Autonomous Software Development: AI coding at Global Scale, with Blitzy
In 2026, insurance technology leaders face an important question: can autonomous development meet the AI determinism, auditability, and quality standards that regulated industries require? This conversation examines how a multinational insurer rebuilds its software development life cycle around AI, covering context engineering, test-driven development, throughput optimization, and the shifting bottlenecks that surface as code generation accelerates.
Autonomous software development creates a dilemma for leaders in regulated industries: adopt AI coding at scale or fall behind on product velocity without compromising auditability and code quality. In CXOTalk episode 917, Kris Tokarzewski, Group Chief Technology Information Officer at Vitality, describes how a 14,000-employee multinational insurer is rebuilding its software development life cycle around AI.
Recorded at Blitzy's headquarters, the conversation examines the importance of deterministic code generation, legacy modernization, and the shifting bottlenecks that surface as throughput accelerates.
In this episode:
- Why regulated industries require deterministic code, not probabilistic output, from AI coding systems
- How Blitzy’s infinite code context (ingestion of codebases, standards, and rules) creates high-quality software
- Reverse-engineering legacy systems with autonomous AI and measured 5x acceleration
- Optimizing end-to-end SDLC throughput rather than local efficiency
- How the roles of requirements engineers, software engineers, and product teams converge
- What executive sponsorship and measurement look like when AI spans the entire delivery pipeline
Key Points
Regulated Industries Require Deterministic Code from AI. Regulated insurers need deterministic, auditable code rather than probabilistic output, which shapes vendor choice, context engineering from codebases and standards, and test-driven development.
Optimize Throughput, Not Local Efficiency. Accelerating one SDLC stage exposes new limiting factors downstream. Treat requirements, code generation, review, testing, and release as one integrated, measured pipeline rather than isolated wins.
Instrument AI Spend Against Actual Business Outcomes. Track velocity, quality, and end-to-end throughput against AI investment, so spend ties to faster product delivery and customer value, not isolated gains.
Episode Participants
Kris Tokarzewski is Chief Information Officer of Vitality. Prior to Vitality, he held a CIO position at Discovery Health in South Africa, where he was responsible for the health division and group enterprise systems. Prior to Discovery, Kris held the position of CIO at Netcare Limited for seven years. Kris has 15 years of healthcare experience, 23 years of IT and 32 years of business experience.
Michael Krigsman is a globally recognized analyst, strategic advisor, and industry commentator known for his deep business transformation, AI, and innovation expertise. He has presented at industry events worldwide and written extensively on the reasons for IT failures. His work has been referenced in the media over 1,000 times and in more than 50 books and journal articles; his commentary on technology trends and business strategy reaches a global audience.
In This Episode
Deterministic code for regulated business
Kris Tokarzewski: Probabilistic code is you just vibe-coding cute ideas and put on the website, and you can get away with this if you are a startup, a coffee shop. But if you are a regulated industry, you need deterministic code.
Michael Krigsman: Kris Tokarzewski is Group Chief Technology Information Officer of Vitality, a multinational insurer with 14,000 employees. He's at Blitzy's headquarters rethinking Vitality's software process using autonomous AI.
Vitality's challenger marketing strategy
Kris Tokarzewski: Our legacy systems were not scaling fast enough, so we embarked on modernization plan to scale them up faster and future-proof the business. We see ourselves as the challengers in the UK market. We've got about 12% market share, and we compete against large institutions that have been in business for hundred of years. So as a challenger, we are growing, and we need flexibility. So opportunities are all over the place, and our systems have to be flexible to capitalize on those opportunities.
So we've realized that flexibility has to manifest itself in the systems because when there's new market opportunity, we need to build products and services that actually support those market needs. So we've been modernizing our systems for quite a while. We are building event-driven architecture that supports our product requirements.
Event-driven architecture and agentic AI
So as our R&D colleagues come up with new products and services we want to launch in the product, that we want to launch in the market, we building microservices which are actually event-driven services, and that's quite important from a customer perspective because historically it was okay to make a phone call to an insurance company and make a request and somebody would do something. Nowadays, everything happens in real time. So in order to be able to service our customers in real time, you need event-driven architecture and event-driven services.
And also when it comes to the agentic AI and the AI world that we entering into, event-driven services are natural partners of agentic AI. So when you combine event-driven services with agentic AI, now you've got a very powerful combination because they're actually like amplifiers, that AI is amplifying the event-driven capabilities, and the event-driven capabilities can leverage the AI capabilities, and ultimately we can service our members better in that way.
An AI-native development life cycle
Michael Krigsman: You're using autonomous development working with Blitzy.
Kris Tokarzewski: With Blitzy, we're doing number of things. Autonomous development is part of it. Because we are in the regulated industry, the autonomous development has to be augmented with other processes, so we call it AI native software development life cycle. And then autonomous development is just part of it, but actually development life cycle spans right across.
I'm looking at what are the limiting factors. So what is slowing us down? Because what happens is AI is accelerating specific processes, and it exposes other bottlenecks. So it's a continuous refocusing of the team. Now we've automated this part of the business or this part of the SDLC process, what limiting factors have been exposed?
So for example, we were able to generate the code very fast. Now who's going to review that code? So if we generated, let's say, 100,000 lines of code, who is going to review 100,000 lines of code? And probably not a human. We're going to need another AI to review that AI-developed code and then have a human review that part. So it's a continuous process of optimizing the throughput.
Optimizing end-to-end coding throughput with Blitzy
Kris Tokarzewski: So I'm quite keen on optimizing the throughput because local efficiency does not translate into overall throughput. So you have to optimize the entire software delivery life cycle to achieve optimal throughput.
Michael Krigsman: So you're working with Blitzy, and you have essentially reimagined that entire software development life cycle.
Kris Tokarzewski: That's exactly right. We're asking ourselves, "What are the limiting factors in our software development life cycle process? How do we leverage AI in that process to our advantage so that we get... We generate better code, higher quality at a faster velocity?" And that translates into throughput.
Platform over point solutions
Michael Krigsman: Clearly, this requires an end-to-end platform rather than specific point solutions.
Kris Tokarzewski: That's exactly right. You do need to have a integrated platform that automates and integrates the entire software development life cycle to achieve optimal throughput. Because if you've got fragmented process, that fragmented process is going to manifest itself in bottlenecks, which I call limiting factors. If you've got integrated process with integrated tooling, you can achieve optimal velocity, quality, and throughput.
The role of Blitzy at Vitality
Michael Krigsman: Where does Blitzy fit into this?
Kris Tokarzewski: We started with Blitzy on reverse engineering of legacy code. And we've learned very quickly that Blitzy is an excellent reverse engineering tool. But then we quickly learned that Blitzy can also generate a high-quality deterministic code, and it is massively important to the insurance business because many of AI companies can generate probabilistic code, and probabilistic code is you just vibe coding cute ideas and put on the website, and you can get away with this if you are a startup, a coffee shop, or some other company.
But if you are a regulated industry, you need deterministic code, and that's where Blitzy comes into it. That, one, we were able to reverse engineer our legacy systems, and we are able to create and generate deterministic code, and that translates into efficiency and throughput of the entire process.
Consistency in a regulated environment
Michael Krigsman: And of course, here again, you're operating within a regulatory framework, and you're a very large organization, multinational organization, so that consistency is fundamental.
Kris Tokarzewski: Absolutely. So the quality of the code and the consistency is massively important to us because of the regulation, and also because we've got to do the right thing for our customers. You know, when customers call in the insurance industry, they call with a specific problem. That problem has to be resolved correctly, not by a probabilistic scenario. You know, it's a very deterministic scenario. I've got a problem. This is a solution, and that's where Blitzy comes into it. There's lots of AI companies out there, but very few companies can actually generate deterministic code which is fit and proper for the insurance business.
Why not hire more engineers
Michael Krigsman: Why didn't you use traditional approaches to modernization, such as hiring more engineers or adopting standard AI coding systems? Why did you take this platform approach?
Kris Tokarzewski: We have been modernizing our systems progressively over the last couple of years. Every time we would build new product, we would then take a chunk of a heritage system, and we would modernize it. So it was kind of a just-in-time modernization for specific new product. However, we believe that the whole world is accelerating, and we have to accelerate our modernization process. So we believed that we can achieve acceleration of modernization with Blitzy.
Context engineering for compliance
Michael Krigsman: Kris, how does the platform support Vitality's internal validation rules, coding standards, governance, and compliance requirements?
Kris Tokarzewski: We achieve it through context engineering, and the context engineering is effectively ingestion of code base, millions of lines of code of our systems, our engineering standards, our development standards. There's number of documents and set of rules that get ingested into the context that help us to build higher quality code.
Michael Krigsman: So this context is massive and includes both technical and business requirements.
Kris Tokarzewski: That's right. So you've got the code, the code base, you've got rules, standards, and all of that put together generates higher quality code base.
Test-driven development with AI
Michael Krigsman: When you say higher quality, can you elaborate on that?
Kris Tokarzewski: We've gone to what we call a test-driven development, and what it means is that you define test cases before you actually write the code. And we found that when we generate code with Blitzy, with test-driven development, AI is naturally aligned with that methodology and generates much higher quality of code, so that when we generate the code, not only we pass the test cases much easier, but also the code quality is higher as well.
Early results and velocity gains
Michael Krigsman: Can you describe the results you've seen so far across autonomous work completed, engineering velocity, development cost, timelines, and also adherence to your compliance requirements?
Kris Tokarzewski: We're looking at different areas of software development lifecycle. And what we found is that, for example, reverse engineering of legacy code, we are able to reverse engineer our code probably 5 times faster than we were able to do it manually by people. So AI helps us to accelerate our reverse engineering of legacy systems by 5 times. We haven't fully quantified end-to-end the entire cycle, but we've got pockets of efficiency at this point in time, and now we are in the process of actually optimize the full delivery lifecycle.
So we're going from local efficiencies of steps in the process to the overall effectiveness of the end-to-end process, and that's where right now. We see major improvements in different steps of the cycle, but now I want to optimize the whole throughput because local efficiency of each step in the process doesn't necessarily translate to the overall effectiveness.
For example, if somebody can generate code quickly, maybe they can have extra coffee break because nowadays they've got a bit of extra time until the next process kicks in. Now I want to optimize the whole thing so the throughput get accelerated, not only specific steps, but the entire process gets accelerated.
Connecting delivery to customer value
Because we are shared value insurance business, we providing value to our customers, and the question is, does the new product deliver value as expected by the customers? And then the question is, how fast can I deliver that better proposition to the customers? So then accelerating the software delivery life cycle gives me the faster response time to the market.
Michael Krigsman: So there's always this linkage then between what you're doing with your software development and the architecture of your approach, and the outcomes that your customers will then experience.
Kris Tokarzewski: Absolutely. So the architecture has got direct impact on the product that we're delivering, and the software development life cycle accelerates the process of from the inception through the engineering to the product delivery.
Blending product and engineering teams
Michael Krigsman: Now, how does all of this change the relationship between product and engineering teams?
Kris Tokarzewski: At Vitality, we operate in matrix organization, and R&D, product, and technology or engineering are actually one team. So we actually have got a blended team with R&D people, with product people, and software engineering people working together to accelerate the process. So we are able to generate quick prototypes for R&D so that we can conceptualize our ideas faster. Then with use of Blitzy and AI, we can then accelerate the delivery of the product, and then of course launch it in the market.
Michael Krigsman: It's almost like you've transposed DevOps into product and engineering.
Kris Tokarzewski: That's right. So the DevOps is a integral part of the software delivery life cycle, and we connecting DevOps with product. So product and DevOps are then integrated.
From requirements to working software
Michael Krigsman: Now, when requirements can move more directly into working software, what happens to the steps in between, such as specifications, handoffs, and iterations?
Kris Tokarzewski: We're using AI to help us crystallize and document our requirements. Those are then ingested into the context that we spoke about a few minutes ago. And of course, that ultimately translates into test cases and code generated and into testing. So product requirements engineering, software engineering, testing, and release is a integrated process.
Leveling up engineering skills
Michael Krigsman: What changed for your engineering teams in terms of their roles, their skills, the workflows, and how they spend their time?
Kris Tokarzewski: We are still at the early stage of the transformation, but I can already see early signs of what we call a leveling up. So the skills get uplifted. So we've got examples where requirements engineers dive into actually code, and actually they want to have a look what the code looks like. And you know, requirements engineers build requirements, they build test cases, and they actually have a look at the code. And even though they are not software engineers, with AI, they've got that ability to do that. So it is a integrated process, and you can see the skills being uplifted.
And then software engineers look upstream at the requirements closer. So the teams are actually getting well-integrated. I see a better handover and more integrated process, or better integrated process, which translates into greater velocity and effectiveness of the whole throughput.
Code review is the new bottleneck
Michael Krigsman: What was it like to shift from reviewing small incremental code changes to reviewing pull requests of 50 to 100,000 lines?
Kris Tokarzewski: This is exactly where we are right now, and this is why I'm right now at Blitzy head office here, because we're actually analyzing the situation, how do we optimize it? Because we find ourselves that now we can generate requirements rapidly, we can generate code rapidly, but we cannot consume that code fast enough. So the code review is now a next limiting factor. So now that's a next change for the agentic AI, how do I accelerate code review to get to testing and, of course, release and launch of the product?
So as we go through the process and we accelerate one part of the SDLC process, we find other limiting factors, and those shift. They shift downstream. Now they shift upstream. And you know, it's like an old Whack-A-Mole game that you whack this one, this one pops up, you whack this one, and you've got to optimize to achieve greater throughput through the whole process.
Measuring what AI delivers
Michael Krigsman: This kind of development is very new, so you are analyzing each of the components as you go and optimizing along the way. That's how it sounds.
Kris Tokarzewski: That's exactly right. And as we optimize the process, we are measuring the velocity, the efficiency, and effectiveness of the whole process. That's right.
Michael Krigsman: It sounds like the measurements are also integral to what you're doing.
Kris Tokarzewski: Yes, because we want to evidence, you know, we are consuming tokens. So the question is, what do we get for those tokens? So we might accelerate specific activities, but if that activity doesn't translate to the overall effectiveness, it's a limited utility. So it's all about measuring the process throughout, and I have to admit, we haven't completely instrumented the whole process. We're in the process of actually analyzing and instrumenting the whole process, but that's exactly the objective, to optimize the entire process.
Risk, audit, and compliance
Michael Krigsman: I have to imagine, in a regulated industry such as insurance, your risk audit and compliance folks are going to be looking at this very, very carefully.
Kris Tokarzewski: Absolutely right. And you know, this is exact science. And us, as technology professionals, we are equally motivated to get it right because it is a cutting edge, brand-new technology, and we want to make sure that the code generated is as good or better to what we were able to do historically.
Executive sponsorship and the AI race
Michael Krigsman: This is a significant set of changes that goes right to the core of your business. Given that, what role did executive sponsorship and leadership play in driving adoption of this new approach to technology?
Kris Tokarzewski: It's massively important. I have to say that we've got a full sponsorship and full support at all level of all the way from the board through executive committee, through management. Everybody's equally motivated to get it right. We believe that AI is as important as the internet. You know, this is a game changer, and I'm personally determined to be the fastest horse in the race.
Michael Krigsman: This is a strategic move for Vitality.
Kris Tokarzewski: It is for us, and we want to be the leaders in the industry. You know, I believe that whoever wins this race is going to outrun the competition, and I intend Vitality to be the fastest horse in the race.
Advice for CIOs and CTOs
Michael Krigsman: Kris, any advice for CIOs, CTOs who are listening to this and wondering, how can I get started with this kind of AI-driven autonomous development?
Kris Tokarzewski: I think first one has to decide why we're doing this, and why is it important to our organization? At Vitality, because we are fast-moving and agile organization, AI is massively important to us. You know, for some companies, might not be. So I think maybe it is not for everyone, but if anybody's got an ambition of being a agile, fast-moving organization, AI is the obvious answer.
Michael Krigsman: Okay. Kris Tokarzewski, thank you so much for spending time with us.
Kris Tokarzewski: Thank you, Michael. Absolute pleasure.
