Delivering agentic AI reliability: Why AI Observability is imperative

As AI investment accelerates, a gap is emerging between ambition and execution. IDC projects¹ that by 2028, AI spending will make up 16.4% of total IT expenditures. However, Gartner, Inc.² predicts over 40% of agentic AI projects will be canceled by end of 2027. Likewise, a CIO survey found that 88% of AI pilots fail to reach production due to unclear objectives, insufficient data readiness, and a lack of in-house expertise. These findings place the expected return on research and innovation firmly at risk, as organizations invest in bespoke models and agentic AI that lack a clear, scalable outcome.

Nonetheless, another Gartner, Inc. article³ predicts that by 2028, 33% of enterprise software applications will include agentic AI, up from less than 1% in 2024, enabling 15% of day-to-day work decisions to be made autonomously by agentic AI systems. Consequently, a Forrester blog⁴ predicts that 40% of highly regulated enterprises will combine data and AI governance in a move toward a more integrated, transparent, accountable, and ethically responsible approach to AI.

These trends are not contradictory-they show how the market is searching for the right formula to adopt AI, and specifically agentic AI. Successful agentic AI outcomes are predicated on trust in AI's reliability, security, and alignment with business goals and strategies to not fall behind competitors. Achieving that trust requires AI-native observability that's deeply integrated with both data and strategic objectives.

Key insights for executives

• Every modern cloud-native enterprise project will also be an AI-native project - either because of first party AI or through invoking agentic AI services. Preparing for AI adoption is among the top drivers for cloud strategy and investment. Likewise, 63% of top-performing companies increase their cloud budgets to be able to leverage AI.
• Visibility into reliability and governance of AI interactions has emerged as a new responsibility for executives to realize the value of AI investments while managing risks. From analyst firms in the US to regulators in the EU - increased oversight, link to business goals and regulation of AI systems has become mandatory.
• Unifying observability signals with AI-powered analytics provides a strategic advantage for AI transformation. By converging observability and AI, teams can accelerate moving projects from pilot production and advance trust and transparency in AI.
• Dynatrace sets the standard for cloud- and AI-native software, including tracing and logging of AI behavior, predicting and optimizing AI resource utilization, and protecting from unintended AI behavior through runtime security.
• Dynatrace delivers unified, full-stack visibility across cloud infrastructure, AI workloads-from chat interfaces and prompts to models, tools, and GPUs running on Kubernetes-plus customer experiences and the business layer, all in a single pane of glass, to confidently deliver advanced, AI-powered cloud-native services via a rapidly growing number of 40+ technologies and integrations with hyperscalers and major agentic frameworks providers.

The rise of AI comes with a rise in complexity-and executive responsibility

Organizations generally find themselves maturing their AI implementations along five phases with growing complexity and risks:

1. Prompt engineering (generative Al hype). Single step human language prompts a large language model (LLM) for automated text processing and assistance.
2. Retrieval augmented generation (embedding Al in digital services). Multi-step prompt engineering and LLM access for customer support, automation, and decision-making.
3. Fine-tuned models. Additional model(s) put on top of existing ones for increased accuracy and domain-aware responses.
4. Multimodal GenAI. Combination of various modalities beyond text-such as video, audio, imaging and others-that further increase heterogeneity and processing power of services and their interdependences.
5. Agentic Al. Multiple AI agents and cloud native digital services intensively interacting with each other to autonomously fulfill a specific goal. Agentic AI can double the number of deployed digital service instances and massively increase IT complexity.

The necessity of AI observability for agentic AI reliability

As the complexity of AI implementations increases, observability becomes an essential feedback channel to properly orchestrate and moderate reliable agentic AI outcomes.

Even the early phase implementations show the need to observe AI, tune experience, manage cost, provide guardrails and govern AI responsibly. As the complexity grows, the risks also increase, making deep, context-rich observability of AI strictly mandatory.

7 important reasons for continuously observing AI

1. Business value. Validate AI investments against business goals and verify end-user value of AI services. Gain business insights from observability data.
2. Cost and performance control. Monitor and control expenses and sustainability associated with AI operations and investments.
3. Security. Increase awareness of interactions among AI services, reducing the risk of hacking and malicious influence. Leverage converged observability and security offerings to minimize risk and cost.
4. Compliance. Monitor that AI output is ethical, unbiased, and adheres to guardrails for meeting regulatory compliance requirements and providing traceability for audits. Expect high volumes of logs and traces to observe AI behaviors and keep audit trails.
5. Accuracy. Verify that AI agents function properly and precisely, generating quality output. Use observability to deeply check run-time behaviors and
6. Reliability. Provide traceability and root-cause analysis to verify AI agent health, scalability, performance, and availability.
7. Collaboration. Govern communications among agent-to-agent and agent-to-human, and provide the means to keep humans in control to override and take responsibility. Automate events from observability platforms that integrate with enterprise ecosystems.

With Dynatrace, executives can solve one of the biggest challenges of managing return on AI investment: Balancing innovation speed with risk, cost, and value.

Increase AI success with AI Observability from Dynatrace

AI is not a single component. Agentic AI in particular is composed of multiple layers and technologies, each observed within a holistic context. Dynatrace provides complete coverage of all layers that allows teams to observe the complete AI stack of modern cloud- and AI-native applications. The layers consist of the following:

• Business - track outcome: does it create productivity gains, does it deflect support tickets, does it act autonomously and is the investment worth it
• Infrastructure - utilization, saturation, errors
• Models - accuracy, precision/recall, explainability
• Semantic caches and vector databases - volume, distribution
• Orchestration - performance, versions, degradation
• Agentic layer - autonomous agents, MCPs
• Application health - availability, latency, reliability

Dynatrace automatically observes and analyzes complex multicloud and agentic AI systems. By securely unifying and storing all data in context, the Grail® data lakehouse with massively parallel processing unifies all data signals with full context and is continuously updated by Dynatrace Smartscape® real-time dependency mapping technology.

Davis® AI combines predictive, causal, and generative AI to provide deterministic answers and insights, which drive AutomationEngine actions and inform teams with recommendations to optimize productivity, performance, and cost. With these advantages, teams can embrace AI with confidence, make better decisions faster, and innovate at speed-without compromising trust, performance, reliability, or control.

Why Dynatrace for reliable agentic AI projects

Top Fortune 500™ organizations use Dynatrace to not only maximize return on investment (ROI) in AI technologies, but across their cloud- and enterprise stacks. Dynatrace leverages partnerships with hyperscalers and major AI framework providers to provide customers with observability for the latest technologies in this fast-moving space.

The recent announcement of our collaboration with NVIDIA is an example of our commitment to providing differentiated AI observability. Dynatrace AI observability delivers real-time, end-to-end observability into AI and LLM workloads-from infrastructure and applications to model performance and end-user experiences. This empowers enterprises to accelerate innovation, ensure compliance, and confidently scale mission-critical AI, all while maintaining reliability and efficiency across their cloud environments.

_____________________________________________

¹ _{IDC Market Forecast, "Worldwide Artificial Intelligence IT Spending Forecast, 2024-2028," October 2024, https://my.idc.com/getdoc.jsp?containerId=US52635424&pageType=PRINTFRIENDLY.}

² _{Gartner Press Release, "Gartner Predicts Over 40% of Agentic AI Projects Will Be Canceled by End of 2027," June 25, 2025, https://www.gartner.com/en/newsroom/press-releases/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027}

_{GARTNER is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally and is used herein with permission. All rights reserved.}

³ _{Gartner Article, "Intelligent Agents in AI Really Can Work Alone. Here's How.," by Tom Coshow, October 01, 2024, https://www.gartner.com/en/articles/intelligent-agent-in-ai.}

⁴ _{"Predictions 2025: An AI Reality Check Paves The Path For Long-Term Success," Forrester Research, Inc., by Jayesh Chaurasia and Sudha Maheshwari, October 22, 2024, https://www.forrester.com/blogs/predictions-2025-artificial-intelligence/.}