Inside AI Assisted Software Development and why tools are not enough (Part 1): By John Adam

The recent squeeze on funding and margins is by no means only being felt in the financial services and fintech sectors. But it's fair to say the pinch is particularly hard and the necessity to quickly and effectively innovate is simultaneously more pressing than ever.
The good news is, new AI tools can speed up delivery and improve the quality of software projects without adding to headcount. But even if that general statement is true, just using tools is not enough. Especially in a regulated industry like financial services.
If there is no pre-approved list of tools and how and where they are applied in an SDLC (software development lifecycle), organisations have governance, observability, measurability and consistency issues.
If 'real' gains are not measured by benchmarking against 'before', do they really exist? Tree falling in a forest metaphor.
Certainly not in a way that can be scaled across or up an organisation. There is no clear business case, just intuition.
Are tools and where and how they are being used compliant with organisational policy and regulatory frameworks? Has anyone read the privacy policies? I'm personally convinced that a big AI company having its Facebook/Cambridge Analytica moment falls under 'when, not if'. And when the first big AI privacy scandal does break, you don't want your organisation published in a list in a newspaper.
To benefit from and scale the gains of an AI-assisted SDLC, organisations need a framework for structured, consistent integration + governance, observability and measurability. Just tools isn't enough.
Realistic gains from an AI-assisted SDLC
It's important to note that at the time of writing, we are in a period of rapid change in AI tooling. A good framework operates at a level or two higher than specific tools and allows for them to be interchangeable with upgrades.
The market most of us operate in is at a point in its cycle where resources are at a premium. Most of the organisations I work with are expected to deliver more with less compared with pre-2023. In that context, banking the productivity gains achievable with AI tooling is non-negotiable. Organisations are demanding it in the demand for greater, better output despite fewer resources.
Getting it right is also non-negotiable and that means marrying increased productivity with measurability, observability and governance, which I cover in-depth in Part 2 of this article.
As an introduction to building a proper framework, I'll start by explaining the realistic improvements AI can provide to each stage of the SDLC:
Product prototyping
Developers use prototypes to test idea viability and functionality, and to gather user and investor feedback. Historically, the average prototype required 2 to 6 weeks of teamwork to complete.
But by amplifying developers' work via low-code/no-code prototyping and AI-generated code and other AI tools, a clickable prototype can now be completed in days or even hours.
UX/UI design
UX (user experience) and UI (user interface) designers collaborate closely with developers to design website and app interfaces.
Using AI tools that can quickly generate multiple design mock-ups and UI components based on foundational style guides and example concepts, designers can visualise ideas and user flows in various contexts to improve design clarity and direction long before designs touch a developer's desktop.
Clarity improves the quality of initial designs and reduces designer-developer back-and-forth, meaning larger projects that took 4 to 6 months to complete now require far less effort and time.
Even UXR (User Experience Research) is accelerated and refined. User interviews are, by necessity, long and complex, and result in large, qualitative datasets.
AI tools can highlight patterns and repetition in datasets and transcripts in seconds—shining a spotlight on insights, false positives or even biased questions that human researchers may have overlooked.
Architecture
Software architects plan higher-level design, bridging technical and business requirements. Their diagrams include the sum of a products' components and their respective interactions; until recently, the initial design phase alone took 1 to 2 weeks.
Using AI, architects can quickly draw up diagrams to easily visualise these relationships and standardise dependency versions across services. AI can also be trained to use PR comments to report architectural violations, and libraries can be unified to encourage stability across features.
Better consistency and immediate feedback mean architects can work faster and create fewer iterations of a product before diagrams meet stakeholder expectations.
Coding
AI-powered tools for coding have a variety of use cases.
My team uses a mix of tools and GenAI to:
ensure comprehensive project documentation,
automate code documentation and README generation,
scan for duplicate code and suggest improvements,
improve understanding of complex, inconsistent or unfamiliar code bases,
unify code styles and standards across different microservices, and
perform code completion and check for bugs and inconsistencies based on defined standards.
Paired with manual oversight to catch any mistakes, we've accelerated writing and testing code by a minimum of 20% across projects.
GenAI makes complex codebases easily understandable—meaning team members can flexibly move to work on unfamiliar projects and diminish time spent on internal comms by about 25%.
One tool we use is SonarQube, which reviews code without executing it. It runs automatically in GitLab CI/CD (Continuous Integration/Continuous Delivery and Deployment) pipeline to find bugs, report security vulnerabilities, and enforce code standards to unify style and mitigate potential misunderstandings down the line with better code readability.
Testing and QA (Quality Assurance)
As they write code, developers write and run unit tests to detect initial bugs and security issues that eat up between 10% and 20% of their time.
The SDLC is slowed further by code reviews and PRs, or feedback from experienced colleagues. Tests are postponed by days, sometimes weeks, if various code reviews are required and dependent on busy colleagues.
GenAI can augment developers' efforts by writing unit tests, conducting code reviews and PRs in real time, and automatically generating and solving for edge cases to overcome bottlenecks like a lack of expertise or teammates' availability.
AI augmented QA can reduce redundancy, unify access to code, and consolidate fragmented knowledge across a project to make a QA team more efficient.
And AI-driven tools like Selenium, for example, can automate web app test writing and execution, accelerating product releases and improving product reliability.
Automated testing is especially compelling in the context of projects with tight deadlines and few resources.
For example, my team's AI toolkit for QA testing includes
Llama 3.3 LLM to generate test cases and analyse code and Excel-based legacy documents,
IntelliJ AI Assistant to automatically standardise test case formatting, and
GitLab to run and test scripts automatically in the CI/CD pipeline.
QA is one of the most impactful applications of AI tools in the SDLC and can commonly slash the resources required by up to 60%, while increasing test coverage.
Deployment
When a product is deployed to end users, AI can be added to the CI/CD to forecast use patterns and improve caching strategies, as well as automatically prioritise and schedule tasks for parallel execution.
With AI oversight, the number of repetitive tasks is automatically reduced and resource allocation anticipated, improving latency and product release cycles without added manual effort.
And AI-driven caching accelerates and simplifies rollbacks (reverting a newly deployed system to a more stable version of itself) by analysing previous deployments and predicting the necessary steps, reducing further manual effort by DevOps teams, for instance.
My team uses Dytrance during deployment, which monitors and analyses system status, and sends self-healing recommendations in real time.
Maintenance and Monitoring
At this stage, teams work to fix bugs, keep the system secure and functioning well, and make improvements based on user feedback, performance data and unmet user needs.
AI can automatically perform root cause analysis for error monitoring, and suggest solutions for maintenance and debugging.
Tools my team uses include AWS Cloud Watch and Azure Monitor with AIOps, which automatically collect, analyse, and suggest responses based on monitoring data, accelerating issue response and system updates by 10x.
The big picture
The acceleration of the individual stages of software development is incentive enough for some teams to add tools and GenAI models to their workflows; especially at stages like QA and coding, where use cases are various and results potent.
But by taking a step back and considering AI's impacts on the SDLC holistically, the argument in favour of AI implementation can be turned into a real business case. A business case that can be used to accelerate AI transformation across an organisation:
Backed by a strong framework, organisations implementing AI across their SDLC see a 30%+ acceleration across projects in the first 6 months.
The keyword being 'strong.' Organisations need a framework that guides leadership to select tools and govern their use, measures outcomes to understand the amount of value different tools offer, and encourages adoption in teams' workflows.
Without it, teams are unable to measurably extract the full potential from new tools and efforts, and risk breaching internal and third-party governance in areas such as data privacy.
Keeping my word count and your patience in mind, I split my deep dive into a framework for AI governance, measurement and adoption into a separate article: Here is Inside an AI-assisted software development framework: using tools is not enough Part 2.

Try Our AI Features

Explore what Daily8 AI can do for you:

Learn with AIFact CheckingText to SpeechAI Summary

Related Articles

Daily Mirror

25 minutes ago

• Daily Mirror

Urgent 'don't click' warning as 16 billion passwords leaked in mega data breach

A staggering 16 billion passwords linked to Apple, Facebook, and Google have been leaked in what is said to be one of the largest data breaches in history A staggering 16 billion passwords linked to Apple, Facebook, and Google users have been leaked, according to researchers. The breach is one of the largest in history, affecting logins for Instagram, Microsoft, Netflix, PayPal, Roblox, Discord, Telegram, GitHub. Government services in more than 29 countries were also targeted in the attack, which experts say has given cybercriminals and hackers "unprecedented access to personal credentials". ‌ The intelligence was leaked in the format of a URL, with logins and passwords, and has allowed access to "pretty much any online service imaginable, from Apple, Facebook, and Google, to GitHub, Telegram, and various government service", according to Cybernews. ‌ The FBI has even warned Americans to not open suspicious links in SMS messages. Researchers at Cybernews have been investigating the leaks and discovered "30 exposed datasets containing from tens of millions to over 3.5 billion records each." "This is not just a leak – it's a blueprint for mass exploitation," the researchers said. "And they are right. These credentials are ground zero for phishing attacks and account takeover. "These aren't just old breaches being recycled. This is fresh, weaponisable intelligence at scale." Below are some of the actions users should take to protect their data being taken by cybercriminals. How will I know if my password was leaked? Sadly, there's no definitive way to find out if your password was leaked. Fortunately, the data was only available for a short amount of time, so investigators hope the information didn't travel too far. ‌ But, it is recommended to keep a close eye on your accounts and be aware of any unusual activity. What should I do? It is vitally important to change your passwords if you use Facebook, Google, or Apple. You should also activate Two-Factor Authentication, which gives another layer of security to logging in, by sending a secure code to your email or phone. Why am I being sent SMS links? The FBI has said smartphone users should not click on any SMS link messages sent to iPhone and Andriod users. These are often known as phishing, which is impersonating as a company or user to gain access to your information. Often, they are very sophisticated and seem incredibly real. "Don't click on anything in an unsolicited email or text message. Look up the company's phone number on your own (don't use the one a potential scammer is providing), and call the company to ask if the request is legitimate," the FBI advised.

Geeky Gadgets

41 minutes ago

• Geeky Gadgets

Automate Your Browser with Gemini 2.5 Pro for Online Workflows

What if your browser could do more than just display web pages? Imagine it seamlessly handling your repetitive tasks, managing complex workflows, and even collaborating with advanced AI models—all while you focus on what truly matters. Enter Gemini 2.5 Pro, the latest evolution in web automation technology. This isn't just another tool; it's a bold redefinition of what your browser can achieve. From automating intricate research projects to streamlining multi-agent workflows, Gemini 2.5 Pro transforms your browser into a dynamic productivity powerhouse. But how does it work, and what sets it apart from the rest? In this detailed report, World of AI explore how Gemini 2.5 Pro integrates innovative AI capabilities with the adaptability of open source frameworks to deliver unparalleled automation. You'll discover how its multi-agent task execution, dynamic adaptability, and robust privacy protections can transform your online workflows. Whether you're a professional looking to optimize your daily operations or a tech enthusiast eager to harness the power of AI, this guide will reveal how Gemini 2.5 Pro can be tailored to your unique needs. By the end, you might just rethink what your browser is truly capable of. Transforming Web Automation The Importance of Open source Flexibility At its core, Nano Browser is built on an open source framework, emphasizing customization and accessibility. This design allows users to integrate their own API keys or connect local AI models, tailoring the browser to specific requirements. For example, you can automate tasks like web research, data extraction, or social media management with ease. The open source nature eliminates dependency on proprietary software, granting you complete control over your automation processes. This flexibility ensures that Nano Browser can adapt to a wide range of use cases, empowering users to create solutions that align with their unique goals. Enhance Efficiency with Multi-Agent Workflows One of Nano Browser's standout features is its ability to handle multi-agent workflows, allowing multiple agents to execute tasks simultaneously. This functionality significantly improves efficiency by allowing parallel task execution. For instance, you could automate booking flights while simultaneously researching accommodations, all within the same browser session. By streamlining these processes, Nano Browser ensures that your workflows remain seamless, time-efficient, and highly productive. Automate Your Browser with Gemini 2.5 Pro Watch this video on YouTube. Advance your skills in Open source Web Automation by reading more of our detailed content. Seamless Integration with Advanced AI Models Nano Browser supports a wide array of AI models, including Gemini 2.5 Pro, the Cloud 4 series, and local models via Olama. This compatibility allows users to integrate innovative AI tools into their workflows, enhancing automation and decision-making capabilities. Whether you're extracting data, generating content, or optimizing complex processes, Nano Browser provides a powerful and adaptable platform for AI-driven solutions. This integration ensures that users can use the latest advancements in AI technology to achieve their objectives more effectively. Comprehensive Task Automation for Complex Processes Task automation lies at the heart of Nano Browser's functionality. The platform enables users to plan, execute, validate, and follow up on tasks with minimal manual intervention. For example, you can automate data scraping, validate the extracted information, and schedule follow-up actions—all within a single, cohesive workflow. This streamlined approach not only simplifies complex processes but also minimizes errors, saving you valuable time and effort. By automating repetitive or intricate tasks, Nano Browser helps users focus on higher-value activities. Interactive and User-Centric Interface Nano Browser features an intuitive interface designed to enhance the overall user experience. A real-time task visualization panel on the right-hand side allows users to monitor progress and make adjustments as needed. This interactive design ensures that you remain in control of your workflows, even as tasks are executed automatically. The interface is both user-friendly and highly functional, making it accessible to professionals across various industries. Advanced Speech-to-Text and Visual Analysis Tools To address more complex challenges, Nano Browser includes speech-to-text conversion and visual analysis capabilities. These tools are particularly useful for tasks such as solving CAPTCHAs or processing visual data. By integrating these advanced functionalities, Nano Browser ensures that even the most demanding tasks can be automated effectively. This makes it a valuable tool for users who require precision and adaptability in their workflows. Dynamic Task Handling for Adaptive Workflows Nano Browser excels in dynamic task handling through a process known as instruction decomposition. This feature breaks down tasks into actionable steps, allowing the browser to adapt to your strategies and requirements. For example, if you're conducting a multi-step research project, Nano Browser can dynamically adjust its actions based on your input, making sure that the results align with your objectives. This adaptability makes it an ideal solution for managing complex and evolving workflows. Browser Extension for Seamless Integration Nano Browser is available as a Chrome extension, making sure compatibility with popular browsers like Chrome and Edge. This format allows for seamless integration into your existing workflows without the need for additional software installations. The extension also simplifies updates and maintenance, making sure that your automation tools remain current and efficient. By offering this level of convenience, Nano Browser makes it easy for users to incorporate advanced automation into their daily routines. Prioritizing Privacy and Local Data Security Privacy is a central focus of Nano Browser's design. By operating locally within your browser, it ensures that your data remains secure and private. Unlike cloud-based solutions, Nano Browser does not require users to upload sensitive information to external servers. This approach provides peace of mind, particularly for professionals handling confidential or sensitive data. By prioritizing local data security, Nano Browser offers a reliable and trustworthy solution for automation. Applications Across Diverse Industries The adaptability of Nano Browser makes it suitable for a wide range of applications. Professionals can use it to automate tasks such as web research, data extraction, social media management, and multi-agent workflows. Its compatibility with advanced AI models further expands its potential, making it a valuable tool for industries ranging from marketing and research to software development and beyond. By offering a flexible and powerful platform, Nano Browser enables users to achieve their goals with greater efficiency and precision. Media Credit: WorldofAI Filed Under: AI, Guides Latest Geeky Gadgets Deals Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.

BreakingNews.ie

42 minutes ago

• BreakingNews.ie

Europe's Trade Commissioner has ‘productive engagements' over US deal

Europe's Trade Commissioner says he has had a series of productive engagements throughout the week with his US counterpart. On social media, Maroš Šefčovič says no time or effort spared - their focus is on securing a forward looking deal. Advertisement Both sides are under pressure to reach a deal before July 9th, when a series of reciprocal tariffs are due to come into force. A series of productive engagements throughout this week with @USTradeRep Ambassador @jamiesongreer and Secretary @howardlutnick . No time or effort spared - our focus and priority remain clear: securing a forward-looking deal. — Maroš Šefčovič🇪🇺 (@MarosSefcovic) June 20, 2025 It comes as European shares rose on Friday after declining for three straight sessions, as a stall in the United States' involvement in the Middle East conflict helped soothe investor concerns. The pan-European STOXX 600 was up 0.6 per cent at 538.85 points. The benchmark is set to log a second consecutive weekly fall. Israel and Iran's air war entered a second week and European officials sought to draw Tehran back to the negotiating table. Advertisement The White House said President Donald Trump will decide within the next two weeks about whether to join Israel in the war. That helped improve market sentiment, spurring some interest in risk assets that were sold off earlier in the week on uncertainty around how long the conflict would go on. "The investors are taking a little bit more risk on their shoulders... it is perhaps because the U.S. is now giving itself two weeks and maybe some diplomatic opening window there to resolve the situation in Iran," said Ipek Ozkardeskaya, senior market analyst at Swissquote Bank. Banks rose 1.3 per cent, leading broader gains. Travel and leisure stocks SXTP were also up 1.3 per cent, led by a 4.8 per cent gain in Europe's largest travel operator TUI after Barclays upgraded the stock to "overweight" from "underweight". Advertisement Conversely, energy shares SXEP were at the bottom of the index with a 0.3 per cent decline but were headed for a weekly gain. Ireland Tariffs and gender-based violence on agenda for No... Read More Investors also remain wary of the approaching July 8th tariff-pause deadline, with little progress on trade deals with Washington. European Commission President Ursula von der Leyen is still aiming to reach a deal by July 9th. "Geopolitical tensions are kind of hiding the other worries in the market, which are trade negotiations being delayed with the U.S. occupied with what to do with the Middle East," said Ozkardeskaya. Trump's tariffs have been a source of turmoil and volatility in the last few months, and have already begun to upend global supply chains and threatened economic growth. Additional reporting Reuters