Existential risk – for risk of existence of software developers
App should collect, list, track or managed the incidents that was assigned to engineers. The table must contains technical info for resolving the incident. Also the app should include the chart with summary of incident statuses.
Specify prompt for app generation and submit:
Wait until the entities are created
Adjust if needed and proceed with app creation:
Just 10 seconds and you have an app that you are not ashamed to show on a demo to a client or to prove to a manager that you have been actively working and here are the results of your work. Isn’t it?
Plug N’ Play – for Dynamics 365 plugin that updates Mario for each support request based on the context using OpenAI
The Existential Risk – for AI decision making and work assignment without human involvment
Go With The Flow – for automating of the technician assignment
Crawler – for an innovative approach of searching for the right Mario technician
Sometimes Princesses are confused and don’t know where to start from when they have technical issues. So we are here to help them with AI! Princesses just need to add the description of the problem and the Dynamics Plugin will suggest Marios that are currently available and best match the case.
So the Princess creates a new support request, and that’s were plugin is triggered. The plugin sends the problem to OpenAI’s smart ChatGPT. The prompt: Given the following case description, rate its severity on a scale of 1 to 4, where 1 is minor and 4 is critical:
I seem to be having a bit of a predicament with our kingdom’s email system, and I’m in dire need of assistance. This morning, when I attempted to send out invitations for the upcoming royal ball, I noticed that none of my emails were being delivered. They seem to be stuck in the outbox, and no matter how many times I try to resend them, they simply won’t go through.
The result of the OpenAI request is the severity level, in our case it is 3. So the plugin is looking for Marios who can cope with this severity and assigns the case to this Mario. Also, plugin updates the details of the case:
It is an extraordinary way to search for an engineer, but also a risky for administrators of the support team, as AI is taking away their job! On the other hand – it follows the flow and automate the routine process, which is a major benefit for the business itself….
Hipster: We protect privacy by not saving any user information except the name in our database. Also, provide cartoon avatars instead of real face of the employees.
The Existential Risk: Our AI generates interesting background stories where humans may fail to do so.
Mario badge: Gamification of the onboarding process. Instead of boring onboarding we provide users a game character creation experience when joining the company
Thieving Bastards: We use paid ChatGPT api to do api requests.
Do you want a fast onboarding process for your agents? We have the right solution.
In our company, we use AI to generate images that look like your agents. We have customizable prompts to generate different characters. We can create a quick backstory for an immersive customer experience.
You can choose different appearance options. For Image generation, we will need a prompt and an image of the person. Based on the selected character AI will make your avatar a lookalike.
Take your picture and generate an image. We are using chatgpt API for image generation. It is a subscription model for text generation and pay as you go model for image generation. Using existing api instead of building a stable diffusion solution save from time. We use power automate cloud flows to call API requests and retrieve responses. We let the ai combine user picture and prompt to create a cartoony avatar.We do not save any user information in our dataverse to keep up with privacy requirements
Choose your theme for the background. AI will create a nice-looking story for you. Based on what is said in your story it will set a skill level too. This time we are using text generation apis of chatgpt with flows. Based on selected background option ai will generate a background story and skill level. Skill level considers generated story too, so it is meaningful.
Responsible AI implementation is critical, especially as we delve deeper into advanced technologies. Microsoft is leading the way with its six foundational principles of responsible AI. In this post, our spotlight is on one of these key principles: reliability and safety.
Consider a scenario where a language model, which I developed, exercises complete control over another language model’s instructions. This setup immediately poses a challenging question of accountability, particularly if the subordinate language model engages in undesirable behavior, such as generating insults. While it might seem straightforward, the responsibility ultimately falls on me, as the developer. This underscores the importance of integrating robust oversight mechanisms and ethical guidelines in AI systems to ensure they operate within the realms of reliability and safety. By doing so, we can not only mitigate risks but also enhance the trustworthiness of AI applications in our increasingly digital world.
The described solution represents a high-level design overview. Leveraging the Bot Framework, it analyzes user sentiment and feeds this data into PromptFlow. However, it’s at this juncture where we encounter the more nuanced, potentially contentious aspect of our solution.
Our current PromptFlow process is straightforward yet effective. It primarily requires two inputs: sentiment and text input. Utilizing the meta-prompter LLM, the system communicates with an OpenAI instance located in Norway East. The core function here is to relay instructions to a secondary language model, ensuring the generated content aligns with the specified sentiment.
While this mechanism might not seem revolutionary, its effectiveness is largely due to the robust moderation capabilities of Azure’s OpenAI instances. These safeguards are crucial in preventing misuse or unintended consequences.
However, it’s important to acknowledge the potential risks. In the hands of someone with advanced prompt engineering skills and access to the right language models, this system could be manipulated into producing outputs that are ‘very non-compliant’ with ethical guidelines.
We recognize that our self-prompting AI solution might not be groundbreaking in practical applications, but it has already earned us the Dooh badge, showcasing our innovative approach within this technological space.
With this blog post we aim for the Go With The Flow, The Existential Risk, Mario badge and Plug N’ Play.
The Mario Badge for the gamification of Copilot.
The go with the Flow and Existensal Risk, because the use of Prompts with CHAT. One prompt to check if answers are correct or not The other prompt tells if the answer is Correct or Incorrect and will use this to send an action to power automate to populate a dataverse table.
The plug N´play for the use of prompt plugins in copilot.
Tested Generative AI inside the copilot studio, got answers, but could not check the answers with generative AI, it was good to give the answers, but not good to check if the answers is correct.
Made a power automate flow that generates a text with AI builder. – But it had limitations, it stopped with that you had to have an approval of text before i could process it.
So the next step i did was to try the new Prompts in Copilot studio: (It took many iterations of the prompt to make the copilot say if it was correct or incorrect).
Started making the Quiz topic that is the “game”, to test if it would work like i thought:
It works
Next STEPS:
Send correct answer to dataverse table to score a point:
Add the Copilot(chatbot) control to the canvas app:
The captain log business value is that he has an app with all the tools he needs at the tip of his hook.
A new feature:
Behold the “Reveal your true face feature”
Revealing the true face
Some pirates find their interest in hiding away, and then it is handy to have an app to show the true face and spot if this is a know fellow shipmate or a rivalling pirate that deserves to be keel hauled.
The service uses a mobile or tablet camera to take a picture of the person in-question and then posts it to mutiny services for identification and face recognition in order to find who this person is.
Our solution is using Power Automate and HTTP trigger to accept new pirates
And put into a workflow used by our Pirate onboarding app.
Badges
Dataminer – The great database of LLM allows us to mine for awesome pirate names and visual traits for our crew.
Hipster – LLM are so hot, it will be a while until they are not. A multi-billion tech, via Azure Open AI studio cannot be beaten!
Existential Risk – It’s mining, it’s a huge learned model, living on the edge! Sure, we didn’t spend the billions training the model, but that’s hard to do on a pirate’s salary in 2023.
We strongly believe that we have used AI in an innovative way and here are the reasons why. In the fleet enlisting app, we are inserting vehicles into our system with out the need to punch a single character. An AI model has been trained to recognize vehicle type based on picture taken in the app.
Once the app recognizes the picture of the vehicle, the app will communicate with a external database to collect detailed information about the vehicle and insert the data into our fleet management system.
Use case flowAI Builder custom modelVehicle tags (objects to detect)Training images
Travelling the seven seas is great fun and pirates can get as moody as anyone else. The ships current loot holding will continue to diminish in between raids and weather sickness can strike at any time. The below input is what we use to simulate mood swings, also output as logic in code.
Of course, we have no idea if this is the actual code or not, as we ask to get schematized JSON – sanitized for input into the dataverse. With mood data available we can start tracking if a mutiny is far away or close at bay.
We’re thinking the following badges apply:
The Existential Risk – text-davinci-003 has never looked better
ACDC Craftsman – documenting verbatim logic for the logical heads out there just makes sense, ensuring everyone can consume and understand the logic at hand independent of their skillset.
Dataminer – LLM are nothing but a huge heap of external data baby! We’re thinking Babels tower in blob.
When we’re creating an app for everyone one to use for their everyday Pirate activites coming from F&O, we might as well include som external data as well to make the experience for the Pirate even better. We have never, and never will, argue that you will get all the information you need every day from F&O, so we have given every Pirate a bit more data they can use every day in their canvas app:
When you first log in to the app in the mornig, it’s handy to get a little greeting just “welcomming” you to a new day, right? We have created a PowerAutomate that uses OpenAI to find a new Pirate greeting just for you (if using AI to cheer up your Pirates isn’t an innovative use of AI, then what is?):
2. If you feel down, and just want some text to make you laugh a little, you don’t need to go to the internet, we have created an Insult of tha day feature in your app. Just click it and start feeling better, at least if you think that this insult is regarding you bunk-buddy 🙂
3. And then, if you want to know what kind of weather it is, look no further, it’s already right there in you Pirate app:
