What If Your Chip Design Team Moved Like a Single Body? — Abduallah Mohamed, AIDAChip

>> Hello everyone. >> Hello everyone. Um Um Um So, I want to start with a simple So, I want to start with a simple So, I want to start with a simple question. question. question. What if your team or your org or company What if your team or your org or company What if your team or your org or company moves like a single body? moves like a single body? moves like a single body? I'm Abdullah Muhammad, the VP of AIML at I'm Abdullah Muhammad, the VP of AIML at I'm Abdullah Muhammad, the VP of AIML at A Data Chef. A Data Chef. A Data Chef. And today was supposed to be Khalid with And today was supposed to be Khalid with And today was supposed to be Khalid with me to present this, but he's he's down me to present this, but he's he's down me to present this, but he's he's down with our development partner at the with our development partner at the with our development partner at the moment. moment. moment. So, I will be presenting the whole So, I will be presenting the whole So, I will be presenting the whole presentation for today. presentation for today. presentation for today. So, let's go for the next slide. So, let's go for the next slide. So, let's go for the next slide. So, how many of you have been attending So, how many of you have been attending So, how many of you have been attending the World Cup soccer or watching some the World Cup soccer or watching some the World Cup soccer or watching some games on ice? We have a couple of fans. games on ice? We have a couple of fans. games on ice? We have a couple of fans. Yeah, it's over all over the place. And Yeah, it's over all over the place. And Yeah, it's over all over the place. And imagine for a moment, just a single imagine for a moment, just a single imagine for a moment, just a single moment, you are a soccer player, all moment, you are a soccer player, all moment, you are a soccer player, all right? right? right? And And And if you are a soccer player, you have if you are a soccer player, you have if you are a soccer player, you have this intent the moment you go into the this intent the moment you go into the this intent the moment you go into the field, you just going to run and score a field, you just going to run and score a field, you just going to run and score a goal. goal. goal. This is what you want to do. This is what you want to do. This is what you want to do. And for the second thing, you have this And for the second thing, you have this And for the second thing, you have this knowledge that you've been accumulated knowledge that you've been accumulated knowledge that you've been accumulated through your training the whole day, through your training the whole day, through your training the whole day, your exercises with your coach, and the your exercises with your coach, and the your exercises with your coach, and the best practices and the videos you have best practices and the videos you have best practices and the videos you have watched.

watched. watched. And you at the moment in the field like And you at the moment in the field like And you at the moment in the field like the moment of truth that you are there, the moment of truth that you are there, the moment of truth that you are there, you combine both of the intent and you combine both of the intent and you combine both of the intent and knowledge knowledge knowledge and compound both of them. and compound both of them. and compound both of them. And through your nervous system, you And through your nervous system, you And through your nervous system, you execute to achieve your goal. execute to achieve your goal. execute to achieve your goal. And we can call this, in a sense, And we can call this, in a sense, And we can call this, in a sense, you are being self-aligned as a single you are being self-aligned as a single you are being self-aligned as a single entity by yourself. And accept the fact that a soccer team And accept the fact that a soccer team or a football team, depending where or a football team, depending where or a football team, depending where you're coming from, is not a single you're coming from, is not a single you're coming from, is not a single player. It's actually player. It's actually player. It's actually 11 players. 11 players. 11 players. And on the field, you are up against And on the field, you are up against And on the field, you are up against another team with 11 players they another team with 11 players they another team with 11 players they playing against you. And at this moment playing against you. And at this moment playing against you. And at this moment it's not about your individual skills, it's not about your individual skills, it's not about your individual skills, it's about how your team working it's about how your team working it's about how your team working together well. together well. together well. So, So, So, in general in general in general like the team keep changing and like the team keep changing and like the team keep changing and everything is getting harder and harder everything is getting harder and harder everything is getting harder and harder and the team that wins actually the team and the team that wins actually the team and the team that wins actually the team that the most aligned that the most aligned that the most aligned in both of the both of teams. So, in in both of the both of teams. So, in in both of the both of teams. So, in short we can say alignment beats short we can say alignment beats short we can say alignment beats individual skills.

individual skills. individual skills. >> [snorts] >> [snorts] >> [snorts] >> Okay. >> Okay. >> Okay. Now, what if your team is over 50 Now, what if your team is over 50 Now, what if your team is over 50 engineers or 50 players? engineers or 50 players? engineers or 50 players? This is completely changes the whole This is completely changes the whole This is completely changes the whole scene right now. scene right now. scene right now. So, everyone at these days So, everyone at these days So, everyone at these days we empower the engineers with AI tools, we empower the engineers with AI tools, we empower the engineers with AI tools, AI agents and we want to increase the AI agents and we want to increase the AI agents and we want to increase the productivity. productivity. productivity. But we know from literature that the But we know from literature that the But we know from literature that the more people you have, the quadratic term more people you have, the quadratic term more people you have, the quadratic term of communication between them and of communication between them and of communication between them and alignment them keep growing and keep alignment them keep growing and keep alignment them keep growing and keep growing. And at a specific point growing. And at a specific point growing. And at a specific point actually it actually starts to going declining. it actually starts to going declining. Your throughput actually is not what you Your throughput actually is not what you Your throughput actually is not what you getting. getting. getting. It's diminishing cost. It's diminishing cost. It's diminishing cost. So, everyone trying to solve this linear So, everyone trying to solve this linear So, everyone trying to solve this linear problem of more tools and more stuff but problem of more tools and more stuff but problem of more tools and more stuff but nobody actually tackling the quadratic nobody actually tackling the quadratic nobody actually tackling the quadratic term over there. term over there. term over there. And this is why the alignment is And this is why the alignment is And this is why the alignment is important. If you are able to change important. If you are able to change important. If you are able to change this quadratic term into a linear term this quadratic term into a linear term this quadratic term into a linear term or build a multi-layer AI system that or build a multi-layer AI system that or build a multi-layer AI system that will solve this problem.

Okay, moving into ship design. Ship Okay, moving into ship design. Ship design is design is design is a different story. a different story. a different story. If you are in software company, you have If you are in software company, you have If you are in software company, you have a bug in your software, you can ship a a bug in your software, you can ship a a bug in your software, you can ship a batch to fix it. You can roll out a new batch to fix it. You can roll out a new batch to fix it. You can roll out a new version. It's most of the time is version. It's most of the time is version. It's most of the time is doable. doable. doable. But in ships, you can't do this in But in ships, you can't do this in But in ships, you can't do this in ships. It's hardware, fixed it on ships. It's hardware, fixed it on ships. It's hardware, fixed it on silicon has been printed. silicon has been printed. silicon has been printed. And if you're going to do this, there is And if you're going to do this, there is And if you're going to do this, there is a cost actually, we call it the risk a cost actually, we call it the risk a cost actually, we call it the risk band cost. band cost. band cost. On average between chip design companies On average between chip design companies On average between chip design companies about $50 million. about $50 million. about $50 million. And for some companies like being 1 And for some companies like being 1 And for some companies like being 1 month late in the market, it's a make or month late in the market, it's a make or month late in the market, it's a make or break for them. break for them. break for them. And we spoke to many practitioners in And we spoke to many practitioners in And we spoke to many practitioners in the field. On average like 15 the field. On average like 15 the field. On average like 15 practitioner and we found that most of practitioner and we found that most of practitioner and we found that most of them pointed towards the same problem. them pointed towards the same problem. them pointed towards the same problem. That we spend 70% of our time doing That we spend 70% of our time doing That we spend 70% of our time doing alignment. alignment. alignment. Alignment to make sure that once we Alignment to make sure that once we Alignment to make sure that once we print the chip, nothing is there. And print the chip, nothing is there. And print the chip, nothing is there. And one of the key words that we heard and one of the key words that we heard and one of the key words that we heard and still resonating that the most still resonating that the most still resonating that the most successful chip organization are not the successful chip organization are not the successful chip organization are not the one with the best engineers, one with the best engineers, one with the best engineers, but they are the most aligned organized.

We start with bottom figure like the We start with bottom figure like the fragmented intent and decision. You fragmented intent and decision. You fragmented intent and decision. You attend couple of meetings, you talk attend couple of meetings, you talk attend couple of meetings, you talk about decisions, what you're going to do about decisions, what you're going to do about decisions, what you're going to do next. You have the specs written next. You have the specs written next. You have the specs written everywhere, you have the Slack messages, everywhere, you have the Slack messages, everywhere, you have the Slack messages, you have emails, everything is you have emails, everything is you have emails, everything is fragmented over there. fragmented over there. fragmented over there. And then we go into a second part, which And then we go into a second part, which And then we go into a second part, which is the knowledge. is the knowledge. is the knowledge. Nobody updates wikis, right? Many of us Nobody updates wikis, right? Many of us Nobody updates wikis, right? Many of us has wikis. has wikis. has wikis. They've been collecting dust for years They've been collecting dust for years They've been collecting dust for years and the code keep evolving outside the and the code keep evolving outside the and the code keep evolving outside the wikis, it's not over there. wikis, it's not over there. wikis, it's not over there. And now we have the tools that you And now we have the tools that you And now we have the tools that you execute with, which comes with many many execute with, which comes with many many execute with, which comes with many many fractions. fractions. fractions. And these tools like the data is lost And these tools like the data is lost And these tools like the data is lost over there, what input, what output, over there, what input, what output, over there, what input, what output, what results, most of the time are not what results, most of the time are not what results, most of the time are not being captured. being captured. being captured. And what you see here is not something And what you see here is not something And what you see here is not something we came with like draw from our imagine, we came with like draw from our imagine, we came with like draw from our imagine, this is actually how is it today. We this is actually how is it today. We this is actually how is it today. We wrote from inside the companies and from wrote from inside the companies and from wrote from inside the companies and from the backgrounds of the people we have in the backgrounds of the people we have in the backgrounds of the people we have in our team. our team. our team. And what we're trying to solve here is And what we're trying to solve here is And what we're trying to solve here is building a multi-layer AI building a multi-layer AI building a multi-layer AI with a shared nervous system. Instead of with a shared nervous system. Instead of with a shared nervous system. Instead of having having having scattered knowledge or scattered intent scattered knowledge or scattered intent scattered knowledge or scattered intent all over the place, we build a living all over the place, we build a living all over the place, we build a living graph. We call it the system of intent.

graph. We call it the system of intent. graph. We call it the system of intent. And this living graph actually And this living graph actually And this living graph actually has all the constraints of the system, has all the constraints of the system, has all the constraints of the system, has all the decisions over there. It has all the decisions over there. It has all the decisions over there. It keep evolving. And as an AI person keep evolving. And as an AI person keep evolving. And as an AI person actually, actually, actually, we don't allow the agents to touch it we don't allow the agents to touch it we don't allow the agents to touch it except with human in the loop approval except with human in the loop approval except with human in the loop approval for specific changes. And this thing is for specific changes. And this thing is for specific changes. And this thing is like the Bible of the whole system. This like the Bible of the whole system. This like the Bible of the whole system. This is where the whole org is going or whole is where the whole org is going or whole is where the whole org is going or whole company is going. company is going. company is going. And the next one is the tribal knowledge And the next one is the tribal knowledge And the next one is the tribal knowledge layer. The tribal knowledge layer layer. The tribal knowledge layer layer. The tribal knowledge layer we can think about it as a memory we can think about it as a memory we can think about it as a memory that keeps evolving with day-to-day that keeps evolving with day-to-day that keeps evolving with day-to-day usage and the knowledge base that usage and the knowledge base that usage and the knowledge base that capture all the information and capture all the information and capture all the information and documents. And it's keep evolving from a documents. And it's keep evolving from a documents. And it's keep evolving from a project to project and keeping the best project to project and keeping the best project to project and keeping the best practice over there. practice over there. practice over there. And lastly, And lastly, And lastly, instead of having this general coding instead of having this general coding instead of having this general coding agent that everyone uses today, we have agent that everyone uses today, we have agent that everyone uses today, we have a special designed agent that being a special designed agent that being a special designed agent that being developed by subject matter experts developed by subject matter experts developed by subject matter experts to help the engineers doing their work. to help the engineers doing their work. to help the engineers doing their work. So for example, like we have So for example, like we have So for example, like we have digital design agent, analog design digital design agent, analog design digital design agent, analog design agent, and so on.

agent, and so on. agent, and so on. And by combining all of this, you will And by combining all of this, you will And by combining all of this, you will have this shared nervous system that have this shared nervous system that have this shared nervous system that allows you to move fast and move allows you to move fast and move allows you to move fast and move forward. Okay. So it's easy to say an idea on a Okay. So it's easy to say an idea on a slide. It's nice. Everyone makes slides. slide. It's nice. Everyone makes slides. slide. It's nice. Everyone makes slides. But I want to show you like a demo from But I want to show you like a demo from But I want to show you like a demo from what we have today what we have today what we have today and showing the intent, knowledge, and and showing the intent, knowledge, and and showing the intent, knowledge, and execution. It will be short demos. execution. It will be short demos. execution. It will be short demos. And we'll start with the first one. And we'll start with the first one. And we'll start with the first one. Yeah, the Yeah, the Yeah, the Yeah. Okay, cool. So we can see that Yeah. Okay, cool. So we can see that Yeah. Okay, cool. So we can see that each engineer gets a role-based AI each engineer gets a role-based AI each engineer gets a role-based AI teammate specific to their role. teammate specific to their role. teammate specific to their role. They can check the knowledge base of the They can check the knowledge base of the They can check the knowledge base of the whole project that being contained and whole project that being contained and whole project that being contained and being growing and compounding over time being growing and compounding over time being growing and compounding over time and now they have their own intent. and now they have their own intent. and now they have their own intent. And And And you have single place you have single place you have single place for design for design for design where it captures all where it captures all where it captures all the tooling you have. It captures the the tooling you have. It captures the the tooling you have. It captures the results. It captures what you did and results. It captures what you did and results. It captures what you did and what you're going to do next and what you're going to do next and what you're going to do next and analysis of everything. So, everything analysis of everything. So, everything analysis of everything. So, everything being contained in one place.

And here we see And here we see a human finishing their work. a human finishing their work. a human finishing their work. This human signing off the This human signing off the This human signing off the the results of some space simulation the results of some space simulation the results of some space simulation and the system of intent realizes, okay, and the system of intent realizes, okay, and the system of intent realizes, okay, this person is done with this. I'm going this person is done with this. I'm going this person is done with this. I'm going to notify the next stakeholders of what to notify the next stakeholders of what to notify the next stakeholders of what they should do they should do they should do and signal to them that they are done and signal to them that they are done and signal to them that they are done with this. And now the system of intent, which And now the system of intent, which actually the nervous system or the Bible actually the nervous system or the Bible actually the nervous system or the Bible of the system, it's a graph living graph of the system, it's a graph living graph of the system, it's a graph living graph that keep compounding with time. We see that keep compounding with time. We see that keep compounding with time. We see in this example, like it realizes like in this example, like it realizes like in this example, like it realizes like there is something off, like some value there is something off, like some value there is something off, like some value out of constraints that shouldn't be out of constraints that shouldn't be out of constraints that shouldn't be there that might cost you $50 million there that might cost you $50 million there that might cost you $50 million actually to suspend the whole ship actually to suspend the whole ship actually to suspend the whole ship and it notified the system and the and it notified the system and the and it notified the system and the notification goes and some engineers notification goes and some engineers notification goes and some engineers start working on it. And once it got it start working on it. And once it got it start working on it. And once it got it fixed, it submit a game into the system fixed, it submit a game into the system fixed, it submit a game into the system and it keep evolving over time. Okay. Okay. Good. Good. Good. So, let's say for example, like um So, let's say for example, like um So, let's say for example, like um you were working in the system, you look you were working in the system, you look you were working in the system, you look at the Bible, you find, oh, there at the Bible, you find, oh, there at the Bible, you find, oh, there there's something wrong about it. Uh I there's something wrong about it. Uh I there's something wrong about it. Uh I don't like this value.

don't like this value. don't like this value. And then you propose a change. So, the And then you propose a change. So, the And then you propose a change. So, the system of intent and this big graph system of intent and this big graph system of intent and this big graph captures all the values over there, all captures all the values over there, all captures all the values over there, all the stakeholders, and you start doing the stakeholders, and you start doing the stakeholders, and you start doing this modification, this modification, this modification, and it gather all the shared knowledge, and it gather all the shared knowledge, and it gather all the shared knowledge, and then it fire a request, as you can and then it fire a request, as you can and then it fire a request, as you can see here, see here, see here, and this request goes to an architect or and this request goes to an architect or and this request goes to an architect or an owner of the system. The owner can an owner of the system. The owner can an owner of the system. The owner can approve or decline it, and the moment approve or decline it, and the moment approve or decline it, and the moment they approve that this is a valid they approve that this is a valid they approve that this is a valid change, it actually goes and echo in the change, it actually goes and echo in the change, it actually goes and echo in the whole system. Like everyone will know whole system. Like everyone will know whole system. Like everyone will know that this decision has been made. There that this decision has been made. There that this decision has been made. There is that change that advises everything is that change that advises everything is that change that advises everything over there. over there. over there. What? moving to a very difficult topic we have moving to a very difficult topic we have like how we going to evaluate uh our like how we going to evaluate uh our like how we going to evaluate uh our claims and measure the success of the claims and measure the success of the claims and measure the success of the system. The philosophy we are The philosophy we are using this or the philosophy toward using this or the philosophy toward using this or the philosophy toward this, we don't grade the agents.

this, we don't grade the agents. this, we don't grade the agents. We try to grade alignment itself. So, we We try to grade alignment itself. So, we We try to grade alignment itself. So, we have four axes, two horizontal, two have four axes, two horizontal, two have four axes, two horizontal, two vertical. The horizontal axes like vertical. The horizontal axes like vertical. The horizontal axes like qualitative, qualitative, qualitative, the vertical axes like qualitative and the vertical axes like qualitative and the vertical axes like qualitative and quantitative values, which is typical in quantitative values, which is typical in quantitative values, which is typical in this domain at the moment. And then this domain at the moment. And then this domain at the moment. And then horizontal ones, which is bare component horizontal ones, which is bare component horizontal ones, which is bare component and the system into it. and the system into it. and the system into it. And [snorts] if we're going to zoom into And [snorts] if we're going to zoom into And [snorts] if we're going to zoom into the bare component, you can measure like the bare component, you can measure like the bare component, you can measure like if that agent if that agent if that agent giving you the correct output for this giving you the correct output for this giving you the correct output for this voltage, like known values versus golden voltage, like known values versus golden voltage, like known values versus golden answers. Or you can use LNM judge and answers. Or you can use LNM judge and answers. Or you can use LNM judge and measure the golden answer versus the measure the golden answer versus the measure the golden answer versus the expert we have for this one. Which is expert we have for this one. Which is expert we have for this one. Which is okay. You can measure how good my okay. You can measure how good my okay. You can measure how good my memory, like if the recall state of art, memory, like if the recall state of art, memory, like if the recall state of art, which is the case in our thing. Are we which is the case in our thing. Are we which is the case in our thing. Are we doing inference really good? doing inference really good? doing inference really good? But then it comes into the harder But then it comes into the harder But then it comes into the harder question, which is basically are we question, which is basically are we question, which is basically are we doing a task completion? Like if someone doing a task completion? Like if someone doing a task completion? Like if someone uses this whole thing, uses this whole thing, uses this whole thing, is he really completing the task he want is he really completing the task he want is he really completing the task he want to do. to do. to do. Is he frustrated while using this? Are Is he frustrated while using this? Are Is he frustrated while using this? Are our agent overstepping human in the loop our agent overstepping human in the loop our agent overstepping human in the loop approval or not?

approval or not? approval or not? Sometimes the agent go goes out on that Sometimes the agent go goes out on that Sometimes the agent go goes out on that end. end. end. And we measure also does does our system And we measure also does does our system And we measure also does does our system allow you to work concurrently on allow you to work concurrently on allow you to work concurrently on multiple task in parallel? This is a multiple task in parallel? This is a multiple task in parallel? This is a success metric or success goal we have. success metric or success goal we have. success metric or success goal we have. And the last one is token tax. We don't And the last one is token tax. We don't And the last one is token tax. We don't want to overload you once you use this want to overload you once you use this want to overload you once you use this with all the lovely tokens and increase with all the lovely tokens and increase with all the lovely tokens and increase your budget. your budget. your budget. And there is hard frontier here like in And there is hard frontier here like in And there is hard frontier here like in the future now the topic of memory or the future now the topic of memory or the future now the topic of memory or graph memory or graph rag, whatever the graph memory or graph rag, whatever the graph memory or graph rag, whatever the title is, title is, title is, is there is around like 150 papers in is there is around like 150 papers in is there is around like 150 papers in this area at the moment and all of them this area at the moment and all of them this area at the moment and all of them are addressing in a nice way. You can are addressing in a nice way. You can are addressing in a nice way. You can measure the recall there is data sets. measure the recall there is data sets. measure the recall there is data sets. But there is no But there is no But there is no work and research at the moment that work and research at the moment that work and research at the moment that targets tribal memory or institutional targets tribal memory or institutional targets tribal memory or institutional memory. Like what does it mean exactly? memory. Like what does it mean exactly? memory. Like what does it mean exactly? How do you measure tribal memory How do you measure tribal memory How do you measure tribal memory success? success? success? And also for the chip design domain, And also for the chip design domain, And also for the chip design domain, it's actually even harder because there it's actually even harder because there it's actually even harder because there is not enough data sets like computer is not enough data sets like computer is not enough data sets like computer vision domain, there is many data sets vision domain, there is many data sets vision domain, there is many data sets over there. So there is nothing over there. So there is nothing over there. So there is nothing collected. So we have our own wheel and collected. So we have our own wheel and collected. So we have our own wheel and going with SMEs collecting this kind of going with SMEs collecting this kind of going with SMEs collecting this kind of data sets.

data sets. data sets. Cool. Cool. Cool. So [snorts] what broke? Which actually So [snorts] what broke? Which actually So [snorts] what broke? Which actually when I attend any talk I like to hear when I attend any talk I like to hear when I attend any talk I like to hear what broke, how do you fix it? what broke, how do you fix it? what broke, how do you fix it? First, agent overstepped. First, agent overstepped. First, agent overstepped. In early design phases of the system, we In early design phases of the system, we In early design phases of the system, we found that an analog agent that's found that an analog agent that's found that an analog agent that's specifically for analog design actually specifically for analog design actually specifically for analog design actually overstepping and doing RTL agent work. overstepping and doing RTL agent work. overstepping and doing RTL agent work. Which wasn't really great. Which wasn't really great. Which wasn't really great. Even we tried to enforce it, but it was Even we tried to enforce it, but it was Even we tried to enforce it, but it was a difficult problem. And then another a difficult problem. And then another a difficult problem. And then another thing is we noticed that truth has thing is we noticed that truth has thing is we noticed that truth has drifted. An agent modifying something in drifted. An agent modifying something in drifted. An agent modifying something in the system the system the system not necessarily means it modifies it not necessarily means it modifies it not necessarily means it modifies it everywhere it should be modified. everywhere it should be modified. everywhere it should be modified. And that make it harder. Like we have And that make it harder. Like we have And that make it harder. Like we have the cases specifically where one agent the cases specifically where one agent the cases specifically where one agent were modifying a parameter, it updated were modifying a parameter, it updated were modifying a parameter, it updated it in one place, five other places were it in one place, five other places were it in one place, five other places were forgotten. forgotten. forgotten. And the third one is one of my favorite And the third one is one of my favorite And the third one is one of my favorite is we asked the agent do not write into is we asked the agent do not write into is we asked the agent do not write into specs. Just don't don't change the specs. Just don't don't change the specs. Just don't don't change the specs. specs. specs. They said, "Okay, I obey you. I'm not They said, "Okay, I obey you. I'm not They said, "Okay, I obey you. I'm not going to write into specs." But then going to write into specs." But then going to write into specs." But then they moved into bash and they used set they moved into bash and they used set they moved into bash and they used set to write into specs. We blocked, bash we to write into specs. We blocked, bash we to write into specs. We blocked, bash we blocked set. They said, "Okay, cool. I blocked set. They said, "Okay, cool. I blocked set. They said, "Okay, cool. I will use cat actually to write over the will use cat actually to write over the will use cat actually to write over the specs." So we're being like specs." So we're being like specs." So we're being like a cat chasing a mouse around to just to a cat chasing a mouse around to just to a cat chasing a mouse around to just to prevent it from writing over specs.

prevent it from writing over specs. prevent it from writing over specs. And based on these three failures we And based on these three failures we And based on these three failures we have, have, have, we came up with principles that we are we came up with principles that we are we came up with principles that we are working today. working today. working today. First, we have a spec hierarchy with First, we have a spec hierarchy with First, we have a spec hierarchy with agent scope and file isolation to allow agent scope and file isolation to allow agent scope and file isolation to allow them only to work on this specific task them only to work on this specific task them only to work on this specific task or specific domain. That's all this or specific domain. That's all this or specific domain. That's all this our problem of agents stepping on each our problem of agents stepping on each our problem of agents stepping on each other. Second one is we have a single other. Second one is we have a single other. Second one is we have a single source of truth source of truth source of truth with automatic conflict detection that with automatic conflict detection that with automatic conflict detection that is not element based but actually rule is not element based but actually rule is not element based but actually rule based that can detect that this agent based that can detect that this agent based that can detect that this agent did this issue. did this issue. did this issue. And we can or want to change this value And we can or want to change this value And we can or want to change this value and actually resonate in the whole and actually resonate in the whole and actually resonate in the whole system immediately. system immediately. system immediately. And thirdly, which I think of it as an And thirdly, which I think of it as an And thirdly, which I think of it as an IT administration for agent, we block at IT administration for agent, we block at IT administration for agent, we block at the source. Like we block from system the source. Like we block from system the source. Like we block from system level, not about level like tool by level, not about level like tool by level, not about level like tool by tool, but just we try to block it over tool, but just we try to block it over tool, but just we try to block it over there. there. there. And the key lesson we learned here that agents care about like if you have your agents care about like if you have your agents which are intelligent, agents which are intelligent, agents which are intelligent, it what matters is substrate layer that it what matters is substrate layer that it what matters is substrate layer that they are living in.

they are living in. they are living in. Like the world they living in is more Like the world they living in is more Like the world they living in is more important than the agents itself. Like important than the agents itself. Like important than the agents itself. Like what they can do, what they cannot do, what they can do, what they cannot do, what they can do, what they cannot do, what you allow and what you don't allow. what you allow and what you don't allow. what you allow and what you don't allow. Cool. So, I'm going to use the word Cool. So, I'm going to use the word Cool. So, I'm going to use the word bottleneck. It's been used many times, bottleneck. It's been used many times, bottleneck. It's been used many times, but actually it's bottleneck in our but actually it's bottleneck in our but actually it's bottleneck in our case. case. case. It wasn't missing intelligence. It was It wasn't missing intelligence. It was It wasn't missing intelligence. It was missing alignment. missing alignment. missing alignment. And a shared nervous system lets your And a shared nervous system lets your And a shared nervous system lets your team move like a one body. team move like a one body. team move like a one body. As we see at the moment, one of the As we see at the moment, one of the As we see at the moment, one of the things I like hearing from our subject things I like hearing from our subject things I like hearing from our subject matter experts that they're saying that matter experts that they're saying that matter experts that they're saying that at the beginning of system is not at the beginning of system is not at the beginning of system is not working fine. working fine. working fine. Now it is good. Now I feel it's racing Now it is good. Now I feel it's racing Now it is good. Now I feel it's racing me. This is success for our case. And we me. This is success for our case. And we me. This is success for our case. And we think that this gives you four x think that this gives you four x think that this gives you four x leverage from our measurement at the leverage from our measurement at the leverage from our measurement at the moment. moment. moment. And alignment is universal. And alignment is universal. And alignment is universal. We're building it for the hardest case, We're building it for the hardest case, We're building it for the hardest case, which is ship design. So currently we're in alpha stage So currently we're in alpha stage with our development partners. with our development partners. with our development partners. And the sign ups for beta are open. And And the sign ups for beta are open. And And the sign ups for beta are open. And you can actually join now and we expect you can actually join now and we expect you can actually join now and we expect it to release it in October 26.

it to release it in October 26. it to release it in October 26. If you want to If you want to If you want to reach out us, sign up for reach out us, sign up for reach out us, sign up for the beta, the beta, the beta, just use this QR code or the link over just use this QR code or the link over just use this QR code or the link over there. Thank you everyone.