Internal-shaped tools that fold AI into the spots where network engineers lose hours. Auditors that cite the control they break. Terminals that pair-program. API consoles that fetch live docs. Digital twins that propose the fix and wait for your nod.
An autonomous Cisco security auditor. Tell it an IP. It SSHes in, runs hardening checks, cross-references NIST 800-53 and CIS, looks up live CVEs, and produces the report. No checklists, no scripts.
A multi-tab SSH terminal with an AI sidekick that watches your session and suggests the right command before you Alt-Tab to ChatGPT. Cloud or local model — your call.
A streaming chat UI for Cisco's DevNet Content Search MCP. Ask anything about Meraki or Catalyst Center APIs and get a token-streamed answer with real operation IDs and doc URLs. Hosted on a single Worker.
A continuous-model platform: snapshots the whole network with pyATS, runs tiered AI agents over it (Ollama → Haiku → Sonnet → Opus on escalation), proposes fixes, executes only after a human approves them.
I'm a network engineer first. Every tool here exists because I needed it on a Friday at 17:30.
Real data, real auth, in days — not weeks. Click the thing before the kickoff meeting ends.
Where does the model actually pay rent? Build both paths. Let the workflow decide.
Boring deploy. Documented. Measured. Forget I was here.