This week covers Microsoft’s open-source Agent Framework for agentic AI, prompt-injection risks and mitigations, and the causes of language model hallucinations. It also highlights NuGet package security updates, Azure SQL Data API Builder improvements, Reka’s new Parallel Thinking feature, and the latest in AI benchmarking.
MCP Prompt-Injection: The Trust Paradox in AI (Saurabh Davala, Sundeep Gottipati) - This is a good post to learn to start learning about the real danger. To be aware of the potential risk and learning about what we can do.
Why language models hallucinate - Very interesting post that explains the reason why we still have hallucinations and how it works
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
This week post explores the intersection of AI, cloud, and DevOps, featuring updates on Microsoft’s Logic Apps integration, practical .NET tools for system automation, and strategies to enhance documentation for AI-driven workflows. Whether you’re refining enterprise security practices with NuGet’s Trusted Publishing or diving into the ethical nuances of AI through vector databases, this post offers a blend of technical deep dives and thought-provoking discussions. Don’t miss the podcast highlights, from DevOps innovation to the business impact of employee well-being, perfect for developers, architects, and curious minds alike. Let’s connect the dots in a world where code, creativity, and collaboration drive progress.
Prompt Files and Instructions Files Explained - .NET Blog (Wendy Breiding) - One question I often hear is how can I tell Copilot the standard and conventions my enterprise uses. Well, now I can send them to this post. Well done!
ohn Bristowe: The Latest from Octopus Deploy - Episode 368 (Azure & DevOps Podcast) - Loved this episode, I don't know a lot about Octopus. Discussing deployment pipelines, AI integration in DevOps, and the evolution from manual weekend deployments to automated, reliable workflows.
The business case for employee well-being (Modern Mentor) - Really enjoyed this episode on how workplace wellbeing isn't just about perks but building better work systems that boost both results and employee experience
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
Welcome to another edition of my reading notes! This week I've gathered some interesting finds across programming, AI, and general tech topics. From exciting Cake updates to practical AI implementation advice, here are the articles that caught my attention recently.
Programming
Cake.Sdk 5.0.25257.82-beta released (devlead) - I'm happy to see the new release of this cake version coming to a recent .NET version. I have one of my projects using cake, and I was waiting for it; this is amazing
AI
Performance Improvements in .NET 10 (Stephen Toub) - There's a lot of good advice in this post. Assuming you're using AI you should definitely read it
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
In this edition, we explore modern development's evolving landscape. From Microsoft's .NET Aspire simplifying distributed applications to AI security considerations, Git workflow optimizations, and backlog management strategies, there's something here to spark your next breakthrough.
The tech world never sleeps, and neither does innovation. Let's explore what caught my attention this week and might just spark your next big idea or solve that problem you've been wrestling with.
Identity and Access Management for .NET (Khalid Abuhakmeh) - This package looks very interesting to add multiple handlers to an HTTP client. The first question that pops in my mind is why this is not already in .NET, I think it should. I'll definitely give it a try.
AI Injection Attacks (ericlaw) - Great post that talks about the current risk when using AI and how we should try to do our best to protect the important information.
How to Get Things Done, Stay Focused, and Be More Productive (The Mel Robbins Podcast) - This compelling episode (available in audio and video) takes a fresh approach to productivity. Having read their books, I found the conversation particularly engaging and highly recommend it.
Welcome to another edition of my weekly reading notes! This week's collection brings together some fascinating developments across the tech landscape. From the intricacies of building cross-platform .NET tools to impressive AI breakthroughs like Warp's stellar performance on SWE-bench, there's plenty to explore. I've also discovered some thought-provoking content about leadership, product management, and the art of meaningful communication. Whether you're interested in the latest AI tools, looking for career insights, or simply want to stay current with industry trends, this week's selection has something valuable for every developer and tech professional.
Programming
Using and authoring .NET tools (Andrew Lock) - Interesting post that shares the behind-the-scenes when you're building a tool for multiple targets and the challenge that it represents. Those also share the new ways of .NET 10
Design at GitHub with Diana Mounter (.NET Rocks!) - Very interesting, discussion about so many things: career, the balance between design and engineering, GitHub, and so much more.
How to Lead with Value with Dr. Morgan Depenbusch (How to Lead with Value with Dr. Morgan Depenbusch) - I really enjoyed this episode about the little things we can do to shift the way we interact with others.
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
I wanted to kick the tires on the upcoming .NET 10 C# script experience and see how far I could get calling Reka’s Research LLM from a single file, no project scaffolding, no .csproj. This isn’t a benchmark; it’s a practical tour to compare ergonomics, setup, and the little gotchas you hit along the way. I’ll share what worked, what didn’t, and a few notes you might find useful if you try the same.
All the sample code (and a bit more) is here: reka-ai/api-examples-dotnet · csharp10-script. The scripts run a small “top 3 restaurants” prompt so you can validate everything quickly.
We’ll make the same request in three ways:
OpenAI SDK
Microsoft.Extensions.AI for OpenAI
Raw HttpClient
What you need
The C# "script" feature used below ships with the upcoming .NET 10 and is currently available in preview. If you prefer not to install a preview SDK, you can run everything inside the provided Dev Container or on GitHub Codespaces. I include a .devcontainer folder with everything set up in the repo.
Set up your API key
We are talking about APIs here, so of course, you need an API key. The good news is that it's free to sign up with Reka and get one! It's a 2-click process, more details in the repo. The API key is then stored in a .env file, and each script loads environment variables using DotNetEnv.Env.Load(), so your key is picked up automatically. I went this way instead of using dotnet user-secrets because I thought it would be the way it would be done in a CI/CD pipeline or a quick script.
Run the demos
From the csharp10-script folder, run any of these scripts. Each line is an alternative
dotnet run 1-try-reka-openai.cs
dotnet run 2-try-reka-ms-ext.cs
dotnet run 3-try-reka-http.cs
You should see a short list of restaurant suggestions.
OpenAI SDK with a custom endpoint
Reka's API is using the OpenAI format; therefore, I thought of using the NuGet package OpenAI. To reference a package in a script, you use the #:package [package name]@[package version] directive at the top of the file. Here is an example:
#:package OpenAI@2.3.0
// ...
var baseUrl = "http://api.reka.ai/v1";
var openAiClient = new OpenAIClient(new ApiKeyCredential(REKA_API_KEY), new OpenAIClientOptions
{
Endpoint = new Uri(baseUrl)
});
var client = openAiClient.GetChatClient("reka-flash-research");
string prompt = "Give me 3 nice, not crazy expensive, restaurants for a romantic dinner in Montreal";
var completion = await client.CompleteChatAsync(
new List<ChatMessage>
{
new UserChatMessage(prompt)
}
);
var generatedText = completion.Value.Content[0].Text;
Console.WriteLine($" Result: \n{generatedText}");
The rest of the code is more straightforward. You create a chat client, specify the Reka API URL, select the model, and then you send a prompt. And it works just as expected. However, not everything was perfect, but before I share more about that part, let's talk about Microsoft.Extensions.AI.
Microsoft Extensions AI for OpenAI
Another common way to use LLM in .NET is to use one ot the Microsoft.Extensions.AI NuGet package. In our case Microsoft.Extensions.AI.OpenAI was used.
#:package Microsoft.Extensions.AI.OpenAI@9.8.0-preview.1.25412.6
// ....
var baseUrl = "http://api.reka.ai/v1";
IChatClient client = new ChatClient("reka-flash-research", new ApiKeyCredential(REKA_API_KEY), new OpenAIClientOptions
{
Endpoint = new Uri(baseUrl)
}).AsIChatClient();
string prompt = "Give me 3 nice, not crazy expensive, restaurants for a romantic dinner in Montreal";
Console.WriteLine(await client.GetResponseAsync(prompt));
As you can see, the code is very similar. Create a chat client, set the URL, the model, and add your prompt, and it works just as well.
That's two ways to use Reka API with different SDKs, but maybe you would prefer to go "SDKless", let's see how to do that.
Raw HttpClient calling the REST API
Without any SDK to help, there is a bit more line of code to write, but it's still pretty straightforward. Let's see the code:
using var httpClient = new HttpClient();
var baseUrl = "http://api.reka.ai/v1/chat/completions";
var requestPayload = new
{
model = "reka-flash-research",
messages = new[]
{
new
{
role = "user",
content = "Give me 3 nice, not crazy expensive, restaurants for a romantic dinner in New York city"
}
}
};
using var request = new HttpRequestMessage(HttpMethod.Post, baseUrl);
request.Headers.Add("Authorization", $"Bearer {REKA_API_KEY}");
request.Content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
var response = await httpClient.SendAsync(request);
var responseContent = await response.Content.ReadAsStringAsync();
var jsonDocument = JsonDocument.Parse(responseContent);
var contentString = jsonDocument.RootElement
.GetProperty("choices")[0]
.GetProperty("message")
.GetProperty("content")
.GetString();
Console.WriteLine(contentString);
So you create an HttpClient, prepare a request with the right headers and payload, send it, get the response, and parse the JSON to extract the text. In this case, you have to know the JSON structure of the response, but it follows the OpenAI format.
What did I learn from this experiment?
I used VS Code while trying the script functionality. One thing that surprised me was that I didn't get any IntelliSense or autocompletion. I try to disable the DevKit extension and change the setting for OmniSharp, but no luck. My guess is that because it's in preview, and it will work just fine in November 2025 when .NET 10 will be released.
In this light environment, I encountered some issues where, for some reason, I couldn't use an https endpoint, so I had to use http. In the raw httpClient script, I had some errors with the Reflection that wasn't available. It could be related to the preview or something else, I didn't investigate further.
For the most part, everything worked as expected. You can use C# code to quickly execute some tasks without any project scaffolding. It's a great way to try out the Reka API and see how it works.
What's Next?
While writing those scripts, I encountered multiple issues that aren't related to .NET but more about the SDKs when trying to do more advanced functionalities like optimization of the query and formatting the response output. Since it goes beyond the scope of this post, I will share my findings in a follow-up post. Stay tuned!
Here are my reading notes for the week: a mix of AI research and evaluation, .NET and Linux troubleshooting, testing framework changes, and JavaScript/TypeScript perspectives, plus a few podcast episodes on C#, work design, and software modernization that I found worthwhile.
AI
Introducing Research-Eval: A Benchmark for Search-Augmented LLMs (Reka Team) - One thing that has fascinated me since the beginning of this AI trend is how they test and measure the efficiency of those models. This post is going to go into details and share the benchmark (oss) and the results very interesting
Converting an xUnit test project to TUnit (Andrew Lock) - Like Andrew said in this post, changing your test framework is a big deal, but I will definitely consider TUnit for my next project. A very interesting post.
C# 14 with Dustin Campbell (.NET Rocks!) - Nice episode talking about C# and more precisely things that are related to Razor Pages. Always nice to listen to Carl and Richard.
How work design can reignite tremendous results (Modern Mentor) - Two Modern Mentor episodes this week, I love those shorter, concentrated episodes. This one focuses on ideas to help leaders redesign how work gets done.
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
From Docker's security practices to the latest in GPT-5 discussions, there's quite a mix of topics to dive into. I particularly enjoyed the thought-provoking piece about junior developers in the age of LLMs - it's a conversation we should all be having.
As always, grab your favorite beverage, and let's explore what caught my attention this week!
DevOps
Practitioner's View: How Docker Enables Security by Default (Pedro Ignácio, Denis Cruz Rodrigues) - Improving the culture can be a challenge, but security is worth the effort. This post lists your first targets if you want to go that way, and explains why it's important.
AI
Announcing the NuGet MCP Server Preview - .NET Blog (Jeff Kluge) - Oh! That's a cool one, looking forward to trying it and seeing if you can help me when I'm searching for a package but I don't know the name or don't remember the name
The GitHub Prompt Injection Data Heist | Docker (Ajeet Singh Raina) - Yes! This post talks about this injection story. But there is more! It shares how to prevent it, and all the things that we need to be aware of those dangers.
SPI 885: What's Working on Social Media Right Now (The Smart Passive Income Online Business and Blogging Podcast) - Social medias are evolving and this podcast episode talk about how we should adapt and change the way we do business with it.
476: GPT-5 Is Here, What's next? (Merge Conflict) - As much as I like the new GPT-5, they made me realized that I was thinking exactly like them! I won't spoil anything but it is a great episode where James is in fire! ;)
Miscellaneous
The role of junior developers in the world of LLMs (Oren Eini) - This is a great question. AI is definitely affecting the job market. However, this interesting post denies the annihilation of junior roles. What do you think?
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
This week post collects concise links and takeaways across .NET, AI, Docker, open source security, DevOps, and broader developer topics. From the .NET Conf call for content and Copilot prompts to Docker MCP tooling, container debugging tips, running .NET as WASM, and a fresh look at the 10x engineer idea.
Running .NET in the browser without Blazor (Andrew Lock) - I never thought about it but it's true we can execute .NET code as WASM without Blazor. This tutorial shows you all the code.
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
This week’s notes cover GenAI vs agentic AI, fresh Docker and Aspire news, how to run WordPress in containers, and building apps with React and .NET. Plus a few podcasts worth a listen.
Does it Make Sense to Run WordPress in Docker? (Lukas Mauser) - Looking at different options to run WordPress? Check out this blog post. All the code to do it in a docker container is shared and also details the reasons why you should do it or not
Introducing Reka Research: Your AI Research Assistant
Meet Reka Research a powerful AI agent that can search the web and analyze your files to answer complex questions in minutes. Whether you're staying up to date with AI news, screening resumes, or researching technical topics, Reka Research does the heavy lifting for you.
What Makes Reka Research Special?
Reka Research stands out in four key areas:
Top Performance: Best in class results on research benchmarks
Fast Results: Get thorough answers in 1-3 minutes
Full Transparency: See exactly how the AI reached its conclusions. All steps are visible.
Smart Web Search That Actually Works
Ever wished you could ask someone to research the latest AI developments while you focus on other work? That's exactly what Reka Research does.
Watch how it works:
In this demo, Jess and Sharath shows how Reka Research can automatically gather the most important AI news from the past week. The AI visits multiple websites, takes notes, and presents a clean summary with sources. You can even restrict searches to specific domains or set limits on how many sites to check.
File Search for Your Private Documents
Sometimes the information you need isn't on the web - it's in your company's documents, meeting notes, or file archives. Reka Research can search through thousands of private files to find exactly what you're looking for.
See it in action:
In this example, ess and Sharath shows how HR teams can use Reka Research to quickly screen resumes. Instead of manually reviewing hundreds of applications, the AI finds candidates who meet specific requirements (like having a computer science degree and 3+ years of backend experience) in seconds!
Writing Better Prompts Gets Better Results
Like any AI tool, Reka Research works best when you know how to ask the right questions. The key is being specific about what you want and providing context.
Learn the techniques:
Jess and Yi shares practical tips for getting the most out of Reka Research. Instead of asking "summarize meeting minutes," try "summarize April meeting minutes about public participation." The more specific you are, the better your results will be.
Ready to Try Reka Research?
Reka Research is currently available for everyone! Try it via the playground, or using directly the API. Whether you're researching competitors, analyzing documents, or staying current with industry trends, it can save you hours of work.
Want to learn more and connect with other users? Join our Discord community where you can:
