On this article, we examined engineers’ expectations relating to AI brokers for networking and safety, in addition to the provision of economic 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 attain particular targets. In contrast to conventional software program that follows fastened directions, brokers repeatedly monitor their atmosphere, make dynamic selections based mostly on accessible data, and adapt their methods by studying and expertise. Fashionable AI brokers make the most of instruments comparable to internet search, APIs, code execution, and file manipulation to work together with exterior programs, enabling them to carry out advanced duties—from community monitoring and troubleshooting to safety evaluation and risk response.
Design and Structure
On the design and structure stage, AI agent creators ought to determine 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 might be deliberate for use.
Fashions for AI Brokers
The LLM is a central controller, or “mind,” for brokers. It’s a vital component for the brokers. So, which mannequin do you have to select? One of many methods to differentiate between the fashions is through the use of benchmarks. Benchmarks in AI are standardized assessments designed to measure and examine the skills of various fashions on particular duties or a set of duties.
Lots of the hottest benchmarks sometimes 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. You can even discover Basis-Sec-8B, a mannequin developed by Basis AI at Cisco. Basis-Sec-8B is an open-weight language mannequin specialised for cybersecurity purposes.
There are pondering 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 here are the outcomes of surveys relating to “Which AI brokers would you most need to discover on Cisco DevNet Code Trade?”:
AI Brokers on Cisco DevNet Code Trade: Survey Outcomes (September 2025).
Mixed survey outcomes (100 complete 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, displaying engineers need AI-powered instruments for community visibility, efficiency monitoring, and operational insights.
- Menace and vulnerability brokers: 22% — Vital curiosity in AI brokers centered on safety monitoring, risk detection, and vulnerability evaluation capabilities.
- Code technology brokers: 9% — Lowest precedence, suggesting engineers are much less all in favour of AI instruments for writing code in comparison with operational automation.
The mixed outcomes from Cisco DevNet, LinkedIn, and X/Twitter surveys show 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 reasonably than code technology utilities. Twenty-two p.c of votes went to AI brokers centered on safety.
Listed here 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 Business
There are open-source AI brokers for networking that allow you to handle and troubleshoot community units by way of pure language, robotically changing requests into secure CLI actions or gRPC/REST API calls. There are additionally brokers that automate advanced 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 reviews.
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 Trade.
And what can business firms provide?
Cisco has a Cisco AI Assistant that may work with numerous merchandise and assist analyze insurance policies, robotically generate reviews, 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 group collaboration throughout all IT domains in a single clever workspace.
Here’s a listing of economic 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 business firms declare to supply multivendor help. The AI brokers developed by business firms can carry out on a regular basis duties, comparable to robotically verifying end-to-end pings, checking community compliance, producing audit reviews on demand, validating firewall guidelines, and offering Stage 1 help 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 Issues
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 relating to 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 based mostly on data/errors obtained from providers by REST APIs/WebSockets/CLI.
- Hallucination.
- Selecting the unsuitable instrument.
Using associated AI safety instruments, guardrails, and deciding on the suitable fashions may help mitigate dangers.
On the identical time, AI brokers can present clever automated protection. Typically safety specialists want an assistant to assist react to incidents or collect and apply associated insurance policies and updates. Safety engineers usually lack adequate time to evaluate alerts, accumulate information from numerous sources, take into account particular and historic context, and take acceptable motion.
Need extra AI content material? Take a look at Cisco DevNet AI Hub: https://developer.cisco.com/web site/ai/
