Three languages, one binary: Building a VMware Nutanix inventory with Claude
Two UIs, two CSV shapes, and a spreadsheet I kept rebuilding. Claude helped turn throwaway scripts into one Go binary that inventories VMware and Nutanix in a single run.
DevNet
Cisco DevNet is your hub for building the next generation of intelligent infrastructure with agentic AI. Discover how AI agents can call Cisco APIs, reason over network data, and take action on their own, with hands-on guides to Model Context Protocol (MCP) servers, agent frameworks, and the SDKs that connect them to real Cisco platforms.
Go beyond scripts and playbooks with AI-driven network automation that can detect issues, recommend fixes, and run multi-step workflows across your environment. Learn how to apply shift left security to agentic systems, from guarding AI-generated code to setting guardrails on what autonomous agents are allowed to do. You’ll also find patterns, sample code, and best practices for enterprise application development where AI agents work alongside your teams.
Explore the latest from the Cisco DevNet community below, and join a global network of developers turning AI ideas into working code.
Our Favorite Topics:
The receipt, not the demo: Four questions that earn AI agent trust
A good demo proves nothing. Four questions about policy, approvals, and audit logs show whether an AI agent has earned the right to touch production.
Rebuilding PubHub: How AI-assisted development shipped a mandatory rewrite 3.5 months early - Part 1
A security mandate forced a PubHub rewrite. AI-assisted development helped 12 engineers deliver nine months of work in about five and a half. Here is the sequence that worked.
DevNet
Rebuilding PubHub: A Cautionary Tale of AI-Driven Requirements, Part 4
AI wrote my requirements instantly, then handed me a mountain to review. Here is the cost of 12 dense epics, and the lean fix that put people back in charge.
Welcome to the DevNet Month of Cisco Validated Designs
Cisco Validated Designs give you tested, supported blueprints, and AI design review catches problems before anyone pulls a cable. Watch episode 1 and join us every Thursday.
CodeGuard: Teaching your AI coding assistant to never write that bug again – Security Loop Series, Part 3
Your AI coding assistant has never read your security reports, so it will write the bug you paid to find. One command turns a real finding into a rule in every IDE.
Mastering stateful stream reordering at 200,000 messages per second
Our Flink job hit a wall at 200,000 messages per second because of RocksDB. Here is the in-memory reordering pattern that fixed it, and how A/B development proved it safe.
Design-to-Code: Reimagine Handoff Workflow with AI – Rebuilding PubHub Part 3
How the PubHub team replaced the Figma handoff with an AI-built, designer-refined HTML prototype, and what worked and didn't along the way, so other teams can adapt it.
Foundry in the real world: Turning LLM hunches into verified findings – Security Loop Series, Part 2
An LLM's "look here" is not "this is real". Foundry adds an evidence gate that turns hunches into verified findings, tested on Langflow, MLflow, and PyGoat.
Rebuilding PubHub: AI-first SDLC, one bottleneck at a time – Part 2
We didn't follow an AI-first playbook, so we built one by trying, failing and iterating. Here's what each step of the PubHub rewrite taught us, and the seven practices that stuck.
Policy as Code for the Network: Guardrails with Open Policy Agent
Learn how to use Open Policy Agent (OPA) to enforce network guardrails as code. Catch insecure configurations before deployment and maintain a unified security posture across your entire enterprise network.
How Cisco IQ Powers Continuous Compliance for PCI DSS 4.0 and Quantum Readiness
How can financial institutions harvest the capabilities of Cisco IQ to navigate compliance with regulatory frameworks and ensuring quantum readiness by 2030? Cisco IQ, with professional grade analysis and AI powered insights, simplifies this.
