devopsy.kinsta.cloud

Tag: ai

Atlassian Adds CLI Option to AI Agent for Building Software

Atlassian has added a command line interface (CLI) option to provide application developers with a familiar construct for invoking Rovo Dev, its artificial intelligence (AI) agent for building software

Part of a portfolio of Rovo Software Agents that Atlassian now makes available in beta, Rovo Dev completes and debugs code, creates tests, surfaces insights and explanations of code bases, makes suggestions to improve code and generates documentation. It is also integrated with Jira project management software and Confluence collaboration tools provided by Atlassian.

Using a set of software engineering (SWE) benchmarks maintained by researchers at Princeton and Stanford, Rovo Dev achieved a 41.98% resolve rate across 2,294 tasks.

It can also be integrated via a Model Context Protocol (MCP) Server to access external data sources capable of providing more context that might be needed to complete a specific task.

Shuyin Zhao, vice president of product for Atlassian, said the goal is to provide a single agent capable of performing a wide range of tasks versus requiring developers to create workflows that require them to orchestrate multiple agents to build and deploy software. The more memory that can be allocated to an AI agent the more it is able to preserve context, she added.

Longer term, as the reasoning capabilities provided by large language models (LLMs) continue to expand, the scope of complex tasks that can be assigned to that AI agent will also increase, noted Zhao.

Eventually, many developers will find they will be spending more time reading and evaluating code rather than writing it themselves, she added.

It’s not clear how widely AI tools are being adopted by software developers and engineers, but a Futurum Group survey found 41% of respondents expect generative AI tools and platforms will be used to generate, review and test code. The one thing that is certain is more developers than ever are using these tools to write code, but how much of that code is making it into production environments is unknown. In some instances, an AI tool might enable a developer to write better code than they can on their own. In other instances, it might create vulnerabilities or recommend using software packages that simply don’t exist.

Additionally, even as more code is generated, the existing DevOps pipelines might not be robust enough to deploy software at higher levels of scale than what is already being achieved.

None of that means AI agents won’t be incorporated into DevOps workflows, but it does mean there is still a considerable amount of effort required to re-engineer those processes in a way that is optimized for AI agents rather than human application developers.

In the meantime, however, DevOps teams would be well-advised to start creating a list of tasks they are willing to delegate to AI agents, assuming there is some level of supervision. Otherwise, it’s all but inevitable that AI agents might generate the same issues that human developers create, albeit just at a different level of scale. The issue then becomes making sure the right governance policies are in place to prevent as many of those issues from arising in the first place.

June 18, 2025
CloudBees Adds MCP Server to Unify Platform for Integrating DevOps Workflows

CloudBees today began providing early access Model Context Protocol Server to its Unify platform for centrally managing DevOps workflows across multiple types of continuous integration/continuous delivery (CI/CD) platforms.

Originally developed by Anthropic, MCP has emerged as a de facto standard for integrating artificial intelligence agents with each other and various data sources.

Shawn Ahmed, chief product officer for CloudBees, said MCP will enable CloudBees to extend the reach of its Unify platform to AI agents that are becoming incorporated into DevOps workflows. The CloudBees MCP Server provides a lightweight, standardized interface between large language models (LLMs), such as OpenAI’s GPT and Anthropic’s Claude, and enterprise DevOps tools and processes, he added.

The overall goal is to make it simpler to orchestrate and automate multi-step tasks spanning multiple AI agents by making pipeline, test, security data and associated metadata, including metrics, available to AI agents via the CloudBees Unify platform, noted Ahmed.

Launched last month, CloudBees Unify is a software-as-a-service (SaaS) platform for centralizing the management of multiple DevOps environments, including GitHub, GitLab and the open source Jenkins continuous integration/continuous delivery (CI/CD) platforms. It enables DevOps and platform engineering teams to centrally manage application development environments more easily via a control plane for CI/CD platforms through which DevOps teams can govern and manage multiple platforms.

In effect, CloudBees Unify provides an operating layer on top of any existing toolchain that makes it possible to both surface analytics in real time, run tests and apply policies that require the running code scans and implement compliance policies. That capability can now also be extended to AI agents to ensure governance policies are followed as tasks are automated, noted Ahmed.

It’s not clear how widely AI agents are being deployed across DevOps workflows, but a Futurum Group survey found 41% of respondents expect generative AI tools and platforms will be used to generate, review and test code. The challenge now is determining to what level tasks can be assigned to AI agents in a way that will be reliably implemented. The issue isn’t so much whether AI agents will be used as much as it is to what degree. Additionally, DevOps teams will then need to determine how potentially hundreds of AI agents might be employed alongside the engineers, who, in addition to continuing to perform some tasks themselves, may need to manage a small army of AI agents.

Ultimately, each DevOps team will need to determine their level of comfort with AI, but the one certain thing is that there is no shortage of manual DevOps tasks to be automated. It’s not likely AI agents will replace the need for software engineers but the nature of the role will undoubtedly change, especially as AI agents increasingly eliminate the need to write custom scripts.

In the meantime, however, DevOps teams would be well-advised to revisit how their existing pipelines are constructed. After all, the more brittle those pipelines are, the more likely it becomes that AI agents will stress them to the point of breaking.

June 18, 2025
AI, the New Hero of Software Development … or Anti-Hero?
Artificial intelligence (AI) can be a hero or an anti-hero in software development, depending on your implementation approach. According to the 2024 DORA Accelerate State of DevOps Report, AI adoption shows promise with 75% of respondents reporting positive productivity gains, but also reveals unexpected challenges, including a 7.2% reduction in software delivery stability.

The key is to position AI as a supportive partner. AI should be utilized to enhance human expertise rather than replace it.

AI Is Promising, but Let’s Stay Suspicious

AI has been rapidly infiltrating software development for almost two years now. Coding assistants, automated testing tools, and AI-powered analytics promise to transform how we build applications, and some early adopters have shown impressive results. When AI first entered development workflows, it tackled well-defined problems such as code completion, simple test generation, commenting, and draft documentation with reasonable success.

But that initial enthusiasm has given way to more complex realities. Modern software development involves intricate systems, multi-cloud deployments, complex security requirements, and accelerating delivery expectations. AI has shown both remarkable capabilities and concerning limitations in this environment.

After hearing customer stories about dozens of AI implementations, I’ve found the story isn’t as binary as “hero” versus “villain”—it’s more like “hero” versus “erratically-troubled-if-ultimately-victorious anti-hero.” The reality of AI is nuanced—and much more interesting, depending very much on the implementation approach, governance scheme, and where organizations choose to apply AI technologies.

The Toil Problem Is Real and Measurable

Every developer knows the frustration of “toil”—those manual, repetitive tasks that consume time without adding much value. Toil isn’t just a minor annoyance. The 2024 DORA report confirms that this challenge remains persistent, with developers continuing to struggle with time allocation between valuable work and repetitive tasks.

Recently, I had the chance to discuss AI heroism and anti-heroism with the Chief Product Officer of CloudBees, Shawn Ahmed. CloudBees is an enterprise DevOps solutions provider and was co-founded by Jenkins creator Kohsuke Kawaguchi, so it has been in a good position to observe the thousand ways AI has been injected into software development. Their internal research indicates developers spend about half of their time triaging test failures, waiting on build times or addressing security issues—and as little as 20–30% of their time writing code. As Ahmed pointed out to me, this inefficiency seems like it wouldn’t be tolerated in most other industries; it is like accepting a manufacturing line that’s only 20–30% effective.

An example of CloudBees’ approach to incorporating AI productively and helpfully is their continuous integration (CI) capability. It analyzes historical pipeline data to identify patterns in successful deployments and uses AI to provide suggestions for future deployments. This eliminates hours of configuration work, thanks to AI’s ability to base pattern recognition on thousands, if not millions, of data points.

From CloudBees’ perspective, AI in software development isn’t a replacement technology in dev but rather what Ahmed characterizes as a “companion.” AI’s best role is handling routine tasks to preserve and expand the human developer’s time performing creative and strategic work.

Three Implementation Models, Three Different Outcomes

It’s clear that not all AI implementations are created equal. I see three distinct approaches emerging, each with dramatically different results:
1. The Replacers: Some organizations approach AI to reduce headcount by automating development tasks. This model typically delivers poor results, fundamentally misunderstanding both AI capabilities and the creative nature of software development. The DORA research supports this concern, showing that while AI adoption is widespread, 39.2% of respondents reported having little or no trust in AI-generated code, indicating that successful implementations require human oversight.
2. Tools First!: These organizations adopt individual AI tools without a cohesive strategy or governance framework. This approach delivers mixed results—productivity improves in specific areas, but in many cases at the cost of quality, security, or long-term maintainability. The DORA findings highlight this challenge, showing that despite AI’s positive impact on individual productivity and code quality, it can lead to decreased software delivery performance.
3. The Augmenters: The most successful approach treats AI as an amplifier of human capabilities rather than a replacement. The DORA research validates this model, showing that AI adoption leads to meaningful improvements: when AI adoption increases by 25%, individual productivity increases by 2.1%, flow improves by 2.6%, and job satisfaction rises by 2.2%.
CloudBees is built on this augmentation philosophy. According to Ahmed, AI handles pattern recognition and repetitive tasks while humans make decisions on strategic matters. Their DevSecOps solution demonstrates this approach by using AI to identify security vulnerabilities while preserving human authority over remediation strategies. CloudBees’ Value Stream Analytics uses AI to spot workflow inefficiencies while leaving process improvement decisions to the teams who understand the organizational context.

Making AI the Hero of Your App Dev Story

Here are five critical success factors that determine whether AI becomes a hero or an anti-hero for you:
1. Target high-toil activities first. Successful implementations start with well-defined, repetitive tasks where AI can deliver immediate value. CloudBees’ recommended targets include test generation, pipeline optimization, and code reviews, including areas where AI can significantly reduce manual effort.
2. Establish governance first, deploy AI second. Organizations seeing positive results implement governance frameworks before widespread AI adoption, defining, for example, appropriate use cases, verification requirements, or clear boundaries for AI autonomy.
3. Invest in developer education. Contrary to some narratives, successful AI implementation requires more skilled developers. Top-performing organizations invest in training programs that help developers understand both AI capabilities and limitations.
4. Integrate rather than isolate. Rather than adopting disconnected point solutions, effective organizations implement AI capabilities that integrate throughout their delivery pipeline. CloudBees’ platform takes this approach, connecting AI capabilities from requirements analysis through production monitoring.
5. Measure meaningful outcomes. The most effective implementations have moved beyond measuring code generation metrics. Instead, they focus on quality improvements, security posture enhancements, and business impact indicators that reflect the true value of AI adoption.
AI Is Your Enthusiastic Partner, Not Your Replacement

Successful AI implementations in app dev seem to share the common characteristic of using it as a complementary force instead of as a replacement. AI is adept at the mundane, repetitive tasks that drain motivation and attention among developers and increase their toil. It lets humans focus on innovation, customer experience, and ultimately, business value.

According to Ahmed, CloudBees envisions a future where AI becomes increasingly personalized to individual developers. He predicts that within two years, developers will likely work with multiple AI companions tailored to their specific preferences and working styles. This personalization aspect represents an important evolution beyond today’s more standardized AI tools.

A particularly noteworthy perspective I got from research and vendor discussions is the relationship between AI adoption and team scaling. While some organizations initially approach AI to reduce headcount, the data suggests the opposite effect. As Ahmed noted in our discussion, the more effective approach isn’t using AI to reduce a 10-person team to 5, but rather leveraging AI to assist that 10-person team in achieving what would have previously required 15 people. This is the proactive, business-building “scale up, not down” perspective that can help propel an organization to its goals.

I’ve concluded that today, the hero of software development isn’t AI. Not AI alone, but it is no longer purely human expertise either. The true hero is the partnership between them, working in concert to create outcomes neither could achieve independently.
June 17, 2025
From Automation to Orchestration: The Key to Digital Success

Digital transformation continues to be a key focus for many organizations, and this usually means the automation of processes and data.

At its core, automation is meant to simplify and streamline business operations. However, if not implemented correctly, it can introduce complexity, risk and fragmentation. The proliferation of automation tools, combined with the rapid growth of interconnected systems has created a tangled web of interdependencies that are becoming increasingly difficult to manage.

In fact, recent research has shown organizations now manage an average of 50 endpoints to execute tasks that are part of a process in their business (this is a 19% increase over the past five years). Without a fundamental shift in approach, organizations risk becoming overwhelmed by digital chaos – what’s more, 82% fear they could find themselves dealing with ‘Automation Armageddon’ if processes are left unchecked.

Bringing Order to Automation Complexity

As automation becomes more ingrained, organizations are facing new operational risks that threaten efficiency, compliance, and agility. One of the biggest challenges is the sheer volume of interconnected systems and workflows that businesses now rely on. When it comes to process complexity, more than three quarters of organizations say that a lack of control has resulted in increased risk that core business processes are not working anymore.

At the same time, rising regulatory demands are making compliance more difficult. A lack of control has also increased business risk relating to compliance and many organizations lack the visibility to ensure compliance across all automated processes.

As automation scales, it becomes harder to gain insights into what’s working, what’s redundant, and where bottlenecks exist. This lack of visibility makes it difficult for leaders to drive continuous improvement and ensure automation is delivering real value.

AI: The Operationalizing and Scaling Challenge

Despite AI being at a relatively early stage in terms of widespread adoption, AI is already revolutionizing industries, enhancing decision-making, improving customer experiences, and driving efficiencies across business processes. Many organizations are eager to expand their AI capabilities, integrating machine learning models, predictive analytics, and AI agents to uncover new opportunities.

A significant challenge facing organizations is being able to operationalize and scale AI; 85% of organizations report such challenges, highlighting the difficulty of moving from isolated AI implementations to fully embedded AI-driven end-to-end processes. This fragmented approach makes it difficult for businesses to realize AI’s full value, as disconnected AI initiatives fail to work cohesively within larger business processes.

Another hurdle is governance and compliance. As AI becomes more embedded in decision-making, organizations need clear oversight into how models are trained, deployed, and maintained. Transparency is crucial, particularly in regulated industries where AI-driven decisions must be explainable and auditable.

To overcome these challenges, organizations must implement “guardrails” that combine deterministic workflows with the non-deterministic nature of AI capabilities. By clearly defining operational parameters, businesses can ensure AI operates autonomously while adhering to organizational policies and regulatory standards. This approach allows businesses to leverage AI’s adaptability and predictive power within structured, reliable processes without sacrificing compliance or control.

How AI Can Be Integrated

AI systems need to be seamlessly integrated into existing business processes to ensure they deliver real value. Without orchestration, AI often functions in isolation, requiring manual effort to synchronize with other process endpoints. This disconnect leads to inefficiencies and makes it impossible to “control” AI sufficiently.

Embedding AI within a structured orchestration framework provides clear governance and simplifies management – effectively balancing predictable, deterministic workflows with the adaptive, non-deterministic capabilities of AI, which are increasingly executed by one or more AI agents. Structured orchestration defines clear interactions between human and AI-driven tasks and delivers real-time visibility into operations. This reduces complexity, eliminates silos, and unlocks AI’s full potential as a strategic asset.

Process orchestration also enables organizations to build processes quicker with the help of AI, as modern orchestration tools can help teams in the process modelling phase. Furthermore, process orchestration allows organizations to gain insights into end-to-end processes in real-time and detect bottlenecks or other problems within an automated process. AI can then help to find solutions to solve the process issues, enabling businesses to optimize operations, improve decision-making, and scale AI usage effectively.

To fully leverage AI, organizations must move beyond ad hoc implementations and toward a strategic, orchestrated approach. This way, they can maximize efficiency, maintain compliance, and ensure that AI contributes meaningfully to broader digital transformation efforts.

Why Orchestration Helps Ensure AI and Automation Initiatives Play the Right Tune

To regain control, organizations must embrace end-to-end process orchestration as a core part of their business and IT strategy. Process orchestration and automation allows organizations to tame complexity, operationalize AI, and accelerate transformation. Organizations can design, manage, and improve the processes that underpin their business, no matter what the processes entail or where they run. Additionally, it serves as a critical link between IT and business teams, aligning automation initiatives with real operational needs and long-term business goals.

Automation Is Inevitable, But Chaos Isn’t

Automation without orchestration leads to fragility, not resilience. Those organizations that prioritize process orchestration will be those who turn automation and AI into a competitive advantage and avoid the looming threat of digital chaos or ‘Automation Armageddon’.

June 13, 2025
New Relic Adds Support for Model Context Protocol to Observability Platform

New Relic this week added support for the Model Context Protocol (MCP) to its observability platform to surface insights into artificial intelligence (AI) agents and applications.

Originally developed by Anthropic, MCP is rapidly becoming a de facto application programming interface (API) for enabling interoperability between AI agents and other sources of data.

New Relic has now incorporated MCP with its application performance monitoring to surface insights into AI agents and applications alongside its ability to monitor and observe legacy applications.

Previously, New Relic had added an ability to observe large language models (LLMs), but via MCP it’s now able to extend the reach of that capability to AI agents and applications that access those LLMs. That capability makes it possible to visualize specific usage and patterns of the entire lifecycle of an MCP request, including invoked tools, call sequences and execution durations.

Additionally, DevOps teams can identify which prompts are being invoked and what choices were made by an AI agent along with surfacing latency, errors and other MCP performance issues.

New Relic AI Monitoring MCP support is now available in Python Agent version 10.13.0, with additional languages coming soon.

In general, New Relic reports it has seen a steady 30% growth in usage of its AI monitoring tools quarter-over-quarter for the past year. The company has also seen a 92% increase in the number of unique AI models being used. However, the ChatGPT models provided by OpenAI accounted for 86% of all the LLM tokens being generated.

Nic Benders, chief technical strategist for New Relic, said that level of activity suggests that OpenAI is well on its way to becoming a de facto standard, even as the number of AI models being made available continues to rapidly increase.

It’s not immediately clear why one LLM might be preferred over another but OpenAI, in addition to making a steady stream of investments, has successfully generated a significant amount of brand recognition. That helps make OpenAI one of the first platforms that most organizations are going to look to when building an AI application, said Benders.

However, there are use cases, such as coding, that lend themselves, for the moment at least, better to coding, he added.

Less clear is the degree to which the various AI models that are available will gain enough traction to warrant the ongoing level of investment required to sustain them. IT teams should carefully consider what foundations they want to build and deploy AI applications on for the long term, noted Benders.

Additionally, not every AI application requires the latest, and most expensive, LLM, said Benders. The cost of previous generations of AI models has declined considerably as more advanced models have become available. Many applications, however, may not require access to a more advanced model, especially when a previous generation will enable a developer to automate a task at a much lower cost.

Ultimately, observability platforms will play a critical role in enabling organizations to track which AI models are being used for which use cases. The challenge now is understanding not only which ones are gaining traction among application developers, but just as importantly, the symbiotic relationship that exists between AI models and the IT infrastructure upon which they depend.

June 13, 2025
From Noise to Narrative: Rethinking Observability for AI-Augmented DevOps Pipelines
Because DevOps teams deal with so much data, they may feel like they are drowning, but rarely find the insights they need. There is more observability data now than ever, yet it often stays separate, disorderly, inaccessible or confusing. As AI enters more organizations’ processes, observability moves from just monitoring to gathering early insight through meaningful narratives. It is not only about having new tools but also changing how development is done and organized. Supporting today’s DevOps — where AI is involved — requires developers to switch from seeing observability as a solely technical aspect to thinking of it as a way to explain what happens in the system: One that links unrelated incidents, highlights how each one is related, and warns users ahead of any failure.

The Telemetry Tsunami

Legacy monitoring was created for stable, predictable systems, including static servers, stable networks and well-known failure points. Nowadays, architectures made of ephemeral containers, dynamic microservices and AI-driven automation result in high-volume and high-velocity telemetry data that older monitoring systems cannot handle.

AI models add more factors to consider in analyzing systems – model drift, low data quality, inference delays and unclear ways AI decides make things difficult to observe. Logs and alerts are insufficient to make sense of what is happening in such systems. Observing these complex, AI-driven systems calls for tracing and feedback that can reveal valuable insights with a lot of noise around them. The result? As a result, most teams experience so much data that it’s hard to find the reason behind any performance, regression or security problems.

Observability as Narrative

Moving forward, DevOps teams need to treat observability as a way to construct coherent stories. DevOps teams should focus on building stories from the signals they gather that help explain what happened and what to do next. This shift involves three fundamental changes:

Correlated Context Over Raw Data: Systems should first add metadata like deployment IDs, feature flags, user behavior and model versions to metrics, traces and logs to describe their life cycle independently (refer to figure 1).

Declarative Telemetry Pipelines: Bringing AI/ML into the system will allow systems to describe their activities using words humans can easily understand. A pipeline should ensure that the effects of an AI model update on latency can be noted and followed, not simply added later on.

Semantic Layering with AI Assistance: Instead of being used only in the system, AI/ML can simplify understanding what is happening. With the help of AI/ML, observability tools are becoming easier for humans to understand.

Figure 1. The three pillars of observability that are essential in an AI-augmented DevOps pipeline.

From Dashboards to Dialogues

Most current observability tools rely solely on the user to interpret data. However, more practitioners are starting to wonder: Why can’t the system simply offer explanations? It all boils down to how observability tools combine AI to help sum up what’s happening, pinpoint regressions and provide possible explanations. With the help of AI, systems can now describe issues, indicate regression points and identify probable problems in the data. An AI-augmented observability system could tell you: “Starting at 12:06, service X saw a 30% increase in latency because many cold starts from model Y, which had just been redeployed recently. Service level objectives (SLOS) did not meet expectations by 12:12. Consider raising the pool size of warm data or re-adjusting the model’s time frame for batch processing”.

This is no longer science fiction but something that is becoming true. Several open-source and commercial solutions integrate machine learning into observability stacks to help find root causes, group anomalies and make suitable suggestions for resolving issues.

Designing for Explainability

AI models used in DevOps also require monitoring for issues, as they can perform worse than expected for reasons that might not be obvious in tests. Unlike standard software, changes in AI models can be challenging to detect until they appear in production. Sometimes, a model that looks good during testing can have problems in the real world, caused by small or unusual changes in the input data.

Explainability is key. AI observability must track:
- Input/output distributions over time
- Feature importance changes
- Data pipeline lineage
- Confidence scores and decision paths
When correlated with infrastructure and application data, this information will tell teams if the incident was caused by a system problem, an issue with the pipeline code, or faulty model behavior.

Practitioner-Centric Observability

For observability to progress, it must be designed for all system users, not just for central teams. This means that not only platform teams but also the mid-level workers responsible for trying to understand user complaints, triaging incidents, or fine-tuning production models need observability tools.

Some key principles include:
- Narrative-Driven Interfaces: Less reliance on dashboards; more chances to look at timelines, see how things are linked and get simple explanations from AI.
- Integrated Feedback Loops: Ability for engineers to fix, add notes to and correct system alerts so the information shown in the future gets better.
- Cross-Domain Visibility: Bringing together data about how applications are doing, how the systems are working and how well your AI is doing all together into one place to help you see your systems better.
Observability must evolve, so it is smarter than simply collecting more data. It will require the entire culture of the industry to change, not just new technology. People in the industry should start seeing observability as telling a story, where each log, trace and metric adds to how the system can be easily explained. This evolution means that your systems must be able to define themselves well, rather than simply based on how much data you can collect.
June 13, 2025
Smooth the Path to AI Agent Adoption for Software Engineers

The release of AI agents marks the latest shift in the developer landscape. These tools are currently being marketed for their ability to make developers’ lives easier. However, in many cases, AI agents are so new that use cases are unclear or undefined, which can complicate development cycles rather than accelerate them. What’s more, many enterprises want to be seen as adopting AI in the “right” way, which stifles experimentation as organizations dictate which AI tools their teams can and can’t use.

To encourage effective AI use among developers and smooth the path to adoption, enterprises must define clear use cases for AI agents. Read on to find out more about how enterprises can use AI agents.

1. Security Updates and Patches

Enterprises can often take months to manually roll out security updates or patch known issues. There is no reason updates should take this long, and, in their simplicity, these updates are ripe for “agentifying”. The shift from human-led to agent-led updates will allow organizations to significantly reduce update cycles. AI agents also provide an avenue for enterprises to reduce engineer toil, which is often worsened by strict deadlines such as milestone moments like Patch Tuesday.

One IDC report, sponsored by JFrog, found that software developers spend nearly a fifth of their workweek (19%) on security-related tasks. It’s not uncommon for some of these to be simple and manual tasks that can be automated with AI agents, such as application scan reviews and secrets detection. The same report found that forcing developers to focus their efforts on such manual tasks is costing organizations $28,000 per developer per year. The use of AI agents has significant potential to drive down this cost when applied to manual workflows that security teams currently struggle with.

Common vulnerability and exposure (CVE) fixes and other simple, repeated security updates don’t require human input for resolution, other than to verify fixes proposed by an agent. If enterprises implement AI agents free engineers from these simple security-related tasks, and will see a major uptick in the value and production from their engineers’ working time.

2. Code Review/Testing

There have never been enough software engineers to meet enterprises’ needs. In today’s economy, this black hole has become increasingly evident. No enterprise can afford to hire entire teams of testers, meaning that code review frequently becomes a workflow blockage.

According to one report, three-quarters of software engineers often sacrifice functional safety to meet code delivery deadlines. Code review and testing offer an opportunity for enterprises to adopt AI agents to remove this common bottleneck in development cycles, especially when simple code from known libraries is in review.

Of course, AI agents can’t take the roles of human coders. In its current state, it is incapable of the creativity required for things like vibe coding and complex code, but AI agents can be applied successfully for code testing to reduce toil for human developers and teams.

3. Augmenting Engineers’ Creativity

AI agents can make excellent “assistants” to carry out the groundwork of coding projects. These tools can augment human developers for the initial stages of this work, including figuring out how an environment should operate. Setting up an environment should be a quick process, taking no more than 5-10 minutes, but in extreme cases, it can take weeks.

AI agents can help with this initial stage of any development task by spinning up an environment in moments based on the prompt given to it by an engineer. This will enable developers to instead focus on the real craft of writing code and exploring creative work rather than spending excessive time on the early stages of any coding project.

The Potential Pitfalls of AI Agent Adoption

There is a risk that adopting AI agents across an entire enterprise will reduce opportunities for junior developers to learn. From both an organizational and industry perspective, AI agents cannot replace the next generation of software engineers. If AI does all the basic work that junior developers would typically have carried out, the early-career workers would find fewer learning opportunities for themselves.

Given that there has always been a shortage of software engineers, organizations must take measured approaches toward maintaining a healthy pipeline of engineers. This means identifying areas where junior developers can take on responsibility and learn, such as writing code, supporting code reviews and assisting in debugging and resolving issues. By giving these tasks to junior developers, organizations can ensure that the talent pipeline continues to produce developers who can perform in large enterprises.

Secondly, AI agents are also regularly over-marketed products, and successful enterprises will be able to decipher reality from the hype. Many practitioners have already found that there are use cases where AI agents cannot be used, despite the promises made by marketing departments. Engineers must work out which tasks can be handled by agents and which must remain in human hands. Human-led tasks are often deeply complex, requiring proprietary data or legacy systems with hard-to-access data that AI agents would struggle to interpret. Accurately identifying where AI tools can be used to bring real value, rather than being used for the sake of using them, will differentiate successful enterprises from the competition.

AI agents cannot be adopted as a hammer in need of a nail. They must be used to solve existing challenges that it is suitable for.

The Two-Step Strategy for AI Agent Success

To successfully adopt AI agents, there are two steps enterprises must take.

First, enterprises must cast a wide net and give teams as many tools as possible to experiment with, in safe environments, to enable creativity. After all, AI adoption is more than just a box-ticking exercise. Engineers must be able to use AI agents to improve their day-to-day experience and not have their suite of available AI tools reduced in the name of uniformity.

Second, engineers must be encouraged to get involved in peer-to-peer research and discussions to find the tools that work for them, as well as use cases that bring tangible value to the organization. From social media discussions to in-person conversations and events, developers best learn from each other. To see the benefits of AI agent adoption, developers must be encouraged to have these conversations with their peers; otherwise, AI agents will just become the latest rung in the ladder of misplaced investment.

June 13, 2025
JFrog Extends Alliance With NVIDIA to Secure AI Software Supply Chain

JFrog and NVIDIA today announced they have expanded the integrations between their software development platforms to now include the Enterprise AI Factory, a set of frameworks and blueprints for building artificial intelligence (AI) applications.

As a result, software artifacts created using the NVIDIA Enterprise AI Factory can be housed in the JFrog Software Supply Chain Platform. The JFrog ML platform, meanwhile, provides a registry for managing the lifecycle for building and deploying AI models by enabling versioning, provenance tracking, model promotion, and enforcement of security policies.

Additionally, JFrog metadata and promotion workflows ensure immutable AI artifacts can only move between stages when all quality, security, and legal checks have passed. AI models can also be cached, continuously monitored and updated to align with regulations. Critical patches and AI model updates can also be centrally managed similarly.

Finally, the JFrog ML platform also enables application development teams to enforce role-based access control (RBAC) to ensure that access to AI artifacts is traceable for compliance purposes.

Collectively, those capabilities ensure all AI software is signed, validated and approved before deployment.

Kristian Taernhed, senior technical alliance manager at JFrog, said the overall goal is to provide a repository that can be deployed in an on-premises IT environment to provide DevSecOps teams with a platform to manage all their software artifacts, including AI agents and models. That capability, for example, enables organizations to leverage scanning tools to prevent malicious AI models from being inadvertently incorporated into an application, he added.

Locking down the software supply chain used for building AI applications is crucial not just for organizations concerned about highly regulated industries but also in countries that have developed policies pertaining to how AI applications are developed, also known as Sovereign AI, he added.

Specifically, Sovereign AI mandates typically require AI data to remain within specified geographic or organizational boundaries and for strict controls across the AI software supply chain to be enforced.

It’s not clear to what degree machine learning operations (MLOps) workflows used to build AI models are being integrated into DevOps workflows, but for all software engineering purposes, those models are simply just another type of artifact that needs to be integrated into a build. Going forward, just about every application being built is going to have some AI capability, so the number of AI models that will need to be incorporated into a DevOps workflow is only going to continue to increase.

The bigger challenge may be melding the cultures of the data science teams that typically build AI models with the DevOps and platform engineering teams responsible for building and deploying software.

In the meantime, there will be no shortage of platforms for building AI models that will need to be integrated into DevSecOps workflows. Some organizations may be able to standardize on a few, but given the pace of innovation, the number of platforms being used to build AI models continues to increase. Most data science teams, much like their DevOps counterparts, prefer to retain control over the tools and platforms used to build those AI models, so enforcing a platform standard across every data science team is in the short term likely to be a challenge.

The good news, of course, is that with each integration, the level of expertise attained should, hopefully, make the next project that much easier.

June 11, 2025
The Future of Application Development in the AI Era

The artificial intelligence (AI) hype has yet to fade. As the technology continues to make headlines, attention is focused on the impact and value AI could deliver for teams, companies and the wider industry.

One of the main questions for those in software development is: Can AI replace human coders?

Despite impressive strides in AI-driven tools, human developers remain essential —though their role is evolving.

Today, 34% of IT leaders report that their organizations use AI-assisted coding extensively, according to The Low-Code Perspective. Meanwhile, nearly half the respondents(47%) are in the experimental phase.

Low-code platforms and AI advancements are creating new opportunities and responsibilities for those involved. Yet, understanding how to make the most from AI-powered low-code requires clarity on the skills and expectations needed from employees.

Let’s take a closer look at the future of application development in this new era of AI — from training teams to navigating stakeholder involvement.

AI Won’t Replace Developers; It Will Help Evolve Their Role

Generative AI (GenAI) tools, such as ChatGPT and Copilot, are currently being used to suggest code snippets, troubleshoot errors and even complete functional code blocks based on prompts.

The role of GenAI in application development is to automate repetitive tasks and reduce low-value activity, but the technology is quickly evolving.

Soon, we could start seeing GenAI work as a co-worker alongside developers. For example, instead of crafting a data model manually, GenAI could assess a requirements document, an existing data schema or an idea formulated in natural language and populate a data model that can then be validated by a developer. The same applies to the generation of user interfaces: Rather than developing UIs from scratch, developers can upload designs or even low-fidelity drawings from a whiteboard session and generate pages that can then be refined.

For some, the productivity benefits of GenAI, as it continues to evolve, pose a question as to whether there is still room for low-code in the future.

Visual development, such as low-code, provides an arena that is not often available to organizations, as it enables people from multiple disciplines to build applications in an environment where everyone understands what’s going on behind the scenes. Not only does GenAI facilitate visual development at pace, but it also increases the speed of the entire development lifecycle when applied to a low-code platform.

AI-assisted low-code paired with skilled developers can unearth significant benefits. Of those surveyed, 85% believe combining AI and low-code would help their organization innovate faster. And 82% say it helps their organization innovate at scale.

Eventually, we will likely see the role of the developer become more of a composer, overseeing the work completed autonomously by virtual software agents. Developers will focus on the management and correction of applications rather than the heavy lifting.

Unlike AI, human expertise can handle nuances to create purpose-driven applications. For instance, understanding user requirements, anticipating potential system failures and integration with existing IT assets are just a few areas where human developers will remain critical. So, as we continue to integrate the technology into application development, it won’t eliminate the need for skilled coders — it will reshape it.

Stakeholder Support for AI is the Next Big Hurdle

We uncovered that a massive 84% of IT leaders say low-code empowers more people to be involved in app development. Yet, 41% report their C-suite lacks the technical knowledge to understand the potential of low-code for their organizations.

Navigating stakeholders is an ongoing consideration for technical teams, whether that is securing buy-in for vital technologies or unlocking future funds to fulfil the development roadmap. Yet, IT leaders are unearthing tension between their goals and those of their stakeholders.

This is concerning, considering that IT leaders report their chief operating officer (COO) as the topmost involved member of the C-suite when making decisions about low-code adoption. And the chief executive officer (CEO) is second.

As non-technical C-suite stakeholders become increasingly important decision-makers in IT capital expenditures and programs, continued conversations between these two stakeholder groups will help create a fuller understanding of low-code benefits.

In the pursuit of easy-to-use applications, businesses can mistakenly assume that low-code and AI tools eliminate the need for technical knowledge altogether — a fear that nearly two in five IT leaders share, with 39% believing their non-technical C-suite wants to use low-code to replace developer talent.

As the lines blur between non-technical and technical leaders in the IT space, goals must be aligned, with the right people in place, so everyone is on the same page for technology investments to be effective.

The Future of AI and Low-Code is Collaborative

Low-code platforms are already facilitating app creation by less technical developers, while AI tools are making coding faster and more efficient. There is a future on the horizon where low-code and AI operate in tandem, allowing developers and stakeholders to collaboratively design and deploy applications.

But the AI skills gap is widening, and today’s developers are expected to keep up. AI, used in conjunction with a powerful enterprise-grade low-code platform, holds significant potential to help bridge this gap when harnessed accessibly for smarter, faster development.

Ultimately, committing to improving productivity and enhancing developer experience is vital for businesses to stay competitive, and that means providing teams with the right tools to make development faster and more efficient. That way, tech teams can focus more on collaborating with the wider organization and problem-solving with accessible tools at the ready.

As organizations move forward, it will be essential to foster collaboration, ensure clarity in roles and encourage ongoing learning.

The true potential of AI and low-code is not in replacing coders but in empowering them. It not only accelerates development but also enables stakeholders to contribute more directly while helping organizations adapt dynamically in a rapidly evolving tech landscape.

June 11, 2025
Datadog Adds Raft of Additional AI Agents and Tools to Portfolio

Datadog at its DASH 2025 conference today previewed a raft of artificial intelligence (AI) agents that automate tasks ranging from assessing infrastructure alerts that normally require the expertise of a site reliability engineer (SRE), to fixing code and triaging cybersecurity issues using the company’s security information event management (SIEM) platform.

In addition, Datadog is also adding Proactive App Recommendations that analyze telemetry data to suggest the next best action and APM Investigator to identify and trouble shoot bottlenecks impacting application performance.

At the same time, Datadog is adding data observability tools, along with extensions to its service for monitoring large language models (LLMs), to add support for AI agents and previews of tools to test and validate the impact of prompt changes, model swaps or application changes on the performance of LLM applications. The company has also added an AI Agents Console to make it simpler to discover and invoke its AI agents. Datadog LLM Observability, now generally available, monitors the integrity of AI models and performs toxicity checks that look for harmful behavior across prompts and responses, while Datadog Workload Protection monitors interactions between LLMs and their host platforms. A Datadog Cloud Security and Sensitive Data Scanner (SDS) also enables organizations to meet compliance requirements.

Datadog is also making generally available Datadog Code Security, a service that leverages AI to detect, prioritize and remediate vulnerabilities in their custom code and open-source libraries based on runtime threat activity and business impact. It has also extended the capabilities of its log management suite to run in an on-premises IT environment—meeting data sovereignty requirements in regulated industries—and to help reduce costs with a lower-cost archive tier of storage.

Finally, Datadog has added a managed internal developer portal (IDP) that is integrated with the company’s core application performance monitoring platform. It provides a live system of record for telemetry data to surface what software is running, who is responsible for it, and how it is performing. There are also templates powered by Datadog’s App Builder and Workflow Automation to automate tasks such as creating the scaffolding for a new service along with engineering reports and scorecards to track compliance, reliability, security, observability, cost and other metrics.

In general, Datadog is making use of a range of proprietary and open source LLMs, including one optimized for time-series data that it has developed. Over time, Datadog plans to mix and match LLMs to address specific use cases as additional AI advances are made.

Michael Whetten, vice president of product for Datadog, said, for example, the latest Bits AI SRE, Bits AI Dev Agent and Bits AI Security Analyst agents not only extend the range of tasks being automated, but also enables them to query data, analyze anomalies or scale infrastructure using shared memory in a way makes it possible for AI agents to reuse functions. Datadog has also developed a Model Context Protocol (MCP) server to make it simpler for AI agents to consume its data and interoperate with each other. The overall goal is to not, for example, replace SREs, but rather augment their expertise in a way that makes it easier to manage complex IT environments, he added.

It’s still early days so far as adoption of AI technologies across DevOps workflows is concerned, but a recent Futurum Research survey finds 41% of respondents expect generative AI tools and platforms will be used to generate, review and test code. In fact, arguably the challenge now is not so much deciding whether to use AI as much as it is determining where AI will have the biggest impact on improving both software quality and the speed at which applications are deployed.

June 10, 2025