On this article, we examined engineers’ expectations concerning AI brokers for networking and safety, in addition to the supply of business and open-source AI brokers or options.
What Is an AI Agent?
An AI agent is an autonomous software program system that independently perceives, causes, and acts to realize particular targets. In contrast to conventional software program that follows mounted directions, brokers repeatedly monitor their atmosphere, make dynamic selections primarily based on accessible info, and adapt their methods via studying and expertise. Trendy AI brokers make the most of instruments equivalent to internet search, APIs, code execution, and file manipulation to work together with exterior programs, enabling them to carry out complicated duties—from community monitoring and troubleshooting to safety evaluation and menace response.
Design and Structure
On the design and structure stage, AI agent creators ought to resolve the next:
- Select the AI framework.
- Select associated AI mannequin(s).
- Design AI agent instruments.
- Collect and check details about databases, APIs, and MCP servers which are deliberate for use.
Fashions for AI Brokers
The LLM is a central controller, or “mind,” for brokers. It’s a vital factor for the brokers. So, which mannequin must you select? One of many methods to differentiate between the fashions is by utilizing benchmarks. Benchmarks in AI are standardized exams designed to measure and examine the skills of various fashions on particular duties or a set of duties.
Lots of the hottest benchmarks usually chosen for mannequin comparability don’t embrace networking- or security-related questions.
One of many closest networking benchmarks that we’ve discovered is Community Operational Information (NOK) benchmarking for LLMs (Dec 15, 2023). For safety, there’s the CTIBench benchmark. It’s also possible to discover Basis-Sec-8B, a mannequin developed by Basis AI at Cisco. Basis-Sec-8B is an open-weight language mannequin specialised for cybersecurity functions.
There are considering fashions that ideally match the necessities for brokers.
AI Reasoning and Considering Fashions
- Gemini 2.5 Professional (Deep Suppose).
- GPT-5 Considering.
- Claude Sonnet 4.0 Considering.
- Claude Opus 4.1 Considering.
- Qwen3-235B-A22B-Considering.
AI Brokers: Expectations
Listed below are the outcomes of surveys concerning “Which AI brokers would you most need to discover on Cisco DevNet Code Alternate?”:
AI Brokers on Cisco DevNet Code Alternate: Survey Outcomes (September 2025).
Mixed survey outcomes (100 whole votes):
- Configuration automation: 37% — The best choice among the many DevNet group, indicating robust demand for AI brokers that may automate community configuration duties and infrastructure administration.
- Community monitoring brokers: 32% — Shut second precedence, exhibiting engineers need AI-powered instruments for community visibility, efficiency monitoring, and operational insights.
- Menace and vulnerability brokers: 22% — Important curiosity in AI brokers targeted on safety monitoring, menace detection, and vulnerability evaluation capabilities.
- Code technology brokers: 9% — Lowest precedence, suggesting engineers are much less interested by AI instruments for writing code in comparison with operational automation.
The mixed outcomes from Cisco DevNet, LinkedIn, and X/Twitter surveys exhibit a transparent desire for operational AI brokers over development-focused instruments. With almost 70% of votes going to configuration automation and community monitoring, the Cisco technical group prioritizes AI brokers that clear up real-world infrastructure challenges moderately than code technology utilities. Twenty-two % of votes went to AI brokers targeted on safety.
Listed below are duties that Community and Infrastructure engineers, SREs, and DevOps groups need to make the most of an AI agent for inside their workflows:
Common outcomes of the offline surveys at Cisco DevNet Share Your Expertise Zone (2024–2025).
AI Brokers for Networking and Safety: Open-Supply and Industrial
There are open-source AI brokers for networking that allow you to handle and troubleshoot community units through pure language, robotically changing requests into protected CLI actions or gRPC/REST API calls. There are additionally brokers that automate complicated diagnostics and troubleshooting finish to finish. These brokers validate intent, plan per-device investigations, execute instructions throughout a number of units, assess findings, and generate clear, memory-augmented experiences.
We in Cisco DevNet collect open-source networking and safety AI brokers right here: https://developer.cisco.com/codeexchange/search/?q=ai+agent. Quickly, it is possible for you to to discover a separate part for MCP servers at DevNet Code Alternate.
And what can industrial firms provide?
Cisco has a Cisco AI Assistant that may work with numerous merchandise and assist analyze insurance policies, robotically generate experiences, and ship notifications, amongst different duties. Cisco AI Assistant is conscious of the newest documentation and guides associated to the merchandise. Cisco can be creating AI Canvas, the primary generative UI that unifies real-time telemetry, AI insights, and staff collaboration throughout all IT domains in a single clever workspace.
Here’s a listing of business firms that develop AI brokers as merchandise: AI Community Engineers from Nanites AI, DevAI, Copilot for Community Automation by Selector AI, and Aviz AI Brokers.
Many industrial firms declare to supply multivendor assist. The AI brokers developed by industrial firms can carry out on a regular basis duties, equivalent to robotically verifying end-to-end pings, checking community compliance, producing audit experiences on demand, validating firewall guidelines, and offering Degree 1 assist automation. Additionally they provide superior capabilities, together with stock insights that immediately entry full community information (units, OS variations, {hardware} SKUs, ASICs, MAC addresses, and transceivers), in addition to correlation and prediction for capability and efficiency planning.
AI Brokers: Safety Considerations
As fashions evolve, issues about accuracy and reliability lower over time; in the meantime, safety and compliance issues enhance. That is related to widespread media protection concerning mannequin jailbreaking, immediate injection, and mannequin poisoning.
AI brokers could cause points, present incorrect directions, or apply non-optimal configurations.
Potential AI agent errors might be related with the next:
- Incorrect agent ideas primarily based on info/errors obtained from companies via REST APIs/WebSockets/CLI.
- Hallucination.
- Selecting the improper instrument.
Using associated AI safety instruments, guardrails, and deciding on the suitable fashions will help mitigate dangers.
On the similar time, AI brokers can present clever automated protection. Generally safety specialists want an assistant to assist react to incidents or collect and apply associated insurance policies and updates. Safety engineers usually lack enough time to assessment alerts, gather information from numerous sources, contemplate particular and historic context, and take applicable motion.
Need extra AI content material? Take a look at Cisco DevNet AI Hub: https://developer.cisco.com/web site/ai/
