The receipt, not the demo: Four questions that earn AI agent trust
Rebuilding PubHub: How AI-assisted development shipped a mandatory rewrite 3.5 months early - Part 1
DevNet
Rain, Agents and Open Source: My Week at Web Summit Lisbon
Storm Charles canceled a day of Web Summit Lisbon, but the masterclass on open-source AI platform engineering with CAIPE still filled the room. Plus one lesson on live demos.
Accelerating innovation: How Cisco CVDs and Red Hat Ansible are transforming data center automation
CVDs now ship with Ansible automation, and the Cisco Intersight collection has grown from about a dozen modules to 137. Watch episode 2 for the full conversation.
Prove It: Does a Learned Rule Actually Change What Your AI Assistant Writes? – Security Loop Series, Part 4
Same requests, identical workspaces, a blind judge. Without learned security rules the agent wrote an insecure trust check 8 of 8 times. With them, 0 or 1 of 4.
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.

















