Splunk and Cisco Unveil Architecture for Agentic Enterprises That Learn from Operational Data

Every day, organizations learn things their AI systems never use. A security analyst corrects an AI-generated investigation. A network engineer identifies the root cause of a recurring outage. An observability team discovers that a pattern of latency, logs and infrastructure changes predicts service degradation. Each moment contains valuable organizational knowledge, but in most enterprises, that knowledge disappears into tickets, dashboards, chat threads, post-incident reviews and the minds of individual experts.

The challenge of lost knowledge in traditional AI systems

This knowledge may help solve the immediate problem, but it rarely becomes part of a reusable system that improves future AI-driven decisions. That is the next challenge for the agentic enterprise, as highlighted by Hao Yang, VP of AI at Splunk (a Cisco company). The future will not be defined solely by who has the most capable model or the most autonomous agents. Many organizations will have access to similar frontier models. The real differentiator will be whether those agents can learn from the organization around them. Not by constantly retraining the underlying model, but by capturing operational experience, converting it into institutional knowledge and making that knowledge available to future agents, workflows, and decisions.

Feedback loops to turn every outcome into a teachable moment

Every agentic workflow creates signals. An agent receives a request, retrieves context, reasons through possible actions, calls tools, and generates answers. A human accepts, rejects, or modifies that answer. Downstream systems reveal whether the action worked. AI observability gives organizations visibility into what happened: the prompt, response, reasoning path, tool calls, data sources, intermediate steps, failure modes and outcomes. Without that visibility, organizations cannot understand why an agent behaved the way it did, let alone improve it. But observability alone is not enough. The larger opportunity is to turn observed behavior into institutional knowledge. A trace should not only help developers and operators debug an agent, but should help the enterprise understand what the agent learned, what the human corrected, what outcome followed, and what should change before the next similar event. That is the shift from monitoring AI to teaching AI.

Architecture of a learning system for the agentic enterprise

A learning-oriented agentic enterprise needs more than a model or chatbot. It needs an architecture that can capture experience, turn it into usable knowledge, connect that knowledge to operational context, and govern how it changes future agent behavior. Memory preserves what happened: what the agent saw, what it did, where humans intervened, and what outcomes followed. Knowledge bases turn that experience into reusable guidance, including playbooks, examples, policies, procedures, and evidence. A data fabric connects the operational environment. The signals agents need live across logs, metrics, traces, tickets, identity systems, security tools, network telemetry, collaboration platforms, and business applications. A data fabric makes those signals discoverable, correlated, governed, and usable in context. AI observability explains how agents behave by capturing prompts, tool calls, intermediate steps, responses, feedback, and outcomes. The control plane governs how learning becomes change: what knowledge is promoted, which prompts or policies are updated, which agents can use new information, what approvals are required, and how changes are audited.

A practical example across security, observability and the network

Consider a service experiencing intermittent degradation. An observability agent detects unusual latency and error rates. A network agent identifies packet loss across a specific path. A security agent notices that the same time window includes suspicious authentication behavior and unusual traffic from a previously unseen source. Individually, each agent has only a partial view. Together, they create a richer operational picture. The first time this incident occurs, human experts may need to intervene. A network engineer confirms that packet loss was caused by a misconfigured routing change. A security analyst determines that the suspicious traffic was not an attack, but a side effect of a misrouted internal service. An SRE connects the network event to the application degradation. This resolution contains knowledge the organization should not have to relearn. A mature agentic learning system would capture the traces, human corrections, topology context, security findings, observability signals and final remediation steps. The next time a similar pattern appears, agents would not start from zero; they could retrieve the prior case, compare current conditions, recommend the proven diagnostic path and escalate with better context. The underlying frontier model did not need to be retrained. The enterprise learned.

Competitive advantage for organizations that learn faster

Organizations that build this ecosystem will create AI systems that improve with every interaction, not because the model is constantly changing, but because the enterprise itself is becoming more intelligent. As discussed in the article on Meta AI Workers Revolt, managing talent is crucial for a successful agentic enterprise. For more on data fabric concepts, see the Wikipedia page on Data Fabric. The next era of AI will not be won by models alone, but by organizations that can capture what they learn from every workflow, expert correction, incident, investigation, and outcome.

Source: https://venturebeat.com/orchestration/why-agentic-enterprises-need-to-become-learning-systems