Note: PRISM, the AI chatbot, is limited by your own permissions on the platform, if your account is registered as a viewer, you cannot create, update or rate elements using the AI.
Note: PRISM is enabled by default for all subscribers unless a different arrangement is requested.
If you want to update your preferences, please get in touch with us via account_manager@itonics-innovation.com.
Attention: Having trouble using PRISM? Ensure that your IT department allows wss://itonics-ws.com through your network firewall. Blocking this WebSocket connection may cause loading issues.
3. Auto-create trend and technology radars
4. Use the Innovation AI to interact with Signals and Elements
5. Auto-rating: Speed of change
6. Autofill description, tags, and images
7. Auto-generate and auto-evaluate ideas
PRISM Chat Window
When in the workspace, to access PRISM, press the dedicated button in the bottom right corner.
PRISM chat is based on Claude 4.0 Sonnet, a LLM similar to ChatGPT, but the internal functionalities are split up into different agents who all communicate between each other based on what prompt they are executing, sometimes referred to as multi-agent debates or deep reasoning.
If you are interested in what is being discussed after your prompt, clicking on the little arrow [1] will show the internal reasoning process.
Master Context
Get the most value out of each prompt and set a Master Context for your workspace.
Note: Only Workspace Admins can set the Master Context.
What is a "Master Context"?
Large language models work best when you provide them with relevant background information. A Master Context is a persistent block of text that gets infused into every conversation you start with the AI. Instead of repeating your company’s mission, priorities, or constraints before every prompt, the Master Context ensures the AI always has this baseline understanding.
Think of it as the lens through which the AI interprets every question, idea, or suggestion, helping it generate responses that are aligned with your company’s identity and strategy.
Why is a Master Context important?
- Consistency: Keeps answers aligned with your goals across multiple sessions.
- Efficiency: Saves time by avoiding repeated instructions.
- Relevance: Ensures outputs resonate with your brand voice, strategic direction, and users’ needs.
- Quality: Increases the chance that suggestions are practical, feasible, and tailored to your business.
How to craft a Master Context
A strong Master Context addresses key dimensions of your organization. You can think of it as answering the following guiding questions:
- Core Identity
- Who are you as a company?
- What values, principles, or cultural traits guide your decisions?
- Strategic Goals
- What outcomes are you working toward?
- What KPIs or success metrics matter most?
- Priorities & Challenges
- What problems are you trying to solve?
- Which trade-offs (speed vs. safety, cost vs. innovation) must be considered?
- Technology Areas & Capabilities
- What platforms, tools, or technologies define your domain?
- Where do you innovate, and where do you rely on partners?
- User & Market Focus
- Who are your users or customers?
- What do they expect in terms of experience, reliability, and trust?
- Constraints & Non-negotiables
- Regulations, compliance, safety, sustainability, or ethical standards that must always be respected.
Hint: If you need support with developing an effective Master Context, start by outlining its intended purpose, provide a brief overview of your organization, such as the introductory paragraph from your company's Wikipedia entry and use an AI chatbot to help generate a first version of your Master Context.
Set the Master Context in the ITONICS Innovation OS
Note: The Master Context is applied on a workspace scope. Which means, if you have multiple, different workspaces with different goals, you can and should, set different Master Contexts.
To set the Master Context, open PRISM via the designated AI button in the bottom right.
Then locate the three dots [2] at the top right of the now expanded side panel and select "configure" [3].
Now write or paste the Master Context in the text field.
At the bottom of the popup you can see another dropdown menu [4] to select an element type. Select which element type best represents this workspace, this is not necessary, but if you already have a "strategy" element or something similar in your workspace, it is recommended to select that and if possible adjust the criteria below, under "advanced filter"[5], to select exactly the elements you want. The advanced filter works just like the regular filter.
Last but not least, make sure "Enable for new chats" [6] is enabled, press "Save" [7], and you are ready to go.
Segment and rate radars
After creating a radar with its designated element types, let PRISM do the job: Automate radar segmentation and let the AI rate the elements based on your, company specific, catered to your needs, master-context.
Click on the PRISM button in the bottom right corner, a new side panel will open. In the top right corner you have the option to close PRISM, expand the side panel to full screen or the three dot menu, with the option to set a Master Context for this workspace.
To segment your elements, simply ask PRISM and don't forget to specify in your prompt which element type you want to segment.
Rating elements works similar to segmenting them. Specify which elements and fields you want to include in the rating process and the AI will do the job.
But be aware, rating is still based on generative AI, while PRISM is much faster than a human at rating, the nature of generative AI is still to guess and therefore you may experience that ratings don't follow your standards.
It is recommended to use qualified personell at your company to rate important elements.
Note:
- You need create permissions to work be able to create elements with PRISM.
Use PRISM to interact with Signals and Elements
The Innovation AI can interact with signals and elements within the workspace to enhance your prompts. Below you find an overview of valuable prompts to execute different use cases:
Prompt Playbook for Signals:
Tip: You can use all filters in the prompt that are also available in the Insights Feed.
Use Case: | Prompt Template: | Prompt Example: |
Create an element based on Signals | Create one [element type] based on all signals from [country] between [start date] and [end date] about [topic]. Combine all insights into one [element type]. | Analyze all signals related to autonomous cars from the United States between May 1, 2024, and July 1, 2024. Synthesize the key insights, trends, or developments from these signals into a single, coherent Idea. The Idea should include a clear opportunity or problem statement, supporting evidence from the signals, and a potential solution or innovation approach. |
Summarize Signals | Summarize all signals from [country] between [start date] and [end date] in the category [category], including the companies [companies]. | Summarize all signals from the United States between 01.05.2024 and 01.07.2024 in the category Technology and Engineering, including the companies IBM and Apple. |
Identify a specific source signal type related to an element | Show recent [source type] related to [element name]. | Show recent patents related to Autonomous Cars. |
Conducting general research | Identify new developments in [topic] within the [industry]. | Identify new developments in Artificial Intelligence within the car industry. |
Prompt Playbook for Elements:
Use Case: | Prompt Template: | Prompt Example: |
Summarize an element | What is the element [element name] about? | What is the element autonomous cars about? |
Find duplicates | Are there any duplicates to the element [element name]? | Are there any duplicates to the element autonomous cars? |
Find related elements for a topic | Are there elements/[element type] related to the topic [topic]? | Are there Ideas related to the topic Artificial Intelligence? |
Find related elements for a signal | Are there any elements related to the signal [signal name]? | Are there any elements related to the signal "Lasers and their Industrial Applications"? |
Find related elements to another element | Are there any elements relevant to the element [element name]? | Are there any elements relevant to the element autonomous cars? |
Create an element based on other elements | Create a [element type] based on the element/s [element names]. | Create a Trend based on the element autonomous cars and self-driving trucks. |
Compare elements | What is the difference between the elements [element name 1] and [element name 2]? | What is the difference between the elements autonomous cars and self-driving trucks. |
Compare elements | What are the similarities between the elements [element name 1] and [element name 2]? | What are the similarities between the elements autonomous cars and self-driving trucks? |
Perform a risk analysis on an element | What are potential risks associated with the element [element name]? | What are potential risks associated with the element autonomous cars? |
Speed of Change index
To activate the speed of change index, head to the element type configuration of your workspace. You can either create a new rating type group [1] or use an existing one. Search for "Speed of Change" and add them from the dropdown [2].
You can rearrange rating criteria by dragging and dropping and hiding the ones you do not want to use anymore by clicking on the eye icon. Once you are happy with your rating setup, hit Save Changes.
You can also compare the speed of change across multiple content elements when you head over to the technology or trend radar. Open the radar view configuration, select Distance, and choose either Speed of Change [90 Days] or Speed of Change [180 Days].
You can now compare the trends and technologies on the radar by the Speed of Change of the last 90/180 Days.
When you watch a content element, you will receive an email notification if the speed of change changes.
Autofill description, tags, and images
We help you reduce the burden of adding images, descriptions, or tags by our smart action feature.
Autofill description
Go to any content detail page and find the smart action button below the content title or in a rich-text-field. Choose Autofill Description from the Smart Actions (1) in the header or navigate to the Description section. (2) A modal will open and create a suggested description for you (3).
When designing a campaign, there is even the option to decide on a preferred storytelling template (3) for auto-filling the description. You can choose between the following options which will generate a description based on your provided Summary:
- Campaign Canvas: This Canvas will produce a structured description covering the following points: Campaign description, Objective of the Campaign, Stakeholders & Audience, How To Participate, Guiding Questions that help idea submitters understand what's expected and a short and engaging closing statement.
- Storytelling Tactics:
The golden circle: This Storytelling method starts with "Why" (the purpose or belief), then "How" (the process or values), and finally "What" (the product or result) to inspire and connect with an audience.
Conflict and Resolution: This Storytelling method introduces a central challenge or problem (conflict) and then presents a solution or outcome (resolution) to engage and inform the audience. The resolution in that case is the campaign itself.
In media res: This Storytelling method begins with a narrative in the middle of the action, often at a critical point.
- Default: This method will create a structured idea description.
To increase the quality of the response enter a few more information. Click the Create button to get the description.
Autofill Tags
Go to any content detail page and find the smart action button below the content title or navigate straight to the tag section. Choose Autofill Tags and the system will return a suggestion of tags based on your provided Summary. This means that suggestions may include both existing tags from your platform and entirely new tags. If you select a suggested tag that already exists in your platform, it will automatically be merged with the existing tag, ensuring consistency and avoiding duplicates. Not fitting tags can be removed by pressing the “x” icon next to the respective tag. Insert your tag selection.
You can also add tags to an element via the chat. Specify which element or elements you have in mind and ask PRISM to generate tags for you.
Autofill Image
Go to any content detail page and find the smart action button below the content title [1]. A modal will open where you can select your preferred image style. You can choose between No style, van Gogh, Futuristic, Digital Art, Artwork, and Cartoon [2]. Describe the image you want to generate in a short and precise sentence [3]. Click the Create button to generate a preview of images [4]. The system will suggest some images from which you can choose. Click Apply if you are satisfied.
Autogenerate and evaluate ideas
Autofill Idea Description
To use the Autofill Idea Description feature, go to the idea detail page and find the smart action button below the content title [1] or navigate to the Description section [2].
A modal will open where you can select your preferred template [3] for auto-filling the idea description based on your summary and further information.
For the writing style of the description, you can choose between the following options, which will generate a description based on your provided summary:
-
-
- Idea Canvas: This Canvas will produce a structured description covering the following points: Problem statement, Key Features, Value Proposition, Concept.
- Personas: Describe the idea in the words and with the mindset of one of the following forward thinkers:
- Albert Einstein
- Warren Buffett
- Elon Musk
- Barack Obama
- Oprah Winfrey
- Creativity Methods:
- Journey Mapping: A visualization of the process that a user undergoes to achieve a goal, capturing all the touchpoints and experiences.
- SCAMPER: An acronym-driven brainstorming technique that prompts users to think about a product or problem through seven different methods: Substitute, Combine, Adapt, Modify, Put to another use, Eliminate, and Reverse.
- Brainstorming: A group creativity technique by which efforts are made to find a conclusion for a specific problem by gathering a list of ideas spontaneously contributed by its members.
- Headstand: A problem-solving technique that involves looking at the problem from the opposite perspective, by considering what would cause the problem to occur or worsen.
- 6-Thinking Hats: A role-playing model that encourages individuals to look at a problem from six distinct perspectives: emotional, informational, logical, creative, critical, and organizational.
- Default: This method will create a structured idea description.
-
To increase the quality of the response enter a target audience that the idea should address [4]. Click the Create button to get the description [5].
As described above, also on an idea the system can automatically provide you with an image and tags (read above).
Auto-create Ideas with Gen-AI
Once you have started your campaign you can leverage the power of generative AI to generate some thought starter ideas. Click on the Smart Actions in the Campaign header and select Autocreate Ideas [1]. A modal will come up and will ask for more context to generate the best ideas possible: In which industry should the ideas primarily be applied? Who will benefit most from it (target audience)? Hit Create [2] once you have provided the relevant information. Click on Explore now once the ideas are created. You will be redirected to the Campaign Board to check out the AI-created ideas.
To learn more on campaigns, read this article.
Auto-rate Ideas with Gen-AI
When the submission phase concludes, tap into the transformative capabilities of generative AI to automatically assess the submitted ideas. The board offers a swift preliminary evaluation, providing a baseline for further analysis. Additionally, it can function as a supplementary AI-informed perspective, integrating seamlessly with expert evaluations in the decision-making process.
Click on the Smart Actions in the Campaign header and select Autorate Ideas [1]. A modal will come up to further specify which ideas you want to be rated. Choose the phases for which you want to rate the ideas [2]. The phases that appear here are dependent on your selected workflow. Select the rating criteria you want to be rated by AI [3]. The rating criteria that appear here are based on the configured rating criteria for the element type idea. Click Continue if you are satisfied with your selection [4]. Click on Explore now once the ideas were rated. You will be redirected to the Campaign Board where you can check out the AI-rated ideas.
AI models in use
Since different AI models have vastly different use cases, the PRISM is using six different models, each for a different use case:
Purpose | Model | Hosted |
Summary generation | GPT 4o | Open AI |
Tag generation | GPT 4o | OpenAI |
Image generation | Dall-e | OpenAI |
Strong Signals | GPT 3.5 Turbo | OpenAI |
Chat | Claude 4.0 Sonnet | AWS Bedrock |
Vector generation | Cohere Embed Multilingual | AWS Bedrock |
AI RTE Editor | Claude 3.7 Sonnet | AWS Bedrock |