by Joche Ojeda | Feb 16, 2026 | CLI, Github Copilot, SDK
Embedding GitHub Copilot Inside a DevExpress XAF Application
GitHub repository:
https://github.com/egarim/XafGitHubCopilot
Repository Structure (correct paths)
Startup (reference file you shared)
Blazor Startup:
/XafGitHubCopilot/XafGitHubCopilot.Blazor.Server/Startup.cs
Key Files (correct links)
Copilot SDK wiring (DI)
Tool calling (function calling)
XAF controllers
The Day I Integrated GitHub Copilot SDK Inside My XAF App (Part 1) | Joche Ojeda
by Joche Ojeda | Feb 16, 2026 | A.I, Apps, CLI, Github Copilot, SDK
A strange week
This week I was going to the university every day to study Russian.
Learning a new language as an adult is a very humbling experience. One moment you are designing enterprise architectures, and the next moment you are struggling to say:
me siento bien
which in Russian is: я чувствую себя хорошо
So like any developer, I started cheating immediately.
I began using AI for everything:
- ChatGPT to review my exercises
- GitHub Copilot inside VS Code correcting my grammar
- Sometimes both at the same time
It worked surprisingly well. Almost too well.
At some point during the week, while going back and forth between my Russian homework and my development work, I noticed something interesting.
I was using several AI tools, but the one I kept returning to the most — without even thinking about it — was GitHub Copilot inside Visual Studio Code.
Not in the browser. Not in a separate chat window. Right there in my editor.
That’s when something clicked.
Two favorite tools
XAF is my favorite application framework. I’ve built countless systems with it — ERPs, internal tools, experiments, prototypes.
GitHub Copilot has become my favorite AI agent.
I use it constantly:
- writing code
- reviewing ideas
- fixing small mistakes
- even correcting my Russian exercises
And while using Copilot so much inside Visual Studio Code, I started thinking:
What would it feel like to have Copilot inside my own applications?
Not next to them. Inside them.
That idea stayed in my head for a few days until curiosity won.
The innocent experiment
I discovered the GitHub Copilot SDK.
At first glance it looked simple: a .NET library that allows you to embed Copilot into your own applications.
My first thought:
“Nice. This should take 30 minutes.”
Developers should always be suspicious of that sentence.
Because it never takes 30 minutes.
First success (false confidence)
The initial integration was surprisingly easy.
I managed to get a basic response from Copilot inside a test environment. Seeing AI respond from inside my own application felt a bit surreal.
For a moment I thought:
Done. Easy win.
Then I tried to make it actually useful.
That’s when the adventure began.
The rabbit hole
I didn’t want just a chatbot.
I wanted an agent that could actually interact with the application.
Ask questions. Query data. Help create things.
That meant enabling tool calling and proper session handling.
And suddenly everything started failing.
Timeouts. Half responses. Random behavior depending on the model. Sessions hanging for no clear reason.
At first I blamed myself.
Then my integration. Then threading. Then configuration.
Three or four hours later, after trying everything I could think of, I finally discovered the real issue:
It wasn’t my code.
It was the model.
Some models were timing out during tool calls. Others worked perfectly.
The moment I switched models and everything suddenly worked was one of those small but deeply satisfying developer victories.
You know the moment.
You sit back. Look at the screen. And just smile.
The moment it worked
Once everything was connected properly, something changed.
Copilot stopped feeling like a coding assistant and started feeling like an agent living inside the application.
Not in the IDE. Not in a browser tab. Inside the system itself.
That changes the perspective completely.
Instead of building forms and navigation flows, you start thinking:
What if the user could just ask?
Instead of:
- open this screen
- filter this grid
- generate this report
You imagine:
- “Show me what matters.”
- “Create what I need.”
- “Explain this data.”
The interface becomes conversational.
And once you see that working inside your own application, it’s very hard to unsee it.
Why this experiment mattered to me
This wasn’t about building a feature for a client. It wasn’t even about shipping production code.
Most of my work is research and development. Prototypes. Ideas. Experiments.
And this experiment changed the way I see enterprise applications.
For decades we optimized screens, menus, and workflows.
But AI introduces a completely different interaction model.
One where the application is no longer just something you navigate.
It’s something you talk to.
Also… Russian homework
Ironically, this whole experiment started because I was trying to survive my Russian classes.
Using Copilot to correct grammar. Using AI to review exercises. Switching constantly between tools.
Eventually that daily workflow made me curious:
What happens if Copilot is not next to my application, but inside it?
Sometimes innovation doesn’t start with a big strategy.
Sometimes it starts with curiosity and a small personal frustration.
What comes next
This is just the beginning.
Now that AI can live inside applications:
- conversations can become interfaces
- tools can be invoked by language
- workflows can become more flexible
We are moving from:
software you operate
to:
software you collaborate with
And honestly, that’s a very exciting direction.
Final thought
This entire journey started with a simple curiosity while studying Russian and writing code in the same week.
A few hours of experimentation later, Copilot was living inside my favorite framework.
And now I can’t imagine going back.
Note: The next article will go deep into the technical implementation — the architecture, the service layer, tool calling, and how I wired everything into XAF for both Blazor and WinForms.
by Joche Ojeda | Feb 11, 2026 | A.I
My last two articles have been about one idea: closing the loop with AI.
Not “AI-assisted coding.” Not “AI that helps you write functions.”
I’m talking about something else entirely.
I’m talking about building systems where the agent writes the code, tests the code, evaluates the result,
fixes the code, and repeats — without me sitting in the middle acting like a tired QA engineer.
Because honestly, that middle position is the worst place to be.
You get exhausted. You lose objectivity. And eventually you look at the project and think:
everything here is garbage.
So the goal is simple:
Remove the human from the middle of the loop.
Place the human at the end of the loop.
The human should only confirm: “Is this what I asked for?”
Not manually test every button.
The Real Question: How Do You Close the Loop?
There isn’t a single answer. It depends on the technology stack and the type of application you’re building.
So far, I’ve been experimenting with three environments:
- Console applications
- Web applications
- Windows Forms applications (still a work in progress)
Each one requires a slightly different strategy.
But the core principle is always the same:
The agent must be able to observe what it did.
If the agent cannot see logs, outputs, state, or results — the loop stays open.
Console Applications: The Easiest Loop to Close
Console apps are the simplest place to start.
My setup is minimal and extremely effective:
- Serilog writing structured logs
- Logs written to the file system
- Output written to the console
Why both?
Because the agent (GitHub Copilot in VS Code) can run the app, read console output, inspect log files,
decide what to fix, and repeat.
No UI. No browser. No complex state.
Just input → execution → output → evaluation.
If you want to experiment with autonomous loops, start here. Console apps are the cleanest lab environment you’ll ever get.
Web Applications: Where Things Get Interesting
Web apps are more complex, but also more powerful.
My current toolset:
- Serilog for structured logging
- Logs written to filesystem
- SQLite for loop-friendly database inspection
- Playwright for automated UI testing
Even if production uses PostgreSQL or SQL Server, I use SQLite during loop testing.
Not for production. For iteration.
The SQLite CLI makes inspection trivial.
The agent can call the API, trigger workflows, query SQLite directly, verify results, and continue fixing.
That’s a full feedback loop. No human required.
Playwright: Giving the Agent Eyes
For UI testing, Playwright is the key.
You can run it headless (fully autonomous) or with UI visible (my preferred mode).
Yes, I could remove myself completely. But I don’t.
Right now I sit outside the loop as an observer.
Not a tester. Not a debugger. Just watching.
If something goes completely off the rails, I interrupt.
Otherwise, I let the loop run.
This is an important transition:
From participant → to observer.
The Windows Forms Problem
Now comes the tricky part: Windows Forms.
Console apps are easy. Web apps have Playwright.
But desktop UI automation is messy.
Possible directions I’m exploring:
- UI Automation APIs
- WinAppDriver
- Logging + state inspection hybrid approach
- Screenshot-based verification
- Accessibility tree inspection
The goal remains the same: the agent must be able to verify what happened without me.
Once that happens, the loop closes.
What I’ve Learned So Far
1) Logs Are Everything
If the agent cannot read what happened, it cannot improve. Structured logs > pretty logs. Always.
2) SQLite Is the Perfect Loop Database
Not for production. For iteration. The ability to query state instantly from CLI makes autonomous debugging possible.
3) Agents Need Observability, Not Prompts
Most people focus on prompt engineering. I focus on observability engineering.
Give the agent visibility into logs, state, outputs, errors, and the database. Then iteration becomes natural.
4) Humans Should Validate Outcomes — Not Steps
The human should only answer: “Is this what I asked for?” That’s what the agent is for.
My Current Loop Architecture (Simplified)
Specification → Agent writes code → Agent runs app → Agent tests → Agent reads logs/db →
Agent fixes → Repeat → Human validates outcome
If the loop works, progress becomes exponential.
If the loop is broken, everything slows down.
My Question to You
This is still evolving. I’m refining the process daily, and I’m convinced this is how development will work from now on:
agents running closed feedback loops with humans validating outcomes at the end.
So I’m curious:
- What tooling are you using?
- How are you creating feedback loops?
- Are you still inside the loop — or already outside watching it run?
Because once you close the loop…
you don’t want to go back.
by Joche Ojeda | Feb 9, 2026 | A.I
I wrote my previous article about closing the loop for agentic development earlier this week, although the ideas themselves have been evolving for several days. This new piece is simply a progress report: how the approach is working in practice, what I’ve built so far, and what I’m learning as I push deeper into this workflow.
Short version: it’s working.
Long version: it’s working really well — but it’s also incredibly token-hungry.
Let’s talk about it.
A Familiar Benchmark: The Activity Stream Problem
Whenever I want to test a new development approach, I go back to a problem I know extremely well: building an activity stream.
An activity stream is basically the engine of a social network — posts, reactions, notifications, timelines, relationships. It touches everything:
- Backend logic
- UI behavior
- Realtime updates
- State management
- Edge cases everywhere
I’ve implemented this many times before, so I know exactly how it should behave. That makes it the perfect benchmark for agentic development. If the AI handles this correctly, I know the workflow is solid.
This time, I used it to test the closing-the-loop concept.
The Current Setup
So far, I’ve built two main pieces:
- An MCP-based project
- A Blazor application implementing the activity stream
But the real experiment isn’t the app itself — it’s the workflow.
Instead of manually testing and debugging, I fully committed to this idea:
The AI writes, tests, observes, corrects, and repeats — without me acting as the middleman.
So I told Copilot very clearly:
- Don’t ask me to test anything
- You run the tests
- You fix the issues
- You verify the results
To make that possible, I wired everything together:
- Playwright MCP for automated UI testing
- Serilog logging to the file system
- Screenshot capture of the UI during tests
- Instructions to analyze logs and fix issues automatically
So the loop becomes:
write → test → observe → fix → retest
And honestly, I love it.
My Surface Is Working. I’m Not Touching It.
Here’s the funny part.
I’m writing this article on my MacBook Air.
Why?
Because my main development machine — a Microsoft Surface laptop — is currently busy running the entire loop by itself.
I told Copilot to open the browser and actually execute the tests visually. So it’s navigating the UI, filling forms, clicking buttons, taking screenshots… all by itself.
And I don’t want to touch that machine while it’s working.
It feels like watching a robot doing your job. You don’t interrupt it mid-task. You just observe.
So I switched computers and thought: “Okay, this is a perfect moment to write about what’s happening.”
That alone says a lot about where this workflow is heading.
Watching the Loop Close
Once everything was wired together, I let it run.
The agent:
- Writes code
- Runs Playwright tests
- Reads logs
- Reviews screenshots
- Detects issues
- Fixes them
- Runs again
Seeing the system self-correct without constant intervention is incredibly satisfying.
In traditional AI-assisted development, you often end up exhausted:
- The AI gets stuck
- You explain the issue
- It half-fixes it
- You explain again
- Something else breaks
You become the translator and debugger for the model.
With a self-correcting loop, that burden drops dramatically. The system can fail, observe, and recover on its own.
That changes everything.
The Token Problem (Yes, It’s Real)
There is one downside: this workflow is extremely token hungry.
Last month I used roughly 700% more tokens than usual. This month, and we’re only around February 8–9, I’ve already used about 200% of my normal limits.
Why so expensive?
Because the loop never sleeps:
- Test execution
- Log analysis
- Screenshot interpretation
- Code rewriting
- Retesting
- Iteration
Every cycle consumes tokens. And when the system is autonomous, those cycles happen constantly.
Model Choice Matters More Than You Think
Another important detail: not all models consume tokens equally inside Copilot.
Some models count as:
- 3× usage
- 1× usage
- 0.33× usage
- 0× usage
For example:
- Some Anthropic models are extremely good for testing and reasoning
- But they can count as 3× token usage
- Others are cheaper but weaker
- Some models (like GPT-4 Mini or GPT-4o in certain Copilot tiers) count as 0× toward limits
At some point I actually hit my token limits and Copilot basically said: “Come back later.”
It should reset in about 24 hours, but in the meantime I switched to the 0× token models just to keep the loop running.
The difference in quality is noticeable.
The heavier models are much better at:
- Debugging
- Understanding logs
- Self-correcting
- Complex reasoning
The lighter or free models can still work, but they struggle more with autonomous correction.
So model selection isn’t just about intelligence — it’s about token economics.
Why It’s Still Worth It
Yes, this approach consumes more tokens.
But compare that to the alternative:
- Sitting there manually testing
- Explaining the same bug five times
- Watching the AI fail repeatedly
- Losing mental energy on trivial fixes
That’s expensive too — just not measured in tokens.
I would rather spend tokens than spend mental fatigue.
And realistically:
- Models get cheaper every month
- Tooling improves weekly
- Context handling improves
- Local and hybrid options are evolving
What feels expensive today might feel trivial very soon.
MCP + Blazor: A Perfect Testing Ground
So far, this workflow works especially well for:
- MCP-based systems
- Blazor applications
- Known benchmark problems
Using a familiar problem like an activity stream lets me clearly measure progress. If the agent can build and maintain something complex that I already understand deeply, that’s a strong signal.
Right now, the signal is positive.
The loop is closing. The system is self-correcting. And it’s actually usable.
What Comes Next
This article is just a status update.
The next one will go deeper into something very important:
How to design self-correcting mechanisms for agentic development.
Because once you see an agent test, observe, and fix itself, you don’t want to go back to manual babysitting.
For now, though:
The idea is working. The workflow feels right. It’s token hungry. But absolutely worth it.
Closing the loop isn’t theory anymore — it’s becoming a real development style.
by Joche Ojeda | Feb 9, 2026 | A.I
Last week I was in Sochi on a ski trip. Instead of skiing, I got sick.
So I spent a few days locked in a hotel room, doing what I always do when I can’t move much: working. Or at least what looks like work. In reality, it’s my hobby.
YouTube wasn’t working well there, so I downloaded a few episodes in advance. Most of them were about OpenClaw and its creator, Peter Steinberger — also known for building PSPDFKit.
What started as passive watching turned into one of those rare moments of clarity you only get when you’re forced to slow down.
Shipping Code You Don’t Read (In the Right Context)
In one of the interviews, Peter said something that immediately caught my attention: he ships code he doesn’t review.
At first that sounds reckless. But then I realized… I sometimes do the same.
However, context matters.
Most of my daily work is research and development. I build experimental systems, prototypes, and proofs of concept — either for our internal office or for exploring ideas with clients. A lot of what I write is not production software yet. It’s exploratory. It’s about testing possibilities.
In that environment, I don’t always need to read every line of generated code.
If the use case works and the tests pass, that’s often enough.
I work mainly with C#, ASP.NET, Entity Framework, and XAF from DevExpress. I know these ecosystems extremely well. So if something breaks later, I can go in and fix it myself. But most of the time, the goal isn’t to perfect the implementation — it’s to validate the idea.
That’s a crucial distinction.
When writing production code for a customer, quality and review absolutely matter. You must inspect, verify, and ensure maintainability. But when working on experimental R&D, the priority is different: speed of validation and clarity of results.
In research mode, not every line needs to be perfect. It just needs to prove whether the idea works.
Working “Without Hands”
My real goal is to operate as much as possible without hands.
By that I mean minimizing direct human interaction with implementation. I want to express intent clearly enough so agents can execute it.
If I can describe a system precisely — especially in domains I know deeply — then the agent should be able to build, test, and refine it. My role becomes guiding and validating rather than manually constructing everything.
This is where modern development is heading.
The Problem With Vibe Coding
Peter talked about something that resonated deeply: when you’re vibe coding, you produce a lot of AI slop.
You prompt. The AI generates. You run it. It fails. You tweak. You run again. Still wrong. You tweak again.
Eventually, the human gets tired.
Even when you feel close to a solution, it’s not done until it’s actually done. And manually pushing that process forward becomes exhausting.
This is where many AI workflows break down. Not because the AI can’t generate solutions — but because the loop still depends too heavily on human intervention.
Closing the Loop
The key idea is simple and powerful: agentic development works when the agent can test and correct itself.
You must close the loop.
Instead of: human → prompt → AI → human checks → repeat
You want: AI → builds → tests → detects errors → fixes → tests again → repeat
The agent needs tools to evaluate its own output.
When AI can run tests, detect failures, and iterate automatically, something shifts. The process stops being experimental prompting and starts becoming real engineering.
Spec-Driven vs Self-Correcting Systems
Spec-driven development still matters. Some people dismiss it as too close to waterfall, but every methodology has flaws.
The real evolution is combining clear specifications with self-correcting loops.
The human defines:
- The specification
- The expected behavior
- The acceptance criteria
Then the AI executes, tests, and refines until those criteria are satisfied.
The human doesn’t need to babysit every iteration. The human validates the result once the loop is closed.
Engineering vs Parasitic Ideas
There’s a concept from a book about parasitic ideas.
In social sciences, parasitic ideas can spread because they’re hard to disprove. In engineering, bad ideas fail quickly.
If you design a bridge incorrectly, it collapses. Reality provides immediate feedback.
Software — especially AI-generated software — needs the same grounding in reality. Without continuous testing and validation, generated code can drift into something that looks plausible but doesn’t work.
Closing the loop forces ideas to confront reality.
Tests are that reality.
Taking the Human Out of the Repetitive Loop
The goal isn’t removing humans entirely. It’s removing humans from repetitive validation.
The human should:
- Define the specification
- Define what “done” means
- Approve the final result
The AI should:
- Implement
- Test
- Detect issues
- Fix itself
- Repeat until success
When that happens, development becomes scalable in a new way. Not because AI writes code faster — but because AI can finish what it starts.
What I Realized in That Hotel Room
Getting sick in Sochi wasn’t part of the plan. But it forced me to slow down long enough to notice something important.
Most friction in modern development isn’t writing code. It’s closing loops.
We generate faster than we validate. We start more than we finish. We rely on humans to constantly re-check work that machines could verify themselves.
In research and experimental work, it’s fine not to inspect every line — as long as the system proves its behavior. In production work, deeper review is essential. Knowing when each approach applies is part of modern engineering maturity.
The future of agentic development isn’t just better models. It’s better loops.
Because in the end, nothing is finished until the loop is closed.
