Sometimes you may encounter annoying training content that forces you to watch a section before you can explicitly advance to the next one. Never understood why I have to do this or sit for long trainings altogether if I already know the answers and can pass the naive quizzes. Usually, a web button to continue gets enabled after you watch a video or after some time elapses.
With some investigative work and low-code JavaScript, you can easily “automate” the process to some extent, such as until it’s time for the quiz, as follows:
The trick is to find the id of the button and what makes it enabled/disabled. In the Edge browser, right click the “button” and then click Inspect. This will open the Dev Tools and you’ll will see the button HTML definition. You can right-click it on the HTML code and then click Copy OuterHTML to paste it in Notepad to inspect it. In my case, the element id is “button-next”. When the button is disabled, the app adds an attribute disabled as follows: <button … disabled=”” type=”button” id=”button-next”>…</button>
In the browser Dev Tools Console (F12), copy and paste the following JavaScript code, and then press Enter (note that you must execute allow pasting before you can copy and paste code for the first time as the Console will inform you):
function checkAndClick() {
const targetElement = document.getElementById('button-next'); // Get the element by ID
if (targetElement) { // Check if the element exists
if (!targetElement.hasAttribute('disabled')) { // Check if it does NOT have the 'disabled' attribute
targetElement.click(); // Simulate a click
console.log('Element clicked!');
} else {
console.log('Element is disabled.');
}
} else {
console.log('Element not found.');
}
}
// Set an interval to run the function every 2 seconds
const intervalId = setInterval(checkAndClick, 2000);
// clearInterval(intervalId); Disable the timer when no longer needed
This code watches every two seconds if the disabled attribute is removed from the button, in which case it “clicks” the button to advance the content. Hope this will save you precious time for more productive work. Happy training!
Looking for easy ways to create intelligent bots or Retrieval-Augmented Generation (RAG) apps? Microsoft Copilot Studio should help. After a year of letting it (and other Microsoft LLM offerings) simmer and inspired by the latest hoopla from the Ignite conference, I took another look at Microsoft Copilot Studio and share my findings in this newsletter. For the uninitiated, Copilot Studio lets you implement AI-powered smart bots (“agents”) for deriving knowledge from documents or websites. Basically, you can view the relationship of Copilot Studio to Retrieval-augmented Generation apps as what Power BI is to self-service BI.
Copilot Studio licensing starts at $200 per month for up to 25,000 messages (interactions between user and agent) although at Ignite Microsoft hinted that pay-as-you-go licensing will be coming.
The Good
A few months ago, when I discussed RAG apps, it was obvious that a lot of custom code had to be written to glue the services together and implement the user interface. Microsoft Copilot Studio has the potential to change and simplify this. It offers a Power Automate-like environment for no-code, low-code implementation of AI agents and therefore opens new possibilities for faster implementation of various and specialized AI agents across the enterprise. I was impressed by how easy the process was and how capable the tool was to create more complex topics, such as conditional branches based on user input.
Like Power BI, the tool gets additional appeal from its integration with the Microsoft ecosystem. For example, it can index SharePoint and OneDrive documents. It can integrate with Power Automate, Azure AI Search and Azure Open AI.
I was impressed by how easy is to use the tool to connect to and intelligently search an existing website. For now, I see this as being its main strength. Organizations can quickly implement agents to help their employees or external users to derive knowledge from intranet or Internet websites.
To demonstrate this, I implemented an agent to index my blog and embedded it below for you to try it out before my free trial expires. Please feel free to ask more sophisticated questions, such as “What’s the author’s sentiment toward Fabric?”, “What are the pros and cons of Fabric?”. Or “I need help with Power BI budget” (I got innovative here and implemented a conditional topic with branches depending on the budget you specify). I instructed the tool to stay only within the content of my website, so the answers are not diluted from other public sources. Given that no custom code was written, Copilot Studio is pretty impressive.
The Bad
Everyone wants to be autonomous and AI agents are no exception. In fact, “autonomous agent” is the buzzword of AI world today. Not to be outdone, Copilot Studio claims that it can “build agents that operate independently to dynamically plan, learn, and escalate on your behalf”. However, as the tool stands today, I don’t think there is much to this claim. Or it could be that my definition of “autonomous” is different than Microsoft’s.
To me, an autonomous agent must be capable of making decisions and taking actions on its own. Like you tell your assistant that you plan a trip, give her some constraints, such as how much to spend on hotel and air, and let her make travel reservations. As it stands, Copilot Studio offers none of this. It follows a workflow you specify. Again, its output is more or less a smarter bot than the ones you see on many websites.
However, at Ignite Microsoft claimed that autonomy is coming so it will be interesting to see how the tool will evolve. Don’t get me wrong. Even as it stands, I believe the tool has enormous potential for more intelligent search and retrieval of information.
The Ugly
My basic complaint as of now is performance. It took the tool 10 minutes to index a PDF document. Then in a momentary lapse of reason, I connected it to an Azure SQL Database with Adventure Works with 15 tables (the max number of tables currently supported) and it’s still not done indexing after a day. Given that many AI implementations would require searching the data in relational databases, this is not acceptable. Not to mention there isn’t much insight on how far it’s done indexing or limit the number of fields it should index.
Therefore, I believe most real-world architectures for implementing AI agents will take the path Copilot Studio->Azure AI Search ->Azure Open AI, where Copilot Studio is used for implementing the UI and workflows (topics and actions), while the data indexing is done by Azure AI Search with semantic ranking in conjunction with Azure Open AI for embedded vectors.
I’ve been recently impressed with xAI Grok compared to Microsoft Copilot. Grok performs better that Copilot which seems to be crippled with political correctness to a point of absurdity although it seems to be getting more permissive of late. But the most important Grok advantage is that it’s always recent… and it doesn’t crash every now and then.
A couple of examples:
Question: Where is this image from?
Microsoft Copilot – what exactly is inappropriate is not clear.
Grok (impressive!) – This image depicts the rock formations and cave dwellings of Cappadocia, a historical region in central Turkey. The unique rock structures and the cave homes carved into them are iconic features of this area, particularly around the town of Göreme.
Question: What are the most important political events to watch for tomorrow (as of 2/18/2025)?
Microsoft Copilot (chaos of past and current events):
Presidential Primaries: Former President Donald Trump and President Joe Biden have both secured enough delegates to become their parties’ presumptive nominees for president. The primaries in Georgia, Mississippi, and Washington state have been particularly significant.
Senate Hearings: There are ongoing confirmation hearings for various cabinet positions, including the Department of Homeland Security and the Department of Housing and Urban Development.
International Relations: Discussions and negotiations on international issues, such as the ongoing conflict in Ukraine and relations with China, are likely to be in the spotlight.
Domestic Policy Debates: Debates on domestic policies, including immigration reform, climate change, and economic policies, will continue to be important topics
Grok – Based on the available information, here are some of the most important political events to watch for on February 19, 2025:
Pat King’s Sentencing in Canada: This event is noted in posts on X, indicating its significance as people are discussing its impact. Pat King was involved in the Freedom Convoy protests, and his sentencing could have broader implications on discussions around civil liberties and protest laws in Canada.
Global Political Dynamics: Although not specific to February 19, the context from web sources suggests a focus on ongoing geopolitical tensions and diplomatic engagements. For instance, the broader political calendar highlights events like the NATO defense ministers’ meeting in Brussels, which might influence or be influenced by daily developments in international relations.
Atlanta BI fans, please join us in person for our next meeting on Monday, February 3rd at 18:30 ET. Jeff Levy (Data Architect @ Protiviti) will present the core concepts, architectures, and use cases of the Fabric Warehouse and Fabric Lakehouse. Your humble correspondent will walk you through the most significant Power BI and Fabric enhancements of late. For more details and sign up, visit our group page.
Presentation: Fabric Warehouse vs. Fabric Lakehouse: Choosing the Right Architecture for Your Environment Delivery: In-person Level: Intermediate Food: Pizza and drinks will be provided
Agenda: 18:15-18:30 Registration and networking 18:30-19:00 Organizer and sponsor time (news, Power BI latest, sponsor marketing) 19:00-20:15 Main presentation 20:15-20:30 Q&A
Overview: The modern data landscape demands scalable, flexible, and efficient architectures to support diverse business needs. With Microsoft Fabric, two leading paradigms have emerged to address these challenges: the Fabric Warehouse and the Fabric Lakehouse. While both tools aim to provide robust solutions for data storage, processing, and analytics, their approaches, strengths, and trade-offs differ significantly.
This presentation explores the core concepts, architectures, and use cases of the Fabric Warehouse and Fabric Lakehouse. I will compare their performance in areas such as data integration, scalability, and cost-efficiency. Attendees will gain insights into how these approaches align with specific business objectives and workloads, enabling informed decisions about which model best suits their organization’s data strategy.
Sponsor: Protiviti (www.protiviti.com) is a global consulting firm that delivers deep expertise, objective insights, a tailored approach and unparalleled collaboration to help leaders confidently face the future. Protiviti and its independent and locally owned member firms provide clients with consulting and managed solutions in finance, technology, operations, data, digital, legal, HR, risk and internal audit through a network of more than 90 offices in over 25 countries.
https://prologika.com/wp-content/uploads/2016/01/logo.png00Prologika - Teo Lachevhttps://prologika.com/wp-content/uploads/2016/01/logo.pngPrologika - Teo Lachev2025-01-28 11:41:232025-01-28 11:41:23Atlanta Microsoft BI Group Meeting on February 3rd (Fabric Warehouse vs. Fabric Lakehouse)
I had the privilege to participate in the early preview program of the new TMDL View in Power BI Desktop which is currently in public preview in the latest January release of Power BI Desktop. Without reiterating what was said in the announcement, I’d like to mention three main benefits of this feature:
Ability to access the entire model metadata – This includes features don’t have User interface in Power BI Desktop. Traditionally, BI developers have been relying on Tabular Editor to do so. Now you have another option although it requires knowing the TMLDL language. Alas, TMLD doesn’t come with user interface although it does support Autocomplete.
Ability to copy specific model features from one Power BI Desktop file to another – For example, in the screenshot below, I have scripted a calculation group. Now, I can open another Power BI Desktop file, copy the script and apply it. Of course, the target model must include the referenced entities, otherwise I’ll get an error.
Automating tasks – Hopefully, in near future support creating add-ins to automate certain aspects like creating macros in Excel by programming the Excel VBA object model. For example, a developer should be to use the Tabular Object Model (TOM) API to create TMDL scripts and apply them to a semantic model.
https://prologika.com/wp-content/uploads/2016/01/logo.png00Prologika - Teo Lachevhttps://prologika.com/wp-content/uploads/2016/01/logo.pngPrologika - Teo Lachev2025-01-22 17:12:262025-01-22 17:12:26TMDL View in Power BI Desktop
Looking for easy ways to create intelligent bots or Retrieval-Augmented Generation (RAG) apps? 
