You know, we had a Thanksgiving weekend in the US a few weeks ago.

And so I had a chance to say like, "what else can one do over Thanksgiving other than build?" And so I built an app of my own, using all of the stuff that Karan was showing.

So this is my Azure environment.

And by the way, this is my regular PC that I travel with, so hopefully nothing happens.

But, and so this is, it's in fact, I have this app deployed, I think, in, south central Canada.

This is my GitHub repo.

And, it's fun, right?

So I kind of have my typical setup, in fact, is, Windows 365, which travels with me essentially everywhere.

And then in there, obviously I have my GitHub, and then it's Codespaces.

So it's kind of like turtles all the way.

So you have your code spaces running on, GitHub in Windows 365 instance.

And then, the idea that now you can go in.

And my favorite thing of course, to do is your, you know, come in, in the morning and just start issuing, whatever coding tasks.

And so this is where I go and just, I usually fire off five or six things.

It creates, five or six draft branches.

And then ultimately, at the end of the day, I go back and mostly delete the branches, but there is a PR or two, I'll accept and go on and, work with it.

So it's fun.

And then the fact that you have all these models, in fact, I think now, I'm mostly using, a lot more codex-max, it's fantastic.

It's fast. I'm using obviously Claude.

So, Claude Opus 4.5 as well.

But, the thing that I've now gotten used to is I have enough trust to just say auto and it picks.

And so, if I'm just, really, I don't I want to really be efficient with my token limits.

And so therefore picking auto seems to be really, really a good way to go about it.

So anyway, so great I did all this, so what the heck did I build?

What I said is, okay, what's my dream?

My dream is to figure out how to get a job, in this Copilot team.

So I said, Matt, I like your deep research stuff, but I want to add a lot more to deep research, so I build my own deep research.

And so, with all these models available, I said, okay, what if I could start putting new decision frameworks?

So one decision framework, Ondrej Karpathy recently talked about this LLM council, which I love a lot.

So I implemented this idea that you can now have all the models available to you.

So GPT, Opus, Gemini, Kimi K2, Grok, what have you, all of these models.

And then you can select a chairman.

So you have council members or the selection committee.

And then you have a chair.

And then you can go issue any query and have it come back and tell you what it thinks.

Then another decision framework I implemented was this thing called DxO.

We did this actually in healthcare first.

So this was done. There you go.

Now let's see.

Let's see how all my oh, it's so fantastic.

So, DxO is a thing, as I said, we implemented, for healthcare and you have specific roles.

So you have a lead researcher.

And the lead researcher in this case is Opus.

It sort of does the breadth first research.

Then you have another role, which is a critical reviewer.

In this case, I am selected 5.1 GPT 5.1 And their role is to find any method errors.

Especially bias and recency bias, what have you.

Then we have a data analyst.

So I picked or I picked a domain expert Gemini I then said data analyst, I picked Kimi K2.

So, this when we published the DxO paper, it performed better than any one frontier model.

So this is in the context of very high stakes health outcomes.

And I said, hey, I want same thing for any decision.

I want to make. So I implemented that.

So I implemented another one as well called Ensemble.

So this is basically use all models and as just essentially a set of MCP servers, anonymize the responses.

So take out even who is responding with what.

Give them, alpha, beta, gamma and then synthesize into one, response.

So these are three decision frameworks.

In fact, I even extended it, by the way, I built a shopping thing.

I built even a finance thing, but basically decision frameworks.

And then of course, like a good sort of crazy South Asian, cricket fanatic.

What do you use it for?

To select the all time best Indian test cricket team, especially in a time like this.

After what happened in the last test series, I think it's time to get to work.

So what I did is I'll show you the history side if I go ahead.

And in fact, you will see, that mostly that's what I've been using it for, which is the MLB lineup was also just crazy.

It is fantastic.

But the test team, so I let me go show you some of the stuff.

So this is the, what happened.

This is the chairman synthesis.

So this is the AI Council, so it came back and it says, you know what?

I figured out all of the, Sunil opens Sehwag opens with him.

Dravid makes it obviously and what have you.

But look at this areas of complete consensus.

is Gavaskar, Sehwag, Dravid, Tendulkar, Kohli, Kapil, Dev, Ashwin, and Bumrah.

Key debates.

Oh man. VVS, do you have him or you don't?

And look at the way it's sort of, made the decision.

Phi-1 basically said and Claude, inclusion or Laxman was heavily weighted because of the crisis management.

And as a good Hyderabadi, I love GPT 5.1 and Claude.

And of course Kumble would say, "this is pretty cool".

Do you really need left arm swing or you need, whatever you call Kumble bowling.

Which is obviously the stats one out, 619 wickets and, and so they selected and oh, and then captaincy debate.

Kohli vs Dhoni and they selected Kohli.

And so it goes off and then annotates.

What I love by the way is I implemented it as even a streaming thing.

it is not deployed in south central Canada.

I would sort of show it to you, but, it's just nice to see.

It's essentially like a chain of debate, not a chain of thought.

So I can see the morals debate and then synthesize.

So anyway, so that's one example.

DxO is another one.

This is very neat because, what it does is you can see by raw, right.

So I see the first the exhaustive search of the lead researcher.

It gives me again what did, what are all the things the critical reviewer will find like, okay, what are the method problems and gaps and weaknesses.

So for example, era bias.

Classic thing that happens, when you sort of compare across generations, you make all kinds of mistakes because you don't adjust for, any of the stats and the difficulty of the wickets, I mean, walking out in a West Indies or an English wicket there is not covered.

I mean, how does one play even in any anyway?

So to be able to take all of that into account and then see the debate between the various models to resolve.

So anyway, so I've had and then the same thing with ensemble as well.

So the point I wanted to make was I built this over maybe a couple of hours, and now I'm constantly refining it.

In fact, one of my hopes, as I said, is to be able to I by the way, this is all going to come to Copilot, and I'm convincing my friends and they're saying, yeah, you can apply as a junior product manager if you are competent enough.

So I'm still in the process of interviewing, but not that said, I think all of this will come because this is to me the next generation of metacognition.

So if you think about these decision frameworks, you have all these agents, you're working with agents, but the metacognition is still us.

And this is tools for metacognition is how I think about it.

And so, to me, building out these type of frameworks, building out these type of agents is interesting to select the Indian cricket team, but think about whether it's a supply chain decision, whether it's a healthcare decision, whether it is a finance decision, these type of chain of debates with multiple agents participating, is going to be a lot of what we are going to all, build in our systems, in our agentic system.