# Network Operations

Network Operations is an approach to managing networks that emphasizes agility, automation, virtualization, orchestration, and rapid deployments.

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

## Janus: One Agent, Two Roles for Digital Twin Construction and Network Orchestration

DevFeed: [Janus: One Agent, Two Roles for Digital Twin Construction and Network Orchestration](<https://devfeed.tech/articles/janus-one-agent-two-roles-for-digital-twin-construction-and-network-orchestration-131574.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14920>)

Author: Peijun Hou, Yue Zhang, Yi Wei, Nan Cen

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [AI Networking](<https://devfeed.tech/topics/ai-networking.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [association](<https://devfeed.tech/tags/association.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [graph](<https://devfeed.tech/tags/graph.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [network](<https://devfeed.tech/tags/network.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [routing](<https://devfeed.tech/tags/routing.md>), [scalability](<https://devfeed.tech/tags/scalability.md>)

### AI overview

Janus combines digital-twin construction and wireless-network orchestration in a closed loop. Its NetTwin agent uses one agent for two roles: building a twin from partial observations and making task-driven network decisions. A planner, modeler and coder structure the work, while a unified prompt module is designed to improve graph reasoning. In evaluations on networks of up to 200 nodes, covering user association and SAGIN routing, Janus reportedly achieved over 90% digital-twin accuracy and performance gaps within 10.53% of optimal, with moderate computational overhead. The supplied text is an abstract and does not provide further evaluation details.

### Source excerpt

arXiv:2611.14920v1 Announce Type: new Abstract: Next-generation wireless networks are increasingly large-scale, heterogeneous, and dynamic, posing significant challenges to network modeling and control. Digital twins offer a promising solution, but existing approaches typically rely on static models and decouple twin construction from network orchestration, limiting adaptability. Meanwhile, large language models (LLMs) provide strong reasoning capabilities but struggle with graph-structured data and are highly sensitive to prompt design, making inference unreliable. In this paper, we propose Janus, an agentic LLM-based framework that unifies digital twin construction and network orchestration within a closed-loop system. At the core of Janus is a novel NetTwin agent, which introduces a new one-agent, two-role paradigm, enabling a single agent to simultaneously construct the digital twin from partial observations while performing task-driven network decision-making. To realize this, we design a modular architecture with three functional roles, including planner, modeler, and coder, along with a newly designed unified prompt module that further enhances graph reasoning robustness. Extensive evaluations on wireless networks with up to 200 nodes and two representative tasks, including user association and SAGIN routing, show that Janus achieves over 90% digital twin accuracy and near-optimal performance with gaps within 10.53%, while maintaining moderate computational overhead. These results demonstrate the effectiveness, scalability, and generalizability of Janus, paving the way for AI-native autonomous wireless network orchestration.

## Agentic AI demands a stronger, more assured network foundation

DevFeed: [Agentic AI demands a stronger, more assured network foundation](<https://devfeed.tech/articles/agentic-ai-demands-a-stronger-more-assured-network-foundation-124197.md>)

Original publisher: [Read original article](<https://blogs.cisco.com/networking/agentic-ai-demands-a-stronger-more-assured-network-foundation>)

Author: Grant Shirk

Published: 2026-11-09T20:00:14Z

Content type: article

Language: en

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

Topics: [AI Networking](<https://devfeed.tech/topics/ai-networking.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [ThousandEyes](<https://devfeed.tech/topics/thousandeyes.md>), [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [Wi-Fi](<https://devfeed.tech/topics/wi-fi.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [about](<https://devfeed.tech/tags/about.md>), [access-point](<https://devfeed.tech/tags/access-point.md>), [act](<https://devfeed.tech/tags/act.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [anchor](<https://devfeed.tech/tags/anchor.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [change](<https://devfeed.tech/tags/change.md>), [cisco-secure-networking](<https://devfeed.tech/tags/cisco-secure-networking.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [machine](<https://devfeed.tech/tags/machine.md>), [more](<https://devfeed.tech/tags/more.md>), [need](<https://devfeed.tech/tags/need.md>), [network](<https://devfeed.tech/tags/network.md>), [networking](<https://devfeed.tech/tags/networking.md>), [operations](<https://devfeed.tech/tags/operations.md>), [post-quantum-cryptography-pqc](<https://devfeed.tech/tags/post-quantum-cryptography-pqc.md>), [speed](<https://devfeed.tech/tags/speed.md>), [technology](<https://devfeed.tech/tags/technology.md>), [transparency](<https://devfeed.tech/tags/transparency.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

Cisco describes network capabilities intended to support trusted AgenticOps: ThousandEyes agents and synthetic tests are automatically provisioned on Wi-Fi 6E and Wi-Fi 7 access points, while Experience Metrics extends telemetry to application performance. Agentic Actions combines AI agents, reasoning, and workflows in Cloud Control, showing recommendations and results and letting operators control how actions run; it is in beta or controlled availability. New MCP servers aim to standardize access to cloud and on-premises network intelligence. Security updates include quantum-ready secure boot and communications, including over-the-air encryption on supported platforms, and Cisco's CW9176ISEC Wi-Fi 7 access point, aligned to CNSA 2.0. Cisco also expands Live Protect runtime vulnerability shields to supported wireless controllers, Campus Gateways, and Secure Routers, allowing protection while permanent fixes are tested and deployed without an immediate upgrade or reboot.

### Source excerpt

When technology change is advancing at machine speed, we need a stronger foundation in the network to establish transparency, anchor trust, and enable autonomous operations.

## PCAP-LM: Helping AI assistants read network traffic

DevFeed: [PCAP-LM: Helping AI assistants read network traffic](<https://devfeed.tech/articles/pcap-lm-helping-ai-assistants-read-network-traffic-121502.md>)

Original publisher: [Read original article](<https://blog.apnic.net/2026/11/06/pcap-lm-helping-ai-assistants-read-network-traffic/>)

Author: Xavier Marjou

Published: 2026-11-06T00:04:21Z

Content type: article

Language: en

Sources: [APNIC Blog](<https://devfeed.tech/sources/apnic-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [network-intelligence](<https://devfeed.tech/topics/network-intelligence.md>), [Internet Traffic](<https://devfeed.tech/topics/internet-traffic.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>)

Tags: [4g](<https://devfeed.tech/tags/4g.md>), [5g](<https://devfeed.tech/tags/5g.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-services](<https://devfeed.tech/tags/ai-services.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [guest-post](<https://devfeed.tech/tags/guest-post.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [network](<https://devfeed.tech/tags/network.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [network-traffic](<https://devfeed.tech/tags/network-traffic.md>), [operations](<https://devfeed.tech/tags/operations.md>), [packet](<https://devfeed.tech/tags/packet.md>), [pcap](<https://devfeed.tech/tags/pcap.md>), [scale](<https://devfeed.tech/tags/scale.md>), [tech-matters](<https://devfeed.tech/tags/tech-matters.md>), [traffic](<https://devfeed.tech/tags/traffic.md>)

### AI overview

PCAP-LM makes packet captures small enough for an AI model to read in full by translating each conversation into compact PacketGlyphs that preserve direction, type, size, and timing while dropping payloads and other detail. It folds repeated patterns and combines frequent symbols. In tests on 30 captures from a 5G/4G measurement campaign, the rewritten files averaged about 800 times smaller than detailed Wireshark command-line text, and a model answered ten forensic questions with 99.3% accuracy. Conventional text truncated to the same length yielded 51%, partly because it exposed only the first few dozen packets. The tests covered large encrypted downloads from one server; retransmissions were missed in about a quarter of affected captures. PCAP-LM omits payload contents, sequence numbers, and exact timings, and encrypted content remains opaque. A side-index can point analysts or AI tools to original frames for follow-up. The excerpt proposes local address and hostname substitution before sharing and suggests testing other protocols, which may require new symbols or vocabulary training.

### Source excerpt

Guest Post: Packet captures are the ground truth of network operations, but analysing them is slow, requires specialist expertise, and does not scale. PCAP-LM rewrites captures into a form that AI assistants can read, helping address that mismatch.

## From Reactive to Agentic Resilience: Multi-Timescale AI-RAN Orchestration Under Signaling Storms

DevFeed: [From Reactive to Agentic Resilience: Multi-Timescale AI-RAN Orchestration Under Signaling Storms](<https://devfeed.tech/articles/from-reactive-to-agentic-resilience-multi-timescale-ai-ran-orchestration-under-signaling-storms-113881.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03406>)

Author: Sotiris Chatzimiltis, Mahdi Boloursaz Mashhadi, Mohammad Shojafar, Rahim Tafazolli

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>)

Tags: [absorption](<https://devfeed.tech/tags/absorption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [calendar](<https://devfeed.tech/tags/calendar.md>), [compute](<https://devfeed.tech/tags/compute.md>), [control-loops](<https://devfeed.tech/tags/control-loops.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [event](<https://devfeed.tech/tags/event.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [hierarchy](<https://devfeed.tech/tags/hierarchy.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [resilience](<https://devfeed.tech/tags/resilience.md>)

### AI overview

The paper proposes a three-tier agentic AI framework for coordinating Open RAN resilience across control timescales during mass-attachment signaling storms. A service management and orchestration layer sets standing policy; a per-site non-real-time agent judges storms and anticipates scheduled crowds; and a deterministic near-real-time loop enforces decisions, keeping slow language-model reasoning off the fast control path. In simulator experiments, reading a scheduled event from a calendar and provisioning ahead of it brought the controller close to the resilience of a fully provisioned server pool using one quarter of its capacity. The authors report that reactive weight setting could not recover that performance once a surge arrived, and that operator intents became control directives with 94% exact match on previously unseen intents. The abstract says the work also quantifies latency, cost, and contention limits; it does not provide their values.

### Source excerpt

arXiv:2611.03406v1 Announce Type: new Abstract: Next-generation open radio access network (Open RAN) and AI-RAN deployments turn the RAN into a disaggregated, compute-aware platform whose service continuity depends on many control loops acting at different timescales. Resilience in this setting is best seen as a lifecycle spanning anticipation, absorption, adaptation, recovery, and evolution. Yet, existing mechanisms remain stage-specific and are rarely coordinated across the control hierarchy. This paper argues that agentic AI offers an orchestration layer that coordinates this lifecycle, turning operator intent into coordinated action while keeping slow language-model reasoning off the fast control path. Using mass-attachment signaling storms as a running study, we build a discrete-event Open RAN attach simulator that captures retry amplification, shared-compute contention, and non-instantaneous provisioning, and we propose a three-tier framework in which an orchestrator at the service management and orchestration layer sets a standing policy, a per-site non-real-time agent judges storms and anticipates scheduled crowds, and a deterministic near-real-time loop enforces every decision. Across experiments, the agentic controller approaches the resilience of a fully provisioned pool of servers at a quarter of its capacity by reading a scheduled event from a calendar and provisioning ahead of it. No reactive weight setting recovers this once the surge arrives. Free-text operator intents ground into control directives at 94% exact match on previously unseen intents, and a single instruction reshapes live behavior end to end. We also quantify the latency, cost, and contention limits that bound it. The supplementary material provides analytical proof of the derived Theorem on anticipation horizon, as well as the subsequent Corollary results on reactive provisioning limits.

## Extreme Networks wants the network to run AI, not just be run by it

DevFeed: [Extreme Networks wants the network to run AI, not just be run by it](<https://devfeed.tech/articles/extreme-networks-wants-the-network-to-run-ai-not-just-be-run-by-it-109238.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/30/extreme-networks-wants-the-network-to-run-ai-not-just-be-run-by-it/>)

Author: Zeus Kerravala

Published: 2026-10-30T19:53:09Z

Content type: article

Language: en

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

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [access-points](<https://devfeed.tech/tags/access-points.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [compute](<https://devfeed.tech/tags/compute.md>), [exchange](<https://devfeed.tech/tags/exchange.md>), [extreme-networks](<https://devfeed.tech/tags/extreme-networks.md>), [first](<https://devfeed.tech/tags/first.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [heres](<https://devfeed.tech/tags/heres.md>), [inc](<https://devfeed.tech/tags/inc.md>), [information](<https://devfeed.tech/tags/information.md>), [information-technology](<https://devfeed.tech/tags/information-technology.md>), [infra](<https://devfeed.tech/tags/infra.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [it](<https://devfeed.tech/tags/it.md>), [just](<https://devfeed.tech/tags/just.md>), [network](<https://devfeed.tech/tags/network.md>), [networking](<https://devfeed.tech/tags/networking.md>), [networks](<https://devfeed.tech/tags/networks.md>), [news](<https://devfeed.tech/tags/news.md>), [run](<https://devfeed.tech/tags/run.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [wants](<https://devfeed.tech/tags/wants.md>)

### AI overview

Extreme Networks is positioning the network as both an AI-managed system and local infrastructure for AI workloads. The article reports early Agent ONE Coworker results, including about 1,000 troubleshooting hours saved in its first month, while noting that only 58% of cases it opens include all evidence support needs. Planned for the first half of 2027, Exchange zones would combine a Universal Compute Platform or customer server with spare compute in installed access points and switches; applications would run locally on open-weight models by default, with cloud inference only when policy permits and with each use logged. The article describes potential uses of network telemetry beyond operations, but says the zones and demo apps remain unproven. It advises IT teams to involve network staff in AI planning, keep governance separate from agent execution, inventory discarded telemetry, assess edge capacity under changing network demand, and establish task costs before evaluating consumption-based pricing.

### Source excerpt

At its recent AI Summit in Amsterdam, Extreme Networks Inc. shared early Agent ONE Coworker results and previewed Exchange zones, which put spare access points and switch compute to work as on-premises artificial intelligence infrastructure. Here's what it means and what information technology pros should do about it. Most of the conversation about AI and [...] The post Extreme Networks wants the network to run AI, not just be run by it appeared first on SiliconANGLE.

## NetClaw returns to Packet Pushers

DevFeed: [NetClaw returns to Packet Pushers](<https://devfeed.tech/articles/netclaw-returns-to-packet-pushers-110106.md>)

Original publisher: [Read original article](<https://www.linkedin.com/posts/john-capobianco-644a1515_netclaw-networkautomation-agenticai-activity-7521962635014283265-GaUw>)

Author: John Capobianco

Published: 2026-10-30T12:00:00Z

Content type: article

Language: en

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

Topics: [AI Networking](<https://devfeed.tech/topics/ai-networking.md>), [Automation](<https://devfeed.tech/topics/automation.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Fair Source](<https://devfeed.tech/topics/fair-source.md>), [Sports](<https://devfeed.tech/topics/sports.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>)

Tags: [2019](<https://devfeed.tech/tags/2019.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [air](<https://devfeed.tech/tags/air.md>), [air-gapped](<https://devfeed.tech/tags/air-gapped.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automation](<https://devfeed.tech/tags/automation.md>), [banks](<https://devfeed.tech/tags/banks.md>), [community](<https://devfeed.tech/tags/community.md>), [contributors](<https://devfeed.tech/tags/contributors.md>), [john](<https://devfeed.tech/tags/john.md>), [john-capobianco](<https://devfeed.tech/tags/john-capobianco.md>), [netclaw](<https://devfeed.tech/tags/netclaw.md>), [network](<https://devfeed.tech/tags/network.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>), [networking](<https://devfeed.tech/tags/networking.md>), [packet](<https://devfeed.tech/tags/packet.md>), [social](<https://devfeed.tech/tags/social.md>)

### AI overview

The author says NetClaw makes network automation easier to try: instead of months of book study and lab work, users can add eight lines of JSON to an agent. The project has three co-maintainers, 16+ contributors, more than 200 documented specs, and integrations being built and tested by named network vendors. Its safety approach includes a "soul file" of operational rules and explicit approval for production actions beyond reads; the author also cites Cisco DefenseClaw and NVIDIA OpenShell as additional protection. NetClaw supports frontier or air-gapped open-weight models, including on Raspberry Pi, and offers a VS Code extension plus mobile and watch access. The author recommends starting read-only in a lab. These are claims from the supplied excerpt.

### Source excerpt

John Capobianco - LinkedIn - John reflects on NetClaw's community, its contributors, and making useful network automation easier to try alongside the new Heavy Networking episode.

## VibeOps Lounge 007 - Learning Network Automation & AI in Public with Elliot Conner

DevFeed: [VibeOps Lounge 007 - Learning Network Automation & AI in Public with Elliot Conner](<https://devfeed.tech/articles/vibeops-lounge-007-learning-network-automation-ai-in-public-with-elliot-conner-110113.md>)

Original publisher: [Read original article](<https://www.youtube.com/watch?v=WnXN88AJD8k>)

Published: 2026-10-29T12:00:00Z

Content type: article

Language: en

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

Topics: [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [camera-phone](<https://devfeed.tech/tags/camera-phone.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [demo](<https://devfeed.tech/tags/demo.md>), [discuss](<https://devfeed.tech/tags/discuss.md>), [free](<https://devfeed.tech/tags/free.md>), [game](<https://devfeed.tech/tags/game.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [john-capobianco](<https://devfeed.tech/tags/john-capobianco.md>), [learning](<https://devfeed.tech/tags/learning.md>), [network](<https://devfeed.tech/tags/network.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>), [network-troubleshooting](<https://devfeed.tech/tags/network-troubleshooting.md>), [operations](<https://devfeed.tech/tags/operations.md>), [planner](<https://devfeed.tech/tags/planner.md>), [public](<https://devfeed.tech/tags/public.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [troubleshooting](<https://devfeed.tech/tags/troubleshooting.md>), [upload](<https://devfeed.tech/tags/upload.md>), [video](<https://devfeed.tech/tags/video.md>), [video-phone](<https://devfeed.tech/tags/video-phone.md>)

### AI overview

Elliot Conner joins John Capobianco to discuss learning in public and demonstrate three network automation projects: a Containerlab operations dashboard, Net Planner, and an interactive network troubleshooting game.

### Source excerpt

John Capobianco - Lounge episode - Elliot Conner joins John to discuss learning in public and demo a Containerlab operations dashboard, Net Planner, and an interactive network troubleshooting game.

## CCAaaS: An Orchestration Platform for High-Velocity Design, Development, and Deployment of Data Center Transports at Meta

DevFeed: [CCAaaS: An Orchestration Platform for High-Velocity Design, Development, and Deployment of Data Center Transports at Meta](<https://devfeed.tech/articles/ccaaas-an-orchestration-platform-for-high-velocity-design-development-and-deployment-of-data-center-transports-at-meta-101661.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33231>)

Author: Prankur Gupta, Balasubramanian Madhavan, Miao Xu, Prashanth Kannan, Jie Meng, Neil Spring, Rajiv Krishnamurthy, Srikanth Sundaresan, Martin Lau, Theophilus A. Benson

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Deployment & Scaling](<https://devfeed.tech/topics/deployment-scaling.md>), [zero downtime deployment](<https://devfeed.tech/topics/zero-downtime-deployment.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.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>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [congestion-control](<https://devfeed.tech/tags/congestion-control.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-center-networks](<https://devfeed.tech/tags/data-center-networks.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [design](<https://devfeed.tech/tags/design.md>), [development](<https://devfeed.tech/tags/development.md>), [ebpf](<https://devfeed.tech/tags/ebpf.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [framework](<https://devfeed.tech/tags/framework.md>), [hyperscale](<https://devfeed.tech/tags/hyperscale.md>), [meta](<https://devfeed.tech/tags/meta.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [platform](<https://devfeed.tech/tags/platform.md>)

### AI overview

CCAaaS is Meta's eBPF-based system for building, deploying, and operating multiple congestion control algorithms (CCAs) for different data center traffic patterns. It combines a modular BPF-TCP framework, an orchestration layer for disruption-free CCA updates, and lightweight CCA observability. The abstract reports that three active eBPF-based CCAs manage over 97% of server-to-server traffic; two of five built have been deprecated. The eBPF approach matched native in-kernel counterparts on retransmissions, bandwidth, and tail latency, while custom CCAs added negligible CPU and memory cost over eBPF baselines. One CCA reduced P99 latency for cross-region services by up to 20x. These findings are reported in the abstract; the supplied text does not provide implementation details or evaluation methodology.

### Source excerpt

arXiv:2610.33231v1 Announce Type: new Abstract: Today, data center networks run multiple congestion control algorithms (CCAs), each tailored to distinct traffic characteristics, from latency-sensitive intra-region RPCs to high-throughput cross-region AI workloads. The rapid evolution of AI training and inference further accelerates this trend by continually introducing new traffic characteristics that demand new CCAs. This paper introduces CCA-as-a-Service (CCAaaS), our eBPF-based ecosystem for the rapid design, deployment, and operation of production-grade CCAs at hyperscale. We present (1) a modular BPF-TCP framework and general lessons for designing modular CCAs; (2) a deployment and orchestration layer that provides disruption-free CCA updates, along with best practices for managing a zoo of CCAs at scale; and (3) a lightweight observability tool for CCAs and a blueprint for scaling CCA observability. CCAaaS manages over 97% of our server-to-server traffic using three active eBPF-based CCAs; two of the five CCAs we have built have since been deprecated. We show that our eBPF-centric approach to CCAs development delivers the same application-level performance (retransmissions, bandwidth, and tail latency) as their native in-kernel counterparts, and that our custom CCAs add negligible CPU and memory cost over their eBPF baselines. In terms of realized benefits, the CCA built with CCAaaS significantly improved network, and application metrics, for example, one of our CCAs reduced P99 latency for cross-region services by up to 20X.

## APNIC 62 workshops help build network security, automation, and routing expertise across the region

DevFeed: [APNIC 62 workshops help build network security, automation, and routing expertise across the region](<https://devfeed.tech/articles/apnic-62-workshops-help-build-network-security-automation-and-routing-expertise-across-the-region-101319.md>)

Original publisher: [Read original article](<https://blog.apnic.net/2026/10/27/apnic-62-workshops-help-build-network-security-automation-and-routing-expertise-across-the-region/>)

Author: Sheryl Hermoso

Published: 2026-10-27T01:27:49Z

Content type: news

Language: en

Sources: [APNIC Blog](<https://devfeed.tech/sources/apnic-blog.md>)

Topics: [network security](<https://devfeed.tech/topics/network-security.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Automation](<https://devfeed.tech/topics/automation.md>), [IP routing](<https://devfeed.tech/topics/ip-routing.md>), [saltstack](<https://devfeed.tech/topics/saltstack.md>), [Routing Security](<https://devfeed.tech/topics/routing-security.md>), [Network Configuration](<https://devfeed.tech/topics/network-configuration.md>), [BGP](<https://devfeed.tech/topics/bgp.md>)

Tags: [apnic-62](<https://devfeed.tech/tags/apnic-62.md>), [apnic-academy](<https://devfeed.tech/tags/apnic-academy.md>), [apnic-training](<https://devfeed.tech/tags/apnic-training.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bgp](<https://devfeed.tech/tags/bgp.md>), [cryptography](<https://devfeed.tech/tags/cryptography.md>), [ddos](<https://devfeed.tech/tags/ddos.md>), [development](<https://devfeed.tech/tags/development.md>), [distributed-denial-of-service](<https://devfeed.tech/tags/distributed-denial-of-service.md>), [dns](<https://devfeed.tech/tags/dns.md>), [dns-security](<https://devfeed.tech/tags/dns-security.md>), [ethernet](<https://devfeed.tech/tags/ethernet.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [events](<https://devfeed.tech/tags/events.md>), [evpn](<https://devfeed.tech/tags/evpn.md>), [flex](<https://devfeed.tech/tags/flex.md>), [network](<https://devfeed.tech/tags/network.md>), [network-operators](<https://devfeed.tech/tags/network-operators.md>), [network-security](<https://devfeed.tech/tags/network-security.md>), [region](<https://devfeed.tech/tags/region.md>), [routing](<https://devfeed.tech/tags/routing.md>), [security](<https://devfeed.tech/tags/security.md>), [skills](<https://devfeed.tech/tags/skills.md>), [workshops](<https://devfeed.tech/tags/workshops.md>)

### AI overview

APNIC 62's workshops gave network engineers practical training in security, automation, and advanced service provider routing. The APNIC Academy security and automation workshops drew 55 participants; a separately organized INNOG routing workshop drew 27. Security exercises covered topics including DDoS mitigation, BGP and DNS security, RPKI, and open-source tools. The automation workshop covered configuration management, SALT, YAML and Jinja, and event-driven workflows, using a train-the-trainer format so participants could share skills with their teams and communities. INNOG's three-day routing workshop was designed for experienced provider engineers and used hands-on labs for Segment Routing, EVPN, Flex-Algo, Containerlab, and telemetry-driven monitoring. Participant feedback described plans to apply the training to security practices, incident response automation, and safer network operations.

### Source excerpt

More than 80 network engineers and operators strengthened their skills at APNIC 62 through hands-on workshops in network security, automation, and next-generation service provider routing.

## AI networks drive SONiC boom

DevFeed: [AI networks drive SONiC boom](<https://devfeed.tech/articles/ai-networks-drive-sonic-boom-92935.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4238494/ai-networks-drive-sonic-boom.html>)

Author: Neal Weinberg

Published: 2026-10-21T14:59:20Z

Content type: article

Language: en

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

Topics: [Network](<https://devfeed.tech/topics/network.md>), [systems](<https://devfeed.tech/topics/systems.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [vendor lock-in](<https://devfeed.tech/topics/vendor-lock-in.md>), [linux foundation](<https://devfeed.tech/topics/linux-foundation.md>), [NVIDIA Spectrum-X Ethernet](<https://devfeed.tech/topics/nvidia-spectrum-x-ethernet.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data-center](<https://devfeed.tech/tags/ai-data-center.md>), [ai-networks](<https://devfeed.tech/tags/ai-networks.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arista](<https://devfeed.tech/tags/arista.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>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cost-control](<https://devfeed.tech/tags/cost-control.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [dell](<https://devfeed.tech/tags/dell.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [disaggregation](<https://devfeed.tech/tags/disaggregation.md>), [driving](<https://devfeed.tech/tags/driving.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [network-management-software](<https://devfeed.tech/tags/network-management-software.md>), [networking](<https://devfeed.tech/tags/networking.md>), [networks](<https://devfeed.tech/tags/networks.md>), [sonic](<https://devfeed.tech/tags/sonic.md>), [storytype-feature](<https://devfeed.tech/tags/storytype-feature.md>)

### AI overview

SONiC is gaining enterprise traction as AI networking needs meet broader vendor and support options. The excerpt reports forecasts of more than $5 billion in SONiC-based data center switching revenue in 2026 and over $10 billion in AI scale-out network switch revenue by 2030; Gartner estimates 2,500 organizations run it in production, about one-third enterprises. Arista, Cisco, Dell, and Nvidia support SONiC on their hardware, while vendor and startup distributions add commercial support, validated compatibility, telemetry, and management features that can address the expertise burden of operating a do-it-yourself white-box deployment. AI-focused work includes SRv6 load balancing, packet trimming for congestion recovery, and higher-frequency telemetry. Community efforts also target edge LANs and campus networks: PENS is adapting SONiC for PoE and 802.1x, while TIP's OLS aims to let enterprises source hardware and software support separately. The excerpt identifies specialized operating skills as a continuing enterprise challenge.

### Source excerpt

Multiple factors are coming together to propel enterprise deployments of SONiC, the open-source network operating system (NOS) created 10 years ago by Microsoft to run on white box switches in hyperscale data centers. Alan Weckel, founder and analyst at 650 Group, is forecasting that data center switching revenue based on SONiC (Software for Open Networking in the Cloud) will exceed $5 billion in 2026 and that enterprise SONiC adoption will grow more than 25% year-over-year through 2027. Dell'Oro Group predicts that SONiC-based switch sales in AI scale-out networks will grow at more than 50% a year through 2030, when revenues will exceed $10 billion. And Gartner estimates that 2,500 organizations are running SONiC in production, and roughly one-third of those are enterprises. "SONiC is slowly and incrementally evolving from a niche white-box solution to a viable option on high-performance switches," Gartner stated earlier this year in its data center switching guide. "The disaggregation of hardware and software is no longer limited to cloud deployments; It is becoming a viable option for enterprises seeking flexibility, cost control, and reduced vendor lock-in, particularly within modern leaf-spine architectures and scale-out AI networks." There are four key factors driving the growth of SONiC, which Microsoft officially transferred to the Linux Foundation in 2022. 1. Major switch vendors are on board Traditional enterprise switch vendors, including Arista, Cisco, Dell, and Nvidia, are offering support for SONiC on their hardware. For example, Cisco announced in May that it is extending SONiC support to its N9000 Series data center switches. (Read more: SONiC momentum continues at OCP Global Summit) Supporting an open-source NOS may sound like a counterintuitive strategy for switch vendors that sell their own proprietary software. But the opportunity to sell high-performance switches into the booming AI data center market is too lucrative to pass up. And giving ente

## J2 Networks Joins MANRS to Strengthen Internet Routing Security

DevFeed: [J2 Networks Joins MANRS to Strengthen Internet Routing Security](<https://devfeed.tech/articles/j2-networks-joins-manrs-to-strengthen-internet-routing-security-90373.md>)

Original publisher: [Read original article](<https://blog.j2sw.com/technology/j2-networks-joins-manrs/>)

Author: j2sw

Published: 2026-10-19T17:35:44Z

Content type: news

Language: en

Sources: [Justin Wilson (j2sw)](<https://devfeed.tech/sources/justin-wilson-j2sw.md>)

Topics: [Routing Security](<https://devfeed.tech/topics/routing-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Internet](<https://devfeed.tech/topics/internet.md>)

Tags: [internet](<https://devfeed.tech/tags/internet.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [networks](<https://devfeed.tech/tags/networks.md>), [routing-security](<https://devfeed.tech/tags/routing-security.md>), [security](<https://devfeed.tech/tags/security.md>), [technology-industry-commentary](<https://devfeed.tech/tags/technology-industry-commentary.md>)

### AI overview

J2 Networks announces that it has joined MANRS, a global initiative promoting practical routing security measures and cooperation among network operators. The article describes filtering routing announcements, preventing IP address spoofing, coordinating operator responses, and publishing routing information for validation.

### Source excerpt

J2 Networks joins MANRS, the Mutually Agreed Norms for Routing Security initiative, reinforcing our commitment to a more secure Internet. MANRS is a global initiative that helps reduce common Internet routing threats through practical actions and cooperation among network operators. Joining this community reinforces our commitment to responsible network operations and a more resilient Internet. ... Read more The post J2 Networks Joins MANRS to Strengthen Internet Routing Security appeared first on Justin Wilson (j2sw).

## The Prisoner's Dilemma of Network Automation and AI Adoption

DevFeed: [The Prisoner's Dilemma of Network Automation and AI Adoption](<https://devfeed.tech/articles/the-prisoner-s-dilemma-of-network-automation-and-ai-adoption-110109.md>)

Original publisher: [Read original article](<https://www.linkedin.com/pulse/prisoners-dilemma-network-automation-ai-adoption-john-capobianco-csmwe>)

Author: John Capobianco

Published: 2026-10-15T12:00:00Z

Content type: opinion

Language: en

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

Topics: [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Automation](<https://devfeed.tech/topics/automation.md>), [AI Networking](<https://devfeed.tech/topics/ai-networking.md>), [Ansible](<https://devfeed.tech/topics/ansible.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-operations](<https://devfeed.tech/tags/agentic-operations.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [article](<https://devfeed.tech/tags/article.md>), [automation](<https://devfeed.tech/tags/automation.md>), [dilemma](<https://devfeed.tech/tags/dilemma.md>), [incentives](<https://devfeed.tech/tags/incentives.md>), [john](<https://devfeed.tech/tags/john.md>), [network](<https://devfeed.tech/tags/network.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>)

### AI overview

The article argues that AI and automation may shift from a competitive advantage to an industry baseline, while network engineers can amplify rather than discard their networking expertise. It distinguishes this from the classic Prisoner's Dilemma: broad adoption could benefit the profession even if early adopters gain an initial edge. Its roadmap starts with automating a familiar networking task, then validating network state with Cisco pyATS, connecting an AI assistant to evidence through pyATS MCP, experimenting with NetClaw in a lab while inspecting tool calls and keeping humans in control of changes, and sharing learning through VibeOps. It emphasizes read-only use at first, protected credentials, verification of AI answers, and evidence-based health checks.

### Source excerpt

LinkedIn - Article - John uses the prisoner's dilemma as a lens for discussing individual incentives, shared learning, and AI adoption among network engineers.

## Advancing NetOps-as-Code: Strategic momentum, enhanced security, and multimode automation

DevFeed: [Advancing NetOps-as-Code: Strategic momentum, enhanced security, and multimode automation](<https://devfeed.tech/articles/advancing-netops-as-code-strategic-momentum-enhanced-security-and-multimode-automation-86666.md>)

Original publisher: [Read original article](<https://www.redhat.com/en/blog/advancing-netops-code-strategic-momentum-enhanced-security-and-multimode-automation>)

Author: Elle Universal

Published: 2026-10-14T00:00:00Z

Content type: article

Language: en

Sources: [Red Hat Blog](<https://devfeed.tech/sources/red-hat-blog.md>)

Topics: [Ansible](<https://devfeed.tech/topics/ansible.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [NetBox](<https://devfeed.tech/topics/netbox.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [automation-hub](<https://devfeed.tech/tags/automation-hub.md>), [bgp](<https://devfeed.tech/tags/bgp.md>), [cloud-environments](<https://devfeed.tech/tags/cloud-environments.md>), [hybrid-cloud](<https://devfeed.tech/tags/hybrid-cloud.md>), [netops](<https://devfeed.tech/tags/netops.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The article reviews Red Hat Ansible Automation Platform and partner ecosystem updates for the third quarter of 2026. It describes security, reliability, and management improvements across Ansible network collections, including safer CI jobs, networking module fixes, NETCONF support for large configurations, and automated testing. It also highlights Arista AVD and NetBox integrations for network infrastructure automation.

### Source excerpt

The 3rd quarter of 2026 has shown that network automation isn't just a "nice to have," but rather a critical support for AI-driven workloads, edge computing, and hybrid cloud environments. Organizations are moving away from manual Day 2 operations and ad hoc solutions to a comprehensive, integrated automation platform. For network operations (NetOps) teams, this means transitioning from managing individual devices to orchestrating entire service delivery frameworks.Ansible Automation Platform updates Red Hat recently made the new automation orchestrator generally available as an add-on for R

## Why Determinism Is the Key to Safely Running AI Agents in Network Operations

DevFeed: [Why Determinism Is the Key to Safely Running AI Agents in Network Operations](<https://devfeed.tech/articles/why-determinism-is-the-key-to-safely-running-ai-agents-in-network-operations-110099.md>)

Original publisher: [Read original article](<https://www.itential.com/resource/blog/determinism-agentic-ai-network-operations/>)

Author: John Capobianco

Published: 2026-10-13T12:00:00Z

Content type: opinion

Language: en

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

Topics: [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [AI in IT operations](<https://devfeed.tech/topics/ai-in-it-operations.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [about](<https://devfeed.tech/tags/about.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [article](<https://devfeed.tech/tags/article.md>), [changes](<https://devfeed.tech/tags/changes.md>), [execution](<https://devfeed.tech/tags/execution.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [itential](<https://devfeed.tech/tags/itential.md>), [network](<https://devfeed.tech/tags/network.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [operations](<https://devfeed.tech/tags/operations.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [running](<https://devfeed.tech/tags/running.md>)

### AI overview

LLMs can propose different network changes for the same goal, and temperature zero does not guarantee repeatable output or protect against provider model updates. The article recommends separating probabilistic reasoning about what to do from deterministic execution of how to do it: agents should invoke defined capabilities rather than issue device commands directly, with validated inputs and outputs, pre- and post-checks, rollback, and audit trails. It argues that human approval for every action becomes a bottleneck and may create an illusion of scrutiny at scale. In Itential's described FlowAI harness, FlowAgents use live infrastructure state to select tools and observe results, while every action passes through the platform's execution engine and its RBAC, approval gates, and audit trail; model reasoning may shift, but tool execution remains as built and tested.

### Source excerpt

Itential - Article - Why infrastructure operations need repeatable execution around probabilistic reasoning, and where governed workflows fit into agent-driven changes.

## Modern retail networks are secure, simple, and ready for what's next

DevFeed: [Modern retail networks are secure, simple, and ready for what's next](<https://devfeed.tech/articles/modern-retail-networks-are-secure-simple-and-ready-for-what-s-next-85385.md>)

Original publisher: [Read original article](<https://blogs.cisco.com/networking/modern-retail-networks-are-secure-simple-and-ready-for-whats-next>)

Author: Miriam Kung

Published: 2026-10-12T15:00:54Z

Content type: article

Language: en

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

Topics: [Network Segmentation](<https://devfeed.tech/topics/network-segmentation.md>), [digital experience monitoring](<https://devfeed.tech/topics/digital-experience-monitoring.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Cloudflare One](<https://devfeed.tech/topics/cloudflare-one.md>)

Tags: [agenticops](<https://devfeed.tech/tags/agenticops.md>), [cisco-meraki](<https://devfeed.tech/tags/cisco-meraki.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [networking](<https://devfeed.tech/tags/networking.md>), [networks](<https://devfeed.tech/tags/networks.md>), [retail](<https://devfeed.tech/tags/retail.md>), [scale](<https://devfeed.tech/tags/scale.md>), [secure-networking](<https://devfeed.tech/tags/secure-networking.md>), [wi-fi-7](<https://devfeed.tech/tags/wi-fi-7.md>)

### AI overview

Modern retailers need networks that can handle seasonal traffic, distributed locations, and growing numbers of connected devices while keeping operations manageable for lean IT teams. The article describes Cisco networking, security, and AI-assisted operations, with retailer examples including centralized management, device protection, and support for new in-store services.

### Source excerpt

Modern retail networks must stay secure; simplify operations; and scale for seasonal traffic, distributed stores, and new in-store technology.

## How to Run Python Network Automation Scripts Securely Without Exposing Secrets

DevFeed: [How to Run Python Network Automation Scripts Securely Without Exposing Secrets](<https://devfeed.tech/articles/how-to-run-python-network-automation-scripts-securely-without-exposing-secrets-77049.md>)

Original publisher: [Read original article](<https://www.rogerperkin.co.uk/itential/how-to-run-python-network-automation-scripts-securely-without-exposing-secrets/>)

Author: Roger Perkin

Published: 2026-10-08T10:00:59Z

Content type: article

Language: en

Sources: [Roger Perkin Network Automation Consultant](<https://devfeed.tech/sources/roger-perkin-network-automation-consultant.md>)

Topics: [Automation](<https://devfeed.tech/topics/automation.md>), [Secrets Management](<https://devfeed.tech/topics/secrets-management.md>), [Python](<https://devfeed.tech/topics/python.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>)

Tags: [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [credential-management](<https://devfeed.tech/tags/credential-management.md>), [itential](<https://devfeed.tech/tags/itential.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>)

### AI overview

The article explains why locally maintained Python network automation scripts can struggle to reach production, highlighting undocumented dependencies, duplicated code, and exposed credentials. It recommends encrypted secret storage and runtime injection, then describes Itential Gateway as a governed execution layer that runs existing automation from Git using isolated, ephemeral environments.

### Source excerpt

Why Most Network Automation Scripts Never Reach Production Network engineers are constantly building Python scripts to solve real operational challenges. Whether it's collecting BGP routes, validating device configurations, checking interface status, or generating reports, many automation initiatives start as quick solutions to immediate problems. These scripts often deliver significant value to the engineer who created ...

## MCP at the Center of Agentic Network Operations -- Toronto slides

DevFeed: [MCP at the Center of Agentic Network Operations -- Toronto slides](<https://devfeed.tech/articles/mcp-at-the-center-of-agentic-network-operations-toronto-slides-65927.md>)

Original publisher: [Read original article](<https://automateyournetwork.com/presentations/mcp-dev-summit-toronto-netclaw-2026.pdf>)

Published: 2026-10-06T12:00:00Z

Content type: article

Language: en

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

Topics: [Agentic SOC](<https://devfeed.tech/topics/agentic-soc.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [dev](<https://devfeed.tech/tags/dev.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [netclaw](<https://devfeed.tech/tags/netclaw.md>), [network](<https://devfeed.tech/tags/network.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [operations](<https://devfeed.tech/tags/operations.md>), [resource](<https://devfeed.tech/tags/resource.md>), [summit](<https://devfeed.tech/tags/summit.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

The document is a 47-slide NetClaw presentation from MCP Dev Summit Toronto. It identifies its subject as agentic network operations; the session video is described as coming soon.

### Source excerpt

The complete 47-slide NetClaw presentation from MCP Dev Summit Toronto. Session video coming soon.

## DevNet Latin & Hispanic Heritage Month recap

DevFeed: [DevNet Latin & Hispanic Heritage Month recap](<https://devfeed.tech/articles/devnet-latin-hispanic-heritage-month-recap-62633.md>)

Original publisher: [Read original article](<https://blogs.cisco.com/developer/devnet-latin-hispanic-heritage-month-recap>)

Author: Poncho Sandoval

Published: 2026-09-30T14:00:22Z

Content type: article

Language: en

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

Topics: [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [developer-relations](<https://devfeed.tech/topics/developer-relations.md>), [cisco networking](<https://devfeed.tech/topics/cisco-networking.md>), [Cisco Catalyst Center](<https://devfeed.tech/topics/cisco-catalyst-center.md>), [lf education](<https://devfeed.tech/topics/lf-education.md>), [QCon Software Development Conference](<https://devfeed.tech/topics/qcon-software-development-conference.md>)

Tags: [cisco](<https://devfeed.tech/tags/cisco.md>), [cisco-catalyst-center](<https://devfeed.tech/tags/cisco-catalyst-center.md>), [cisco-devnet](<https://devfeed.tech/tags/cisco-devnet.md>), [developer](<https://devfeed.tech/tags/developer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [hispanic-heritage-month](<https://devfeed.tech/tags/hispanic-heritage-month.md>), [ise](<https://devfeed.tech/tags/ise.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [recap](<https://devfeed.tech/tags/recap.md>), [servicenow](<https://devfeed.tech/tags/servicenow.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Cisco DevNet recaps a Spanish-language video series featuring engineers from Latin America and beyond. The episodes discuss a software engineer's career in network automation, a solution integrating Cisco Catalyst Center, Cisco ISE, and ServiceNow to automate network operations, and a software architect's career path and advice. The article also highlights how language access affects participation in technology education.

### Source excerpt

Celebrate Latin and Hispanic Heritage Month with Cisco DevNet! Explore our Spanish-language video series featuring four engineers shaping the future of network automation, and learn why multilingual tech education matters.

## A practical AI journey with John Capobianco

DevFeed: [A practical AI journey with John Capobianco](<https://devfeed.tech/articles/a-practical-ai-journey-with-john-capobianco-66230.md>)

Original publisher: [Read original article](<https://www.youtube.com/watch?v=PRMyg2C1RTA>)

Published: 2026-09-29T12:00:00Z

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [camera-phone](<https://devfeed.tech/tags/camera-phone.md>), [free](<https://devfeed.tech/tags/free.md>), [interview](<https://devfeed.tech/tags/interview.md>), [john-capobianco](<https://devfeed.tech/tags/john-capobianco.md>), [network](<https://devfeed.tech/tags/network.md>), [network-automation](<https://devfeed.tech/tags/network-automation.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [upload](<https://devfeed.tech/tags/upload.md>), [video](<https://devfeed.tech/tags/video.md>), [video-phone](<https://devfeed.tech/tags/video-phone.md>)

### AI overview

John Capobianco discusses his path into AI, practical applications in networking, and his vision for future AI interfaces and management.

### Source excerpt

Modern Business Life - Interview - AI & network automation

## AI best practices for AWS network operations with AI agents and MCP

DevFeed: [AI best practices for AWS network operations with AI agents and MCP](<https://devfeed.tech/articles/ai-best-practices-for-aws-network-operations-with-ai-agents-and-mcp-60222.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/networking-and-content-delivery/ai-best-practices-for-aws-network-operations-with-ai-agents-and-mcp/>)

Author: Vijay Menon

Published: 2026-09-25T18:49:16Z

Content type: article

Language: en

Sources: [Networking & Content Delivery](<https://devfeed.tech/sources/networking-content-delivery.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Amazon VPC](<https://devfeed.tech/topics/amazon-vpc.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [Kiro](<https://devfeed.tech/topics/kiro.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [aws](<https://devfeed.tech/tags/aws.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [devops](<https://devfeed.tech/tags/devops.md>), [iam](<https://devfeed.tech/tags/iam.md>), [kiro](<https://devfeed.tech/tags/kiro.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [networking-content-delivery](<https://devfeed.tech/tags/networking-content-delivery.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>)

### AI overview

This AWS post presents best practices for using AI agents and MCP in network operations. It describes correlating telemetry across AWS services, supporting agentic diagnostics, and building an AI NetOps stack with scoped IAM boundaries and human approval gates.

### Source excerpt

This post is for platform and SRE teams running 24/7 network operations who want AI Agents and Model Context Protocol (MCP) for intelligent, automated event response, and for individual engineers who want agentic diagnostics during development and triage. If you are in the first group, focus on AWS DevOps Agent, Amazon Bedrock AgentCore, and the [...]

## NetOps is already deploying agentic autonomy - trust will decide how far it goes

DevFeed: [NetOps is already deploying agentic autonomy - trust will decide how far it goes](<https://devfeed.tech/articles/netops-is-already-deploying-agentic-autonomy-trust-will-decide-how-far-it-goes-58740.md>)

Original publisher: [Read original article](<https://blogs.cisco.com/news/netops-is-already-deploying-autonomy-trust-will-decide-how-far-it-goes>)

Author: Joe Vaccaro

Published: 2026-09-23T13:00:52Z

Content type: opinion

Language: en

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

Topics: [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Network](<https://devfeed.tech/topics/network.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [incident](<https://devfeed.tech/topics/incident.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [context](<https://devfeed.tech/tags/context.md>), [data](<https://devfeed.tech/tags/data.md>), [executive-platform](<https://devfeed.tech/tags/executive-platform.md>), [incident](<https://devfeed.tech/tags/incident.md>), [it](<https://devfeed.tech/tags/it.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [netops](<https://devfeed.tech/tags/netops.md>), [network](<https://devfeed.tech/tags/network.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [networks](<https://devfeed.tech/tags/networks.md>), [operational](<https://devfeed.tech/tags/operational.md>), [operations](<https://devfeed.tech/tags/operations.md>), [production](<https://devfeed.tech/tags/production.md>), [reactive](<https://devfeed.tech/tags/reactive.md>)

### AI overview

The article argues that AI agents are already taking on production responsibilities in network operations. It focuses on the operational pressure caused by alert volume and complexity, and argues that trust and appropriate controls will determine how broadly agentic AI is deployed.

### Source excerpt

A recent Cisco and Omdia study of 1,000 IT and network operations leaders confirms a shift to AI-led networks run by autonomous agents.

## 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

## Understanding ASPA: The next step in routing security

DevFeed: [Understanding ASPA: The next step in routing security](<https://devfeed.tech/articles/understanding-aspa-the-next-step-in-routing-security-58378.md>)

Original publisher: [Read original article](<https://blog.apnic.net/2026/09/23/understanding-aspa-the-next-step-in-routing-security/>)

Author: Dale Roberts

Published: 2026-09-23T04:55:18Z

Content type: news

Language: en

Sources: [APNIC Blog](<https://devfeed.tech/sources/apnic-blog.md>)

Topics: [Routing Security](<https://devfeed.tech/topics/routing-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [BGP](<https://devfeed.tech/topics/bgp.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Internet](<https://devfeed.tech/topics/internet.md>)

Tags: [apnic-academy](<https://devfeed.tech/tags/apnic-academy.md>), [aspa](<https://devfeed.tech/tags/aspa.md>), [bgp](<https://devfeed.tech/tags/bgp.md>), [development](<https://devfeed.tech/tags/development.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [network](<https://devfeed.tech/tags/network.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [routing](<https://devfeed.tech/tags/routing.md>), [routing-security](<https://devfeed.tech/tags/routing-security.md>), [rov](<https://devfeed.tech/tags/rov.md>), [rpki](<https://devfeed.tech/tags/rpki.md>), [security](<https://devfeed.tech/tags/security.md>), [tech-matters](<https://devfeed.tech/tags/tech-matters.md>), [webinar](<https://devfeed.tech/tags/webinar.md>)

### AI overview

APNIC Academy announces a webinar on Autonomous System Provider Authorizations (ASPAs), an RPKI object for validating BGP AS paths and identifying route leaks. The session will cover ASPA deployment, monitoring, validation, and its relationship to ROAs and ROV.

### Source excerpt

Join this APNIC Academy webinar to understand how ASPAs work, how they complement ROAs, and how you can begin monitoring and deploying them in your network.

## Riverbed bolsters network performance monitoring with agentic AI

DevFeed: [Riverbed bolsters network performance monitoring with agentic AI](<https://devfeed.tech/articles/riverbed-bolsters-network-performance-monitoring-with-agentic-ai-50534.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4222770/riverbed-bolsters-network-performance-monitoring-with-agentic-ai.html>)

Author: Denise Dubie

Published: 2026-09-16T19:55:38Z

Content type: news

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [Network](<https://devfeed.tech/topics/network.md>), [Network Operations](<https://devfeed.tech/topics/network-operations.md>), [intelligence](<https://devfeed.tech/topics/intelligence.md>), [telemetry](<https://devfeed.tech/topics/telemetry.md>), [interface](<https://devfeed.tech/topics/interface.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Microsoft Teams](<https://devfeed.tech/topics/microsoft-teams.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-network-management-software-network-monitoring-networking](<https://devfeed.tech/tags/artificial-intelligence-network-management-software-network-monitoring-networking.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [interface](<https://devfeed.tech/tags/interface.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [network](<https://devfeed.tech/tags/network.md>), [network-management-software](<https://devfeed.tech/tags/network-management-software.md>), [network-monitoring](<https://devfeed.tech/tags/network-monitoring.md>), [network-operations](<https://devfeed.tech/tags/network-operations.md>), [networking](<https://devfeed.tech/tags/networking.md>), [performance-monitoring](<https://devfeed.tech/tags/performance-monitoring.md>), [visibility](<https://devfeed.tech/tags/visibility.md>)

### AI overview

Riverbed has added agentic AI capabilities to its network performance management products. The company says Riverbed NPM 360 can help network operations teams investigate problems through natural-language questions, correlate relevant network data, monitor conditions over time, and optionally take remediation actions such as rerouting traffic with a human kept in the loop.

### Source excerpt

Riverbed has added new AI capabilities to its network performance management products that the company says will help network operations teams more quickly troubleshoot problems and provide visibility across distributed enterprise networks. Riverbed NPM 360 integrates agentic AI capabilities of Riverbed IQ and Q into Riverbed's AppResponse and NetProfiler tool and extend network visibility across remote users, Zero Trust architecture, and public environments with NPM+, according to the company. Riverbed IQ serves as the intelligence layer behind NPM 360, applying causal, predictive, generative, and agentic AI across operational data. Riverbed Q provides a conversational interface that lets network professionals investigate performance problems using natural-language questions instead of navigating multiple dashboards and queries, says Richard Tworek, chief technology officer at Riverbed. "We see in the marketplace that the 'gray beards' are starting to disappear," Tworek says. "Less experienced folks are coming into managing network operations." Riverbed's goal, he adds, is to "basically make someone who is fairly new into an expert by using our tools." Historically, network teams have had to determine which monitoring system has the relevant answer across multiple tools and then correlate that data to determine the cause of a slow application or connectivity problem, he explains. With Network 360, Tworek says, an operator can ask a question and let the platform determine which systems and network data are relevant to the problem. "Just ask the question," Tworek says. Network 360 can determine where an issue is occurring, identify the relevant part of the network, and use that intelligence to help solve the problem, he explained. Tworek says the technology can also take remediation actions, such as rerouting traffic, although customers can keep a human in the loop before those actions are carried out. Tworek says an operator could assign an agent to watch a router o

[Next page](<https://devfeed.tech/topics/network-operations.md?cursor=WyIyMDI2LTA5LTE2VDE5OjU1OjM4KzAwOjAwIiwgIjcyMzE0MGJlLTAzNmMtNGY3YS1hNDcyLTU0MDZmMGEzOGFlNiJd>)