{
 "schema": "aiblocks-page/1",
 "id": "agency-engineering-network-engineer",
 "type": "agent",
 "name": "Network engineer",
 "summary": "Find why traffic fails on Cisco, Juniper or Palo Alto gear. Get the path, the likely cause, exact commands to run and a change plan with rollback.",
 "headline": "Network engineer",
 "subhead": "Paste your show-command output, your config and what is failing. It follows the packet path, separates facts from guesses, and names the layer that is failing. You get the next commands to run and, for any change, pre-checks, validation and a rollback.",
 "job": {
  "id": "build-software",
  "name": "Build and ship software"
 },
 "level": "intermediate",
 "thinking": "high",
 "tested": true,
 "updated": "2026-11-03",
 "first_published": "2026-10-26",
 "inputs": [
  {
   "type": "question",
   "required": true,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  },
  {
   "type": "source_text",
   "required": false,
   "label": "Source text",
   "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link"
  }
 ],
 "outputs": [
  {
   "type": "audit_report",
   "required": true,
   "label": "Audit report",
   "what": "findings with evidence, severity, missing inputs and next actions"
  },
  {
   "type": "plan",
   "required": true,
   "label": "Plan",
   "what": "a dated plan: what to do, in what order, with a decision rule for each step"
  }
 ],
 "you_give": [
  "The problem in one line, with the source and destination addresses",
  "Make, model and software version of each device on the path",
  "Output of the show commands you have already run, with passwords and keys removed",
  "A sketch or list of the path from source to destination (optional)",
  "Your change window, and whether you have a console or out-of-band way in"
 ],
 "you_get": [
  "The packet path, and which layer is failing, with the evidence",
  "Facts kept apart from guesses",
  "The exact next commands to run on your platform",
  "For a change, pre-checks, steps in order, validation commands and rollback",
  "The impact of the change, and what else it could touch",
  "A list of what is still missing"
 ],
 "use_when": [
  "Users can't reach a site or app, and you have a traceroute, show output or logs.",
  "A BGP or OSPF neighbour won't come up, or routes are missing.",
  "A firewall rule or NAT isn't doing what you expect on Cisco ASA, Palo Alto or Junos.",
  "You must change a router or firewall in a maintenance window and need steps and a rollback."
 ],
 "skip_when": [
  "Your equipment is Huawei, H3C, Ruijie or Hillstone. Use the China network engineer.",
  "The whole service is down and you need to run the response. Use the Incident response coordinator.",
  "You need to log in and change live devices for you. This agent only writes the plan and commands. You run them."
 ],
 "output_sample": {
  "input": [
   "The problem, with the source and destination addresses",
   "The make, model and software version of each device on the path",
   "Show-command output and config, with secrets removed",
   "Your change window and your console or out-of-band access (optional)"
  ],
  "prerequisites": [
   "An AI that can read pasted text or files, such as Claude, ChatGPT or Gemini",
   "Access to your devices, to run the commands it lists"
  ],
  "output": [
   {
    "name": "Packet path",
    "contains": "The route a packet takes from source to destination, and where it should be matched or changed."
   },
   {
    "name": "Evidence",
    "contains": "What your output proves, kept apart from what is only a guess."
   },
   {
    "name": "Likely failing layer",
    "contains": "Which layer is failing, with the reason and how sure the AI is."
   },
   {
    "name": "Next commands",
    "contains": "Exact commands for your platform, what each shows, and whether it is safe to run now."
   },
   {
    "name": "Change plan",
    "contains": "Pre-checks, steps in order, validation commands and an exact rollback."
   },
   {
    "name": "Impact",
    "contains": "What the change touches and how wide the effect could be."
   },
   {
    "name": "Missing information",
    "contains": "What is still unknown and why it matters."
   }
  ]
 },
 "output_shape": "PACKET PATH\n  <source> enters <interface or VLAN>, routes via <next hop>, exits <interface>, and should match <rule>\n\nEVIDENCE\n  Facts: <what the output shows> | Hypotheses: <what is not yet proven>\n\nLIKELY FAILING LAYER\n  <link, routing, policy and NAT, DNS or application> | <why> | <how sure>\n\nNEXT COMMANDS\n  <platform> | <command> | <what it tells you> | <safe to run now or needs a window>\n\nCHANGE PLAN (if a change is needed)\n  Pre-checks: <commands and expected results>\n  Steps: <numbered, platform-specific>\n  Validation: <commands and expected results>\n  Rollback: <exact commands, and the trigger to use them>\n\nIMPACT\n  <who or what the change touches> | <blast radius>\n\nMISSING INFORMATION\n  MISSING: <what> | <why it matters>",
 "how_to_use": [
  "Download the pack and add it to your AI as a skill. Or open a new chat and paste SKILL.md, then references/source-agent.md.",
  "Describe the problem with the source and destination addresses. Name each device's make and software.",
  "Paste your show output. Remove passwords, SNMP strings, keys and pre-shared secrets first.",
  "Run only the next commands it lists, and paste the new output back. It narrows the cause each round.",
  "For a change, check the rollback and the console plan before you start. Read the impact line twice.",
  "Run the validation commands after the change and keep the output with your change record."
 ],
 "checks": [
  "The result addresses your actual task and cites the evidence used.",
  "Examples, role-play experience and targets are kept separate from verified results.",
  "Claims of tests, memory, tool access or completed actions match what actually happened."
 ],
 "next": [
  {
   "name": "Developer tools engineer",
   "url": "https://useaiblocks.com/skills/agency-engineering-developer-tooling-engineer",
   "why": "Build it"
  }
 ],
 "source": {
  "by": "Michael Sitarzewski and Agency Agents contributors",
  "repo": "msitarzewski/agency-agents",
  "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/engineering/engineering-network-engineer.md",
  "licence": "MIT",
  "original_name": "Network Engineer",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "Network Engineer",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/engineering/engineering-network-engineer.md",
   "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions."
  }
 ],
 "files": [
  "LICENSE",
  "references/source-agent.md",
  "SETUP.md",
  "source.json"
 ],
 "links": {
  "page": "https://useaiblocks.com/agents/agency-engineering-network-engineer",
  "markdown": "https://useaiblocks.com/agents/agency-engineering-network-engineer.md",
  "json": "https://useaiblocks.com/agents/agency-engineering-network-engineer.json",
  "instructions": "https://useaiblocks.com/skills/agency-engineering-network-engineer/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-engineering-network-engineer.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-engineering-network-engineer",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-engineering-network-engineer",
  "mcp": "https://useaiblocks.com/mcp"
 }
}
