# AIOps

AIOps applies artificial intelligence and machine learning to maintain IT infrastructure and automate operational tasks.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## From AIOps Pipelines to Agentic Service Operations: A Survey of Capability, Authority, and Evidence

DevFeed: [From AIOps Pipelines to Agentic Service Operations: A Survey of Capability, Authority, and Evidence](<https://devfeed.tech/articles/from-aiops-pipelines-to-agentic-service-operations-a-survey-of-capability-authority-and-evidence-139580.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21620>)

Author: Hailiang Zhao, Wenzhuo Qian, Jianwei Yin, Shuiguang Deng

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [capability](<https://devfeed.tech/tags/capability.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [incident](<https://devfeed.tech/tags/incident.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [operational](<https://devfeed.tech/tags/operational.md>), [operations](<https://devfeed.tech/tags/operations.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [production](<https://devfeed.tech/tags/production.md>), [service-operations](<https://devfeed.tech/tags/service-operations.md>), [survey](<https://devfeed.tech/tags/survey.md>)

### AI overview

The audit of 22 language-model-enabled service operations systems finds that most remain copilots or read-only investigators. Only two exercise write authority; both constrain actions, and neither has controlled evidence of production outcomes. The survey frames the transition from conventional AIOps around capability, operational authority, and evaluation evidence, and proposes a four-plane reference architecture, evidence grades, an evaluation ladder, and a controlled adoption path to clarify what current evaluations support.

### Source excerpt

arXiv:2611.21620v1 Announce Type: new Abstract: Modern service systems combine rapidly changing dependencies, heterogeneous telemetry, and operational actions whose side effects may amplify an incident. Conventional AIOps research has produced effective detectors, localizers, and diagnostic models, yet surveys typically organize them by task, telemetry modality, or learning technique. Such taxonomies describe what a method predicts, but not which decisions it may make or which evidence justifies that authority. We survey the transition from AIOps pipelines to agentic service operations through three coupled lenses: capability, operational authority, and evaluation evidence. We first relate SOA, microservices, Kubernetes, service meshes, and serverless platforms to the incident lifecycle. We then review conventional AIOps methods and audit 22 language-model-enabled systems according to their evaluated behavior rather than their intended autonomy. The audit shows that most systems remain copilots or read-only investigators. Only two exercise write authority; both use constrained action envelopes, and neither carries controlled production-outcome evidence. Building on these findings, we synthesize a four-plane reference architecture, evidence grades, an evaluation ladder, and a controlled adoption path. Together, these artifacts clarify which claims current evaluations support and what evidence is still required for dependable agentic service operations.

## Evaluating AST-Derived Knowledge Graph Retrieval for AIOps Incident Diagnosis in Apache Kafka

DevFeed: [Evaluating AST-Derived Knowledge Graph Retrieval for AIOps Incident Diagnosis in Apache Kafka](<https://devfeed.tech/articles/evaluating-ast-derived-knowledge-graph-retrieval-for-aiops-incident-diagnosis-in-apache-kafka-139584.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21625>)

Author: Shashank Mishra, Shweta Mishra

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>)

Tags: [aiops](<https://devfeed.tech/tags/aiops.md>), [apache-kafka](<https://devfeed.tech/tags/apache-kafka.md>), [ast](<https://devfeed.tech/tags/ast.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [diagnosis](<https://devfeed.tech/tags/diagnosis.md>), [graph](<https://devfeed.tech/tags/graph.md>), [incident](<https://devfeed.tech/tags/incident.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [log](<https://devfeed.tech/tags/log.md>), [queries](<https://devfeed.tech/tags/queries.md>), [reranking](<https://devfeed.tech/tags/reranking.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [source](<https://devfeed.tech/tags/source.md>)

### AI overview

In Apache Kafka incident diagnosis, vector-only retrieval achieved Recall@20 of 0.956, and adding static or confidence-guided staged AST ownership-graph expansion did not significantly improve recall. Staging did reduce cross-encoder pair workload and measured reranking time by about 52% compared with static expansion. As an external control, HippoRAG scored 0.308 versus 0.803 for its ColBERTv2-only backbone; a post-hoc document ensemble raised its score to 0.648 but did not close the gap. In a manually evaluated 100-query study, AST-derived structural evidence showed no significant advantage in root-cause correctness. The findings are based on 1,600 source-linked log records and a 315-query benchmark covering 103 targets.

### Source excerpt

arXiv:2611.21625v1 Announce Type: new Abstract: Incident diagnosis requires retrieving source-linked operational evidence from large codebases. We evaluate graph-augmented retrieval for Apache Kafka using an abstract-syntax-tree (AST)-derived ownership graph over 1,600 source-linked log records and an audited benchmark of 315 incident-style queries covering 103 unique targets. Vector-only retrieval is a strong baseline at Recall@20 of 0.956, and neither static nor confidence-guided staged AST expansion significantly improves Recall@20 over it. As an external control we evaluate HippoRAG, a published text-derived graph-retrieval system, against its own ColBERTv2 retrieval backbone. Against ColBERTv2-only (Recall@20 0.803), HippoRAG attained 0.308; a post-hoc document-ensemble sensitivity raised Recall@20 to 0.648 but did not eliminate the deficit. Relative to static expansion, staging reduces cross-encoder pair workload and measured reranking time by about 52%. A manually evaluated 100-query downstream study finds no significant root-cause-correctness advantage for AST-derived structural evidence.

## Dynatrace recognized as a Leader in The Forrester Wave™: AIOps Platforms, Q4 2026

DevFeed: [Dynatrace recognized as a Leader in The Forrester Wave™: AIOps Platforms, Q4 2026](<https://devfeed.tech/articles/dynatrace-recognized-as-a-leader-in-the-forrester-wavetm-aiops-platforms-q4-2026-118023.md>)

Original publisher: [Read original article](<https://www.dynatrace.com/news/blog/dynatrace-recognized-as-a-leader-in-the-forrester-wave-aiops-platforms-q4-2026/>)

Author: Bob Wambach

Published: 2026-11-04T15:52:03Z

Content type: article

Language: en

Sources: [Dynatrace news](<https://devfeed.tech/sources/dynatrace-news.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [dynatrace](<https://devfeed.tech/topics/dynatrace.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [aiops-platforms](<https://devfeed.tech/tags/aiops-platforms.md>), [business](<https://devfeed.tech/tags/business.md>), [business-context](<https://devfeed.tech/tags/business-context.md>), [company-and-culture](<https://devfeed.tech/tags/company-and-culture.md>), [context](<https://devfeed.tech/tags/context.md>), [dynatrace](<https://devfeed.tech/tags/dynatrace.md>), [forrester](<https://devfeed.tech/tags/forrester.md>), [forrester-wave](<https://devfeed.tech/tags/forrester-wave.md>), [insights](<https://devfeed.tech/tags/insights.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [leader](<https://devfeed.tech/tags/leader.md>), [operational](<https://devfeed.tech/tags/operational.md>), [operational-intelligence](<https://devfeed.tech/tags/operational-intelligence.md>), [q4](<https://devfeed.tech/tags/q4.md>), [score](<https://devfeed.tech/tags/score.md>), [teams](<https://devfeed.tech/tags/teams.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

Dynatrace says it was named a Leader in Forrester's Q4 2026 AIOps Platforms Wave, with the highest Current Offering score and the highest possible scores in 16 criteria. The article describes its approach as combining telemetry in Grail with Smartscape's live topology and Dynatrace Intelligence to connect signals, dependencies, and business context for causal analysis and risk forecasting. The reported top scores include predictive risk forecasting, change impact control, causal root cause analysis, explainability, AI governance, and autonomous remediation. The article emphasizes that AIOps should help prevent incidents, while Forrester advises buyers to assess whether platforms can recommend or initiate mitigation before services are affected. It also stresses governed autonomy: define agent permissions, use least agency, and require human oversight for actions according to risk. Forrester's evaluation does not constitute an endorsement or product recommendation.

### Source excerpt

Dynatrace was recognized as a Leader in The Forrester Wave™: AIOps Platforms, Q4 2026, receiving the highest score in the Current Offering category and the highest possible score in 16 criteria. Operational intelligence connects telemetry with topology, business context, actionable insights, and governed action to help teams decide what to do next. AIOps is moving [...] The post Dynatrace recognized as a Leader in The Forrester Wave™: AIOps Platforms, Q4 2026 appeared first on Dynatrace news.

## Autonomous site reliability engineering startup Traversal bags $120M in funding at a $1B valuation

DevFeed: [Autonomous site reliability engineering startup Traversal bags $120M in funding at a $1B valuation](<https://devfeed.tech/articles/autonomous-site-reliability-engineering-startup-traversal-bags-120m-in-funding-at-a-1b-valuation-115910.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/03/autonomous-site-reliability-engineering-startup-traversal-bags-120m-in-funding-at-a-1b-valuation/>)

Author: Mike Wheatley

Published: 2026-11-04T03:47:11Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [site-reliability-engineering](<https://devfeed.tech/topics/site-reliability-engineering.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-sre](<https://devfeed.tech/tags/ai-sre.md>), [anish-agarwal](<https://devfeed.tech/tags/anish-agarwal.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-agents](<https://devfeed.tech/tags/artificial-intelligence-agents.md>), [automate](<https://devfeed.tech/tags/automate.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-site-reliability-engineer](<https://devfeed.tech/tags/autonomous-site-reliability-engineer.md>), [autonomous-sre](<https://devfeed.tech/tags/autonomous-sre.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [funding](<https://devfeed.tech/tags/funding.md>), [it-environments](<https://devfeed.tech/tags/it-environments.md>), [it-infrastructure](<https://devfeed.tech/tags/it-infrastructure.md>), [khosla-ventures](<https://devfeed.tech/tags/khosla-ventures.md>), [kleiner-perkins](<https://devfeed.tech/tags/kleiner-perkins.md>), [news](<https://devfeed.tech/tags/news.md>), [production-environments](<https://devfeed.tech/tags/production-environments.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [reliability-engineering](<https://devfeed.tech/tags/reliability-engineering.md>), [site](<https://devfeed.tech/tags/site.md>), [site-reliability](<https://devfeed.tech/tags/site-reliability.md>), [site-reliability-engineer](<https://devfeed.tech/tags/site-reliability-engineer.md>), [site-reliability-engineering](<https://devfeed.tech/tags/site-reliability-engineering.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [traversal](<https://devfeed.tech/tags/traversal.md>), [valuation](<https://devfeed.tech/tags/valuation.md>)

### AI overview

Traversal raised $120 million at a $1 billion valuation in a round led by Kleiner Perkins, Redpoint Ventures and Khosla Ventures, with Sequoia Capital, Battery Ventures and Amex Ventures participating. Its product is an autonomous SRE agent that analyzes operational logs, metrics and traces to establish normal behavior, diagnose infrastructure problems using causal machine learning, and recommend fixes for a human engineer to accept. The article says general-purpose frontier models score barely 25% on medium-difficulty SRE tasks in the ORCA-bench benchmark, while often hallucinating at rates above 40%; it does not provide a comparative accuracy figure for Traversal. The company reports revenue grew more than ninefold and monthly active users increased twentyfold over the past year, and names PepsiCo, DigitalOcean, Nubank and Harvey AI as customers. It plans to use the funding to expand engineering, go-to-market and research and development hiring.

### Source excerpt

Traversal Inc., a startup that's trying to automate site reliability engineering tasks with artificial intelligence agents, seems to be closing in on that goal after raising $120 million in fresh funding, bringing its valuation to $1 billion. The newly minted unicorn's round was led by Kleiner Perkins, Redpoint Ventures and Khosla Ventures, three of Silicon [...] The post Autonomous site reliability engineering startup Traversal bags $120M in funding at a $1B valuation appeared first on SiliconANGLE.

## Harish Babu Guttikonda on Autonomous Cloud Infrastructure

DevFeed: [Harish Babu Guttikonda on Autonomous Cloud Infrastructure](<https://devfeed.tech/articles/harish-babu-guttikonda-on-autonomous-cloud-infrastructure-106122.md>)

Original publisher: [Read original article](<https://hackernoon.com/harish-babu-guttikonda-on-autonomous-cloud-infrastructure?source=rss>)

Author: Jon Stojan Journalist

Published: 2026-10-29T08:30:22Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Cloud Native Operations](<https://devfeed.tech/topics/cloud-native-operations.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [observability](<https://devfeed.tech/topics/observability.md>), [cloud-infrastructure](<https://devfeed.tech/topics/cloud-infrastructure.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [abstraction](<https://devfeed.tech/tags/abstraction.md>), [access-management](<https://devfeed.tech/tags/access-management.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adapting](<https://devfeed.tech/tags/adapting.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-devops-automation](<https://devfeed.tech/tags/agentic-devops-automation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-security](<https://devfeed.tech/tags/ai-agent-security.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-native-cloud-infrastructure](<https://devfeed.tech/tags/ai-native-cloud-infrastructure.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-cloud-operations](<https://devfeed.tech/tags/autonomous-cloud-operations.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [cloudctl-cctl-open-source](<https://devfeed.tech/tags/cloudctl-cctl-open-source.md>), [control](<https://devfeed.tech/tags/control.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [governance](<https://devfeed.tech/tags/governance.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [intent-to-infrastructure](<https://devfeed.tech/tags/intent-to-infrastructure.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [planes](<https://devfeed.tech/tags/planes.md>), [self-healing](<https://devfeed.tech/tags/self-healing.md>)

### AI overview

The article describes Harish Babu Guttikonda's approach to cloud operations: an AI control plane interprets high-level infrastructure goals against live environment state, while standardized telemetry interfaces provide operational context and deterministic pipelines validate changes. It presents self-healing as a shift from threshold-triggered alerts to state comparison and pre-validated corrective actions, with versioned changes, policy checks, and ephemeral cryptographic agent attestations intended to govern access. The text reports an evaluation with 74% fewer manual diagnostic steps, reducing 11 operations to one autonomous command, and 92.6% diagnostic accuracy. It also describes cloudctl (cctl on PyPI) as an open-source implementation and positions reliability engineers' future work around governance and policy design. These are claims and figures reported in the supplied article; it does not provide the evaluation methodology or comparative results against other tools.

### Source excerpt

Explore how Harish Babu Guttikonda applies AI control planes, self-healing pipelines, and deterministic governance to autonomous cloud infrastructure.

## Datadog named a Leader in the Forrester Wave™: AIOps Platforms, Q4 2026

DevFeed: [Datadog named a Leader in the Forrester Wave™: AIOps Platforms, Q4 2026](<https://devfeed.tech/articles/datadog-named-a-leader-in-the-forrester-wavetm-aiops-platforms-q4-2026-107136.md>)

Original publisher: [Read original article](<https://www.datadoghq.com/blog/datadog-aiops-platforms-forrester-wave-2026/>)

Author: Yanbing Li

Published: 2026-10-29T00:00:00Z

Content type: release

Language: en

Sources: [Datadog](<https://devfeed.tech/sources/datadog-the-monitor-blog.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [bits ai](<https://devfeed.tech/topics/bits-ai.md>), [datadog](<https://devfeed.tech/topics/datadog.md>), [observability](<https://devfeed.tech/topics/observability.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-observability](<https://devfeed.tech/tags/agent-observability.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [datadog](<https://devfeed.tech/tags/datadog.md>), [forrester](<https://devfeed.tech/tags/forrester.md>), [leader](<https://devfeed.tech/tags/leader.md>), [observability](<https://devfeed.tech/tags/observability.md>), [operations](<https://devfeed.tech/tags/operations.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [q4](<https://devfeed.tech/tags/q4.md>), [report](<https://devfeed.tech/tags/report.md>)

### AI overview

Datadog says its Forrester Wave™: AIOps Platforms, Q4 2026 Leader placement reflects a shift from observability toward agentic operations. Its Bits AI investigates production issues, learns from runbooks and engineer feedback, and can propose fixes, create code and pull requests, and run remediation workflows within customer-defined approval and service guardrails. Datadog says Bits AI exposes its reasoning and evidence; Forrester awarded the highest score possible in Innovation and Roadmap, Zero-Trust Agent (Least-Agency), and ModelOps and AI Governance (Sovereignty). The platform combines telemetry, AI observability, OpenTelemetry ingestion, data pipeline controls, historical analytics, and over 1,000 integrations. Datadog cites Uber Freight's 40-day move from pilot to production, 99.99% uptime, and more than 20 minutes saved per incident with Bits AI reports. These are company-reported capabilities and customer results; Forrester's disclaimer says its ratings are not endorsements.

### Source excerpt

Datadog has been named a Leader in this report, reflecting Datadog's commitment to transforming observability into AI-powered, autonomous operations.

## Elastic is a Strong Performer in The Forrester Wave™ for AIOps Platforms, Q4 2026

DevFeed: [Elastic is a Strong Performer in The Forrester Wave™ for AIOps Platforms, Q4 2026](<https://devfeed.tech/articles/elastic-is-a-strong-performer-in-the-forrester-wavetm-for-aiops-platforms-q4-2026-105794.md>)

Original publisher: [Read original article](<https://www.elastic.co/blog/forrester-wave-aiops-platforms-2026>)

Author: Natalie Blake

Published: 2026-10-28T00:00:00Z

Content type: release

Language: en

Sources: [Elastic Blog](<https://devfeed.tech/sources/elastic-blog-elasticsearch-kibana-and-elk-stack.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Logging](<https://devfeed.tech/topics/logging.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coworker](<https://devfeed.tech/tags/ai-coworker.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-sre](<https://devfeed.tech/tags/ai-sre.md>), [ai-stack](<https://devfeed.tech/tags/ai-stack.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [always-on-ai](<https://devfeed.tech/tags/always-on-ai.md>), [complete](<https://devfeed.tech/tags/complete.md>), [context](<https://devfeed.tech/tags/context.md>), [elastic](<https://devfeed.tech/tags/elastic.md>), [forrester](<https://devfeed.tech/tags/forrester.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [observability-log-analytics-metrics](<https://devfeed.tech/tags/observability-log-analytics-metrics.md>), [opentelemetry-log-management](<https://devfeed.tech/tags/opentelemetry-log-management.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [q4](<https://devfeed.tech/tags/q4.md>)

### AI overview

Forrester named Elastic a Strong Performer in its Q4 2026 AIOps Platforms Wave, evaluating 10 providers across 24 criteria; Elastic says it received the highest possible scores in five, including explainability, OpenTelemetry and GitOps alignment, sovereign deployment, and pricing transparency. Elastic describes its nightshift AI SRE as an always-on agent that shows its reasoning, data, alternatives, and supporting evidence for engineers to verify before approving actions. It says cost-efficient storage lets teams retain logs, traces, and metrics together, while compact environmental context helps the agent reason efficiently. The agent carries lessons from earlier incidents into later investigations and aims to surface issues beyond rule-based alerts. Elastic also emphasizes native-form telemetry and OpenTelemetry to support instrumentation changes without rebuilding pipelines or translating schemas. These are Elastic's descriptions; the article notes Forrester does not endorse products or advise selection based on its ratings.

### Source excerpt

Elastic is a Strong Performer in The Forrester Wave™: AIOps Platforms, Q4 2026. Elastic's AI is built on complete context, shows its evidence, and learns from every investigation.

## Operating in the agentic era: AIOps sessions at re:Invent 2026

DevFeed: [Operating in the agentic era: AIOps sessions at re:Invent 2026](<https://devfeed.tech/articles/operating-in-the-agentic-era-aiops-sessions-at-re-invent-2026-101696.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/mt/operating-in-the-agentic-era-aiops-sessions-at-reinvent-2026/>)

Author: Matheus Arrais

Published: 2026-10-26T18:04:40Z

Content type: article

Language: en

Sources: [AWS Cloud Operations Blog](<https://devfeed.tech/sources/aws-cloud-operations-blog.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Service fabric](<https://devfeed.tech/topics/service-fabric.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-investigation](<https://devfeed.tech/tags/agentic-investigation.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [cloud-operations](<https://devfeed.tech/tags/cloud-operations.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-tools](<https://devfeed.tech/tags/coding-tools.md>), [incident](<https://devfeed.tech/tags/incident.md>), [operational](<https://devfeed.tech/tags/operational.md>), [operations](<https://devfeed.tech/tags/operations.md>), [re-invent](<https://devfeed.tech/tags/re-invent.md>), [release](<https://devfeed.tech/tags/release.md>), [review](<https://devfeed.tech/tags/review.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [tools](<https://devfeed.tech/tags/tools.md>), [volume](<https://devfeed.tech/tags/volume.md>)

### AI overview

The re:Invent 2026 AIOps sessions present AI agents as tools for investigating incidents, recommending or carrying out remediation, reviewing releases, and finding proactive operational improvements. AWS DevOps Agent is described as correlating telemetry, logs, and code across AWS, multicloud, and on-premises systems to identify likely root causes and suggest targeted actions; customer talks report investigations shortened from hours to minutes. Sessions cover hands-on fault injection and custom skills, agent protocols and orchestration options, and release readiness based on runtime health and deployment risk. Safety and accountability topics include opt-in controls, per-action approvals, guardrails, audit traces, drift detection, and an investigation-scoped Linux sandbox with read-only AWS access. The text recommends pairing strategy sessions with practical workshops or builders' sessions; limited-seat workshops should be reserved early.

### Source excerpt

Telemetry volume and incident counts keep growing while operations headcount stays flat, and coding tools now produce changes faster than most release processes can review them. The AIOps topic on the re:Invent 2026 Cloud Operations (COP) track covers how AI agents handle operational work: investigating incidents, recommending fixes, reviews code changes to catch issues before [...]

## NVIDIA Minerva Brings AIOps to AI Factories Through Dell, Lenovo, and Supermicro

DevFeed: [NVIDIA Minerva Brings AIOps to AI Factories Through Dell, Lenovo, and Supermicro](<https://devfeed.tech/articles/nvidia-minerva-brings-aiops-to-ai-factories-through-dell-lenovo-and-supermicro-101892.md>)

Original publisher: [Read original article](<https://www.storagereview.com/news/nvidia-minerva-aiops-ai-factory-observability-dell-lenovo-supermicro>)

Author: Brian Beeler

Published: 2026-10-26T15:06:57Z

Content type: news

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [dell](<https://devfeed.tech/topics/dell.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-factories](<https://devfeed.tech/tags/ai-factories.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [dell](<https://devfeed.tech/tags/dell.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [gtc](<https://devfeed.tech/tags/gtc.md>), [lenovo](<https://devfeed.tech/tags/lenovo.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [networking](<https://devfeed.tech/tags/networking.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [operations](<https://devfeed.tech/tags/operations.md>), [software](<https://devfeed.tech/tags/software.md>), [storage](<https://devfeed.tech/tags/storage.md>), [supermicro](<https://devfeed.tech/tags/supermicro.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>)

### AI overview

NVIDIA Minerva combines telemetry from GPUs, networks, storage, schedulers, and AI workloads to detect developing faults and trace slow jobs to likely causes across large AI clusters. It maps infrastructure and scheduled jobs in a dynamic knowledge graph, analyzes billions of data points per hour, and groups related alerts into incidents. Operators can query telemetry with a built-in assistant and choose whether people or automation apply recommended fixes. Dell Technologies, Lenovo, and Supermicro plan to offer Minerva; IREN is already using it, while several other organizations plan deployments. NVIDIA has not published pricing, general availability, quantified uptime or repair results, or details on how Minerva fits with Mission Control and DSX OS or how OEM offerings will be packaged.

### Source excerpt

NVIDIA announced Minerva at GTC Berlin, an AIOps platform that pulls telemetry from GPUs, networking, storage, schedulers, and the AI workloads running on them, then applies machine learning to find a degrading component before it slows a training job. Dell Technologies, Lenovo, and Supermicro will offer it in their AI factory operations portfolios, IREN is The post NVIDIA Minerva Brings AIOps to AI Factories Through Dell, Lenovo, and Supermicro appeared first on StorageReview.com.

## Bitdeer AI Brings NVIDIA Minerva's AI-Native AIOps For Maximizing AI Factory Yield

DevFeed: [Bitdeer AI Brings NVIDIA Minerva's AI-Native AIOps For Maximizing AI Factory Yield](<https://devfeed.tech/articles/bitdeer-ai-brings-nvidia-minerva-s-ai-native-aiops-for-maximizing-ai-factory-yield-95860.md>)

Original publisher: [Read original article](<https://www.bitdeer.ai/en/blog/nvidia-minerva/>)

Author: Evelyn Xiong

Published: 2026-10-22T15:09:48Z

Content type: release

Language: en

Sources: [Bitdeer AI Cloud](<https://devfeed.tech/sources/bitdeer-ai-cloud.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>), [NVIDIA DSX](<https://devfeed.tech/topics/nvidia-dsx.md>), [NCCL](<https://devfeed.tech/topics/nccl.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [ai-factories](<https://devfeed.tech/tags/ai-factories.md>), [ai-factory](<https://devfeed.tech/tags/ai-factory.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [ai-training-and-inference](<https://devfeed.tech/tags/ai-training-and-inference.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [alert](<https://devfeed.tech/tags/alert.md>), [bitdeer](<https://devfeed.tech/tags/bitdeer.md>), [factory](<https://devfeed.tech/tags/factory.md>), [native](<https://devfeed.tech/tags/native.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [yield](<https://devfeed.tech/tags/yield.md>)

### AI overview

Bitdeer AI says it now supports NVIDIA Minerva, an AI-native AIOps platform for AI Factory infrastructure. Minerva correlates metric, log, and topology telemetry across NVIDIA hardware, networking, NCCL, schedulers, and AI workloads into a cluster-and-job knowledge graph. It analyzes telemetry in real time to learn normal behavior, predict anomalies, and correlate events; operators can use its MCP server and Sherlock assistant to investigate live telemetry in natural language. NVIDIA reports internal test results including one NVMe power-fault repair reduced from a multi-day outage to six hours, and 81 noisy events consolidated into one alert, saving 54 hours of cluster uptime. Bitdeer says the platform is available standalone or integrated with NVIDIA DSX OS and is intended to improve uptime and productive GPU hours as its infrastructure scales.

### Source excerpt

Bitdeer AI Brings NVIDIA Minerva's AI-Native AIOps For Maximizing AI Factory Yield.

## Can We Run Autonomous AI Agents in Production?

DevFeed: [Can We Run Autonomous AI Agents in Production?](<https://devfeed.tech/articles/can-we-run-autonomous-ai-agents-in-production-84375.md>)

Original publisher: [Read original article](<https://blog.devops.dev/can-we-run-autonomous-ai-agents-in-production-484b57cad8dc?source=rss----33f8b2d9a328---4>)

Author: ObsNSods

Published: 2026-10-09T20:06:01Z

Content type: article

Language: en

Sources: [DevOps.dev](<https://devfeed.tech/sources/devops-dev.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>), [Splunk Cloud](<https://devfeed.tech/topics/splunk-cloud.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [automation](<https://devfeed.tech/tags/automation.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [banking](<https://devfeed.tech/tags/banking.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data](<https://devfeed.tech/tags/data.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [grafana](<https://devfeed.tech/tags/grafana.md>), [grafana-cloud](<https://devfeed.tech/tags/grafana-cloud.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [llms](<https://devfeed.tech/tags/llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [sre](<https://devfeed.tech/tags/sre.md>)

### AI overview

The article argues that production AI workflows should gate each step on evidence appropriate to the action's consequences, rather than treating an agent's answer or confidence as sufficient. VectorStep, the author's free, code-defined orchestration tool, makes workflows explicit and version controlled, with checks governing whether to continue, retry, stop, or escalate to a human. Its "Trust Vector" combines agent confidence, independent verification, evidence grounding, deterministic checks, and historical calibration; these remain separate signals rather than a single averaged trust score. In the production alert example, a triage report can be checked against evidence and alert-specific remediation rules before proceeding. The author cautions that verifiers and sources can also be wrong, so the approach makes uncertainty visible but cannot guarantee truth.

### Source excerpt

VectorStep's tag line I've spent most of my career in observability, in industries -banking, insurance, healthcare - where "let the AI just handle it" isn't a casual decision. VectorStep, the AI pipeline orchestration tool I built out of that experience, went public this week. Here's the story of why I built it, and the idea at the center of it. I arrived unfashionably late to the OpenClaw party around March this year. When I started reading about implementing a personal AI assistant I couldn't necessarily see what I might need a fleet of agents for in my personal life. I have no interest in having AI check-in for flights (I don't go on many flights these days) or produce a morning briefing (what would AI brief me on?) but I have for many years tried to find ingenious ways to try and make my weekend hobby of sports betting profitable by delving into stats using tools such as Splunk and streaming odds into grafana cloud and analysing from there. What interested me wasn't really the betting itself, but the idea of building a system that could continuously watch a bunch of data, spot something interesting and then help me decide what to do with it. So it was this use-case that got me tinkering with Openclaw. I liked the idea of agents just continually keeping context and essentially getting to know you and keeping a memory. But in practice, in my opinion, memory management and the idea that your personal agents just "remember" and "know" stuff about you is still some way off. But what tinkering with these tools and features did do is cement my thinking on how AI could be useful in my working life. I have worked in observability for an awfully long time and I have heard the term AIOps used so often and for so long i've almost become immune to anything an article says after it. Quite frankly, AIOps used to mean some sort of automation and at best some machine learning. At a stretch you could tag that "Artificial Intelligence", but not as we know it today with LLMs. Thing

## Beyond Operational Obsolescence: The New Paradigm of IT Management in the AI Era

DevFeed: [Beyond Operational Obsolescence: The New Paradigm of IT Management in the AI Era](<https://devfeed.tech/articles/beyond-operational-obsolescence-the-new-paradigm-of-it-management-in-the-ai-era-62634.md>)

Original publisher: [Read original article](<https://blogs.cisco.com/innovation/beyond-operational-obsolescence-the-new-paradigm-of-it-management-in-the-ai-era>)

Author: Michele Festuccia

Published: 2026-09-30T20:17:59Z

Content type: article

Language: en

Sources: [Cisco Blogs](<https://devfeed.tech/sources/cisco-blogs.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [configuration-management](<https://devfeed.tech/topics/configuration-management.md>), [Legacy Modernization](<https://devfeed.tech/topics/legacy-modernization.md>), [Infrastructure as a Service (IaaS)](<https://devfeed.tech/topics/infrastructure-as-a-service-iaas.md>)

Tags: [aiops](<https://devfeed.tech/tags/aiops.md>), [cisco-networking](<https://devfeed.tech/tags/cisco-networking.md>), [devops](<https://devfeed.tech/tags/devops.md>), [digital-transformation](<https://devfeed.tech/tags/digital-transformation.md>), [infrastructure-as-code](<https://devfeed.tech/tags/infrastructure-as-code.md>), [innovation](<https://devfeed.tech/tags/innovation.md>), [it-management](<https://devfeed.tech/tags/it-management.md>), [it-modernization](<https://devfeed.tech/tags/it-modernization.md>), [legacy](<https://devfeed.tech/tags/legacy.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>), [risk](<https://devfeed.tech/tags/risk.md>)

### AI overview

The article argues that rapidly changing hybrid infrastructure and more capable AI models make traditional, static IT operations inadequate and risky. It proposes evolving ITIL through automated processes, digitalized intent, automated execution, and continuous validation. The supplied summary describes Cisco's three-pillar approach as Services as Code, AIOps, and AI-powered DevOps, aimed at autonomous, self-healing infrastructure.

### Source excerpt

Modern IT requires more than legacy models. Learn how Cisco's three-pillar strategy--Services as Code, AIOps, and AI-powered DevOps--enables a shift to autonomous, self-healing infrastructure that reduces risk and accelerates innovation.

## 80% of network pros are OK with giving AI an autonomous role in network operations

DevFeed: [80% of network pros are OK with giving AI an autonomous role in network operations](<https://devfeed.tech/articles/80-of-network-pros-are-ok-with-giving-ai-an-autonomous-role-in-network-operations-58591.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4225341/80-of-network-pros-are-ok-with-giving-ai-an-autonomous-role-in-network-operations.html>)

Author: Paul Desmond

Published: 2026-09-23T13:00:00Z

Content type: news

Language: en

Sources: [Network World](<https://devfeed.tech/sources/network-world.md>)

Topics: [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [Network](<https://devfeed.tech/topics/network.md>), [Cisco](<https://devfeed.tech/topics/cisco.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-network-management-software-networking](<https://devfeed.tech/tags/artificial-intelligence-network-management-software-networking.md>), [cisco](<https://devfeed.tech/tags/cisco.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [network-management-software](<https://devfeed.tech/tags/network-management-software.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [networking](<https://devfeed.tech/tags/networking.md>)

### AI overview

A Cisco and Omdia survey finds that many network and IT operations professionals already use agentic AI for corrective actions and are comfortable granting it significant autonomy in network operations. The report links adoption to rising network complexity and emphasizes the need for effective guardrails.

### Source excerpt

Network professionals are pinning their hopes on artificial intelligence to deliver them relief from an uptick in network complexity that is only getting worse, in no small part due to the increased use of artificial intelligence. A new report from Cisco and the research and advisory firm Omdia paints a picture of enterprise networks that have literally become too complex for humans to manage. The situation is so dire that 51% of respondents use agentic AI tools in production to take corrective action in real time, rather than simply taking advice from them. Eighty-four percent expect to reach a fully AI-led operating model within twelve months. Three-quarters of the 1,000 IT and network operations leaders surveyed say they use AI in some fashion for network operations, and 80% are comfortable granting AI a "high or fully autonomous role" in network operations. More than half of respondents (56%) will do so only with a human approving those actions, but 24% are comfortable with AI taking network actions with no human oversight. The vast majority (82%) are comfortable allowing AI to make some production network changes on its own for some categories. Cisco calls it a move from AIOps to agent-powered operations, or AgenticOps. Longtime industry watchers such as Zeus Kerravala, founder and principal analyst at ZK Research, are on board with the idea. "You have to have agentic operations. Networking pros will embrace it," he says. It may take some time to fully develop trust in the new tools, but that will come, too--similar to the curve for autonomous vehicles, which he notes get in far fewer accidents than cars with human drivers. By the same token, agentic AI tools are "going to make mistakes, but a lot fewer than people will. And it's going to let people focus on things that are higher value," Kerravala says. Jim Frey, principal analyst, networking, at Omdia, who helped develop the Cisco survey, likewise sees the move to AgenticOps as inevitable. "To me it's a combin

## When Security Operations Can't Keep Up: 4 Ways Agentic Network Security Management Improves Security Operations

DevFeed: [When Security Operations Can't Keep Up: 4 Ways Agentic Network Security Management Improves Security Operations](<https://devfeed.tech/articles/when-security-operations-can-t-keep-up-4-ways-agentic-network-security-management-improves-security-operations-55331.md>)

Original publisher: [Read original article](<https://blog.checkpoint.com/hybrid-mesh/when-security-operations-cant-keep-up-4-ways-agentic-network-security-management-improves-security-operations/>)

Author: lizwu@checkpoint.com

Published: 2026-09-18T13:00:09Z

Content type: article

Language: en

Sources: [Check Point Blog](<https://devfeed.tech/sources/check-point-blog.md>)

Topics: [network security](<https://devfeed.tech/topics/network-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Firewall](<https://devfeed.tech/topics/firewall.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [firewall](<https://devfeed.tech/tags/firewall.md>), [hybrid-mesh](<https://devfeed.tech/tags/hybrid-mesh.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [network-security](<https://devfeed.tech/tags/network-security.md>), [protection](<https://devfeed.tech/tags/protection.md>), [security](<https://devfeed.tech/tags/security.md>), [security-operations](<https://devfeed.tech/tags/security-operations.md>)

### AI overview

This article explains how agentic network security management can help security teams handle changing hybrid environments. It discusses continuously optimizing firewall policies for zero trust, detecting operational issues through AIOps and telemetry, and prioritizing threat prevention based on actual risk.

### Source excerpt

Security teams are under pressure. Networks are growing. Cloud environments are expanding. AI is accelerating change across users, applications, and infrastructure. At the same time, security teams are expected to maintain strong protection, support business initiatives, and operate efficiently. The challenge is not a lack of security control. The challenge is keeping up with a hybrid environment that changes faster than people can manage it. This challenge will only grow as organizations adopt AI. Gartner predicts that by 2028, 15% of day-to-day work decisions will be made autonomously by agentic AI. As environments become more dynamic, security operations will need to be adapted. This is where agentic network security [...] The post When Security Operations Can't Keep Up: 4 Ways Agentic Network Security Management Improves Security Operations appeared first on Check Point Blog.

## 16 governance tools for securing your AI fleet

DevFeed: [16 governance tools for securing your AI fleet](<https://devfeed.tech/articles/16-governance-tools-for-securing-your-ai-fleet-50547.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4223016/16-governance-tools-for-securing-your-ai-fleet-2.html>)

Author: Peter Wayner

Published: 2026-09-18T10:01:00Z

Content type: comparison

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Security](<https://devfeed.tech/topics/security.md>), [trust](<https://devfeed.tech/topics/trust.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [application-security-artificial-intelligence-data-and-information-security-it-governance-securit](<https://devfeed.tech/tags/application-security-artificial-intelligence-data-and-information-security-it-governance-securit.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [data-and-information-security](<https://devfeed.tech/tags/data-and-information-security.md>), [governance](<https://devfeed.tech/tags/governance.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [it-governance](<https://devfeed.tech/tags/it-governance.md>), [llms](<https://devfeed.tech/tags/llms.md>), [security](<https://devfeed.tech/tags/security.md>), [tools](<https://devfeed.tech/tags/tools.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

A comparison of 16 tools for governing and securing AI fleets, with a focus on production LLM risks such as hallucinations, data leakage, and misinformation. The article describes overlapping governance, trust, guardrail, privacy, and agent-management capabilities, including Collibra's AI Command Center and Unified Control Plane.

### Source excerpt

Every DevOps team member knows that dealing with an AI is like being a circus lion tamer. The boss and the audience are happy when the lions sit on the pedestal and roar on cue, but there's always the danger that they'll go rogue and bring the whole show to a quick and disastrous end. The reality is that running LLMs in production means being ready to handle hallucinations, data leakage, misinformation, madness, or worse. Lately, a range of companies have emerged to offer tools, platforms, and systems aimed at helping AIOps teams shoulder the load of keeping AIs in check. They're building algorithms that are an amalgamation of psychiatrist, police officer, social worker, politruk, and office snitch. Yes, some have their own LLMs buried inside, an irony not lost on anyone, but at least they're trying. These tools often have words like "guardrails," "governance," or "trust" in their name. They're closely related to other AIOps tools that focus on development or benchmarking. These emerging product categories often overlap and that overlap will only grow as AI -- and the market surrounding the technology -- continues to evolve. Other AI-Related Tools for Solutions for Your AI Fleet - 20 AI workflow tools for adding intelligence to business processes - 21 agent orchestration tools for managing your AI fleet - 19 AgentOps tools for monitoring AI activity, issues, and costs - 13 tools for evaluating and benchmarking agentic AI systems - 19 vibe coding tools for democratizing app development Here in alphabetical order are 16 of the most interesting companies working on controlling the wonderful and dangerous LLMs that promise to do so much -- as long as they can be kept on that pedestal and behaving. Collibra Data products require controlling access enough to stop leaks while providing just the right data that the clients need. Collibra offers an AI Command Center that merges tools for governance and privacy protection with general agent management jobs such as minimizing the

## What is AIOps?

DevFeed: [What is AIOps?](<https://devfeed.tech/articles/what-is-aiops-41388.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/what-is-aiops>)

Author: Databricks Staff

Published: 2026-09-17T16:49:43Z

Content type: tutorial

Language: en

Sources: [Databricks](<https://devfeed.tech/sources/databricks.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data-plus-ai-foundations](<https://devfeed.tech/tags/data-plus-ai-foundations.md>), [devops](<https://devfeed.tech/tags/devops.md>), [logs](<https://devfeed.tech/tags/logs.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [network](<https://devfeed.tech/tags/network.md>), [observability](<https://devfeed.tech/tags/observability.md>)

### AI overview

This guide explains AIOps, which applies AI and machine learning to IT operations to detect anomalies, correlate events, identify root causes, and trigger responses. It describes how AIOps analyzes logs, traces, events, and network topology, while complementing observability, DevOps, and human judgment.

### Source excerpt

Artificial Intelligence for IT Operations (AIOps) applies AI and machine learning to IT operations to detect anomalies...

## Becoming an AI Team

DevFeed: [Becoming an AI Team](<https://devfeed.tech/articles/becoming-an-ai-team-1228.md>)

Original publisher: [Read original article](<https://medium.com/pinterest-engineering/becoming-an-ai-team-866d6b567803?source=rss----4c5a5f6279b6---4>)

Author: Pinterest Engineering

Published: 2026-09-01T15:01:06Z

Content type: article

Language: en

Sources: [Pinterest](<https://devfeed.tech/sources/pinterest-engineering-blog-medium.md>)

Topics: [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>)

Tags: [accessible](<https://devfeed.tech/tags/accessible.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-ai](<https://devfeed.tech/tags/artificial-intelligence-ai.md>), [automate](<https://devfeed.tech/tags/automate.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [contributors](<https://devfeed.tech/tags/contributors.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data](<https://devfeed.tech/tags/data.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-productivity](<https://devfeed.tech/tags/developer-productivity.md>), [development](<https://devfeed.tech/tags/development.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-culture](<https://devfeed.tech/tags/engineering-culture.md>), [execution](<https://devfeed.tech/tags/execution.md>), [goals](<https://devfeed.tech/tags/goals.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [pinterest](<https://devfeed.tech/tags/pinterest.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

The article argues that becoming an AI team requires changing how work is prioritized and managed, not just adding tools. At Pinterest, AI agents help write and validate Spark jobs, triage alerts, investigate database issues, and enable larger infrastructure refactors; the article says this shifts engineers toward roadmap work and strategic problem-solving. Because AI makes more projects feasible, teams still need to choose work for its strategic value. The transition can strain teams that remain fully committed while learning new tools, so managers should set direction, provide time for experimentation, share useful practices, and make it safe to learn from failures. The examples and claims are the author's account of Pinterest teams.

### Source excerpt

John Grass | Sr. Manager, Engineering A Fundamental Transformation An AI team is fundamentally more than just a group whose members incorporate AI tools into their existing workflows. The journey to becoming an AI team necessitates a fundamental and comprehensive paradigm shift in how the team defines ownership, engages in strategic planning, and, most critically, executes on its core goals and objectives. This transformation is not merely an addition of new technology; it is a restructuring of the team's operating model, philosophy, and individual roles. Becoming an AI team requires a holistic shift: team members transition from routine, manual execution to empowered, AI-augmented strategists and problem-solvers. In an AI-centric environment, every single member is significantly empowered, not only through access to cutting-edge AI tools and sophisticated models but through an expanded scope of responsibility and influence. These new capabilities allow individuals to automate routine tasks, accelerate data analysis, and rapidly prototype solutions, freeing up cognitive resources for higher-level, more strategic thinking. The expectation shifts from simply completing tasks to orchestrating intelligent systems and focusing on solving problems that were previously intractable. Consequently, the very nature of the work for both individual contributors and managers will be fundamentally different from anything that has come before. At Pinterest, this isn't theoretical. Our infrastructure teams sit at the core of a product that serves billions of Pins, boards, ads, and real-time signals. That reality has forced us to treat "becoming an AI team" as an operational necessity, not a side project as we cannot keep scaling reliability, cost efficiency, and developer productivity using only traditional playbooks. AI Team Capabilities The advent of accessible Artificial Intelligence (AI) tools has fundamentally raised the performance ceiling for what development teams can accomp

## SREs To AI Agents: Prove Yourself Before You Touch Production

DevFeed: [SREs To AI Agents: Prove Yourself Before You Touch Production](<https://devfeed.tech/articles/sres-to-ai-agents-prove-yourself-before-you-touch-production-48014.md>)

Original publisher: [Read original article](<https://www.nextplatform.com/control/2026/07/15/sres-to-ai-agents-prove-yourself-before-you-touch-production/5271533>)

Author: Published

Published: 2026-07-15T02:15:35Z

Content type: article

Language: en

Sources: [The Next Platform: In-depth coverage of high end computing](<https://devfeed.tech/sources/the-next-platform-in-depth-coverage-of-high-end-computing.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [site-reliability-engineering](<https://devfeed.tech/topics/site-reliability-engineering.md>), [observability](<https://devfeed.tech/topics/observability.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [downtime](<https://devfeed.tech/topics/downtime.md>), [Security](<https://devfeed.tech/topics/security.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [control](<https://devfeed.tech/tags/control.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [neubird](<https://devfeed.tech/tags/neubird.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [sponsored](<https://devfeed.tech/tags/sponsored.md>), [sre](<https://devfeed.tech/tags/sre.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

This sponsored article examines why enterprises remain cautious about deploying AI agents in production operations. It highlights trust, ROI, security, and data quality concerns, and describes NeuBird AI's approach of correlating observability signals and using agentic instrumentation to support higher-confidence investigations.

### Source excerpt

Trusting an AI agent to summarize user complaints about downtime is one thing; trusting it to fix th ...

## Pop Goes the Stack | VibeOps: Guardrailed agents for deterministic production | AIOps

DevFeed: [Pop Goes the Stack | VibeOps: Guardrailed agents for deterministic production | AIOps](<https://devfeed.tech/articles/pop-goes-the-stack-vibeops-guardrailed-agents-for-deterministic-production-aiops-66253.md>)

Original publisher: [Read original article](<https://www.youtube.com/watch?v=W7H9XALjvkQ>)

Published: 2026-03-10T12:00:00Z

Content type: article

Language: en

Sources: [Automate Your Network](<https://devfeed.tech/sources/automate-your-network.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [AIOps for Kubernetes](<https://devfeed.tech/topics/aiops-for-kubernetes.md>)

Tags: [agent-adoption](<https://devfeed.tech/tags/agent-adoption.md>), [agent-development-kit](<https://devfeed.tech/tags/agent-development-kit.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ops](<https://devfeed.tech/tags/agentic-ops.md>), [agents-governance](<https://devfeed.tech/tags/agents-governance.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [conversational-operations](<https://devfeed.tech/tags/conversational-operations.md>), [deterministic-production](<https://devfeed.tech/tags/deterministic-production.md>), [deterministic-workflows](<https://devfeed.tech/tags/deterministic-workflows.md>), [f5](<https://devfeed.tech/tags/f5.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [human-on-the-loop](<https://devfeed.tech/tags/human-on-the-loop.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [langgraph](<https://devfeed.tech/tags/langgraph.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-protocol](<https://devfeed.tech/tags/mcp-protocol.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [netdevops](<https://devfeed.tech/tags/netdevops.md>), [network-automation-agents](<https://devfeed.tech/tags/network-automation-agents.md>), [nginx](<https://devfeed.tech/tags/nginx.md>), [octo](<https://devfeed.tech/tags/octo.md>), [office-of-the-cto](<https://devfeed.tech/tags/office-of-the-cto.md>), [pop-goes-the-stack](<https://devfeed.tech/tags/pop-goes-the-stack.md>), [probabilistic-ai-risk](<https://devfeed.tech/tags/probabilistic-ai-risk.md>), [rag](<https://devfeed.tech/tags/rag.md>), [vibeops](<https://devfeed.tech/tags/vibeops.md>), [yaml](<https://devfeed.tech/tags/yaml.md>)

### AI overview

The video describes a shift in operations from YAML and careful deployment routines to probabilistic models, token-related cost surprises, and reliability questions. Its title identifies guardrailed agents for deterministic production as the subject.

### Source excerpt

F5, Inc. - Video publication

## AIOps: What we learned in 2025

DevFeed: [AIOps: What we learned in 2025](<https://devfeed.tech/articles/aiops-what-we-learned-in-2025-57199.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/generative-ai/aiops-what-we-learned-in-2025>)

Author: Zichuan Xiong

Published: 2026-01-30T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [blog](<https://devfeed.tech/tags/blog.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [rca](<https://devfeed.tech/tags/rca.md>), [root-cause-analysis](<https://devfeed.tech/tags/root-cause-analysis.md>)

### AI overview

Thoughtworks reports lessons from 20 AIOps proofs of concept across more than 16 clients in 2025, with eleven reaching production. The article identifies governance, operational knowledge, continuous tuning and buy-versus-build decisions as key factors in the gap between proof of concept and production. It highlights knowledge-focused use cases such as incident deduplication, operational knowledge retrieval and root-cause analysis, while noting that autonomous remediation and MCP-based agent communication remain constrained or immature.

### Source excerpt

AIOps: What we learned in 2025

## AI for Ops vs. Ops for AI

DevFeed: [AI for Ops vs. Ops for AI](<https://devfeed.tech/articles/ai-for-ops-vs-ops-for-ai-57197.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/generative-ai/ai-for-ops-vs-ops-for-AI>)

Author: Anton Baturan, Zichuan Xiong

Published: 2025-11-27T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [observability](<https://devfeed.tech/topics/observability.md>), [site-reliability-engineering](<https://devfeed.tech/topics/site-reliability-engineering.md>), [ai evaluation](<https://devfeed.tech/topics/ai-evaluation.md>), [incident](<https://devfeed.tech/topics/incident.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [incident](<https://devfeed.tech/tags/incident.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [observability](<https://devfeed.tech/tags/observability.md>)

### AI overview

This article distinguishes AI for Ops, which applies AI to improve IT operations, from Ops for AI, which manages AI models, pipelines, agents, and datasets as production systems. It compares their goals, practices, skill requirements, and operational concerns, including reliability, observability, evaluation, cost, model drift, hallucinations, and data leakage.

### Source excerpt

AI for Ops vs. Ops for AI

## From alert fatigue to AIOps: Building a proactive observability stack with Datadog on EKS

DevFeed: [From alert fatigue to AIOps: Building a proactive observability stack with Datadog on EKS](<https://devfeed.tech/articles/from-alert-fatigue-to-aiops-building-a-proactive-observability-stack-with-datadog-on-eks-57228.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/generative-ai/from-alert-fatigue-to-AIOps-building-proactive-observability-stack-with-Datadog-on-EKS>)

Author: Anirban Brahmochari, Swapnil Panchal, Ashwin Mattur, Zichuan Xiong

Published: 2025-08-21T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [datadog](<https://devfeed.tech/topics/datadog.md>), [observability](<https://devfeed.tech/topics/observability.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [Amazon Elastic Kubernetes Service](<https://devfeed.tech/topics/amazon-elastic-kubernetes-service.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>)

Tags: [aiops](<https://devfeed.tech/tags/aiops.md>), [alert-fatigue](<https://devfeed.tech/tags/alert-fatigue.md>), [aws](<https://devfeed.tech/tags/aws.md>), [datadog](<https://devfeed.tech/tags/datadog.md>), [eks](<https://devfeed.tech/tags/eks.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [logs](<https://devfeed.tech/tags/logs.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [observability](<https://devfeed.tech/tags/observability.md>), [proactive](<https://devfeed.tech/tags/proactive.md>)

### AI overview

This article describes using Datadog on AWS EKS to replace noisy, reactive monitoring with a proactive observability approach. It discusses alert fatigue, monitors-as-code, unified tagging, anomaly detection, chaos validation, and business-aware alerting, reporting reductions in alert noise and mean time to restore.

### Source excerpt

From alert fatigue to AIOps: Building a proactive observability stack with Datadog on EKS

## AI evals for MCP in AIOps

DevFeed: [AI evals for MCP in AIOps](<https://devfeed.tech/articles/ai-evals-for-mcp-in-aiops-57176.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/generative-ai/AI-evals-for-MCP-in-AIOps>)

Author: Zichuan Xiong, Larissa Dornelles, Scott Juang

Published: 2025-07-31T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [AIOps](<https://devfeed.tech/topics/aiops.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Context-aware AI](<https://devfeed.tech/topics/context-aware-ai.md>), [Risk](<https://devfeed.tech/topics/risk.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Security](<https://devfeed.tech/topics/security.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Availability](<https://devfeed.tech/topics/availability.md>)

Tags: [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [ai-evals](<https://devfeed.tech/tags/ai-evals.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [availability](<https://devfeed.tech/tags/availability.md>), [blog](<https://devfeed.tech/tags/blog.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [context-aware-ai](<https://devfeed.tech/tags/context-aware-ai.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [latency](<https://devfeed.tech/tags/latency.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

This article examines how AI evaluations can be embedded into MCP-driven AIOps workflows. It describes how context-aware agents retrieve live operational data and explains risks including hallucinations, compliance gaps, security vulnerabilities, latency, inconsistent results and cascading failures.

### Source excerpt

AI evals for MCP in AIOps

## How AI is reshaping IT operations: From firefighting to intelligent evolution

DevFeed: [How AI is reshaping IT operations: From firefighting to intelligent evolution](<https://devfeed.tech/articles/how-ai-is-reshaping-it-operations-from-firefighting-to-intelligent-evolution-56971.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/articles/how-ai-is-reshaping-it-operations>)

Author: Zichuan Xiong

Published: 2025-06-27T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [AIOps](<https://devfeed.tech/topics/aiops.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [aiops](<https://devfeed.tech/tags/aiops.md>), [alert-fatigue](<https://devfeed.tech/tags/alert-fatigue.md>), [cloud-native](<https://devfeed.tech/tags/cloud-native.md>), [it-operations](<https://devfeed.tech/tags/it-operations.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [observability](<https://devfeed.tech/tags/observability.md>)

### AI overview

The article explains how AI and AIOps can help IT teams move from reactive firefighting to proactive operations. It describes difficulties caused by complex environments, alert overload, delayed diagnosis and short-term fixes, then outlines AIOps capabilities including pattern extraction, early warnings, root-cause analysis, recommended or automated resolutions, and reusable operational knowledge.

### Source excerpt

How AI is reshaping IT operations: From firefighting to intelligent evolution

[Next page](<https://devfeed.tech/topics/aiops.md?cursor=WyIyMDI1LTA2LTI3VDAwOjAwOjAwKzAwOjAwIiwgImFlMjU1MzgxLWRkNWQtNGI5Ny04NjQzLTk4MmRlOTFkZWFlYyJd>)