Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

Agentic AI–Driven Firewall Migration

A human-in-the-loop production cutover — field report

Version 1.0 — July 2026 · Français · Licence: CC BY 4.0

TL;DR — In late July 2026, an ageing production firewall HA cluster at an industrial site was replaced by a new-generation HA cluster from a different vendor. The entire operation — pre-cutover audit, API configuration writes, cable-by-cable cutover guidance, automated acceptance testing, site-to-site VPN bring-up (including root-cause diagnosis), a real HA failure test, and all documentation — was driven by a general-purpose agentic AI system (Claude, Anthropic — via Claude Code), with a human operator in the loop for every physical action and every GO/NO-GO decision.

To our knowledge, this is the first publicly documented field report of a live production firewall migration cutover executed by a general-purpose AI agent. Prior art exists in adjacent areas (see Related work) but stops at operations assistance or offline configuration translation.

Results

Metric Outcome
Incidents 0
Rollbacks 0
GO pronounced T₀ + 95 min (25 min ahead of the deadline)
Internal segment cutovers < 10 s each
Internet service restored 3 min after T₀
Site-to-site VPN Operational after 5 min of effective configuration
HA takeover (hard power cut) < 10 s, no perceived outage
Acceptance tests 12/13 PASS, 1 reserve out of firewall scope*

* The single reserve concerned an ancillary element that remained unreachable for a cause located upstream of the firewall — the firewall saw no traffic from it and blocked nothing. It was documented in-window and handed over to the relevant third party.

Who this is for

Network and security engineers planning a cross-vendor firewall migration; administrators working through a serverd-based management API; anyone assessing whether agentic AI can be trusted with production infrastructure changes, and under what constraints.


1. Scope of the operation

Item Detail
Source Legacy firewall HA cluster, Active-Active, in production
Target New-generation NGFW HA pair (different vendor), Active-Passive
Method Physical swap at constant IPs, segment-by-segment (LAN → WAN1 → WAN2 → DMZ)
Final policy 28 filter rules (ordered as the source policy), 3 NAT rules, 8 static routes, ~140 network objects, IP-reputation blocking, explicit logged final deny
Extras done in-window IPsec IKEv2 site-to-site tunnel to a partner site (pre-registered, diagnosed & activated live), real HA failure test (hard power cut of the active member), WAN failover test
Human role All cabling, all GO/NO-GO decisions, business acceptance tests (VoIP calls, badge system, cameras, mail), password custody
Agent role Everything else: audits, API sessions, config writes, verification, network testing, incident diagnosis, documentation, backups

2. Why this is different from "AI-assisted networking"

The agent did not suggest configurations for a human to apply. Within an explicit safety harness, it held the API sessions itself: it read state, wrote configuration, activated policies, verified outcomes, took backups before/after every write batch, and drove the human's physical actions step by step ("unplug WAN2 from both members, then tell me done"). The human never typed a firewall command during the window.

3. The safety harness (what made it acceptable in production)

  1. Single-attempt authentication — anti-bruteforce/lockout discipline: one clean auth per session, hard stop on any failure. (Applied for real: one ACCESS_DENIED on a partner device ended that line of work immediately.)
  2. Backup before any write — every write batch bracketed by verified configuration backups (6 produced during the window, integrity-checked by size).
  3. Read-only by default — the entire pre-cutover audit ran in a single read-only session; write privileges were taken explicitly per batch.
  4. Same-session commit — buffered changes (filter rules) checked and activated in the same API session, never left dangling.
  5. HA sync discipline — forced HA synchronisation + verification after every write, with known-quirk tolerance (slave silent up to 5 min).
  6. Human GO gates — three formal GO/NO-GO gates (equipment state, cutover start, final acceptance), pronounced by the human window chief only.
  7. Rollback always defined — the legacy cluster stayed powered and cabled-off; documented physical rollback < 15 min available until the final GO.
  8. Full traceability — every command, finding and decision journaled in real time into the operations log; acceptance report generated in-window.

4. Timeline (T₀ = 12:00)

Time Event
11:32 Blank-run audit of the new cluster (single read-only API session): policy, routes, objects, HA, licences — conformity + 3 deviations found (incl. an over-broad admin ACL flagged to the human for decision)
11:45 HA master forcing re-applied; new DMZ interface configured via API; pre/post backups
12:00 T₀ — cutover starts, segment by segment, both members
12:03 Internet restored through the new cluster (gratuitous-ARP did its job)
12:20–12:35 Site-to-site IPsec tunnel: agent found the pre-registered policy disabled with a wrong selector, fixed it, then root-caused a silent failure to the IPsec engine never having loaded its config (CONFIG IPSEC RELOAD — see lessons) → SA established, SIEM reachable
12:50 Business acceptance: VoIP, badge system, cameras (4G), mail, intranet — 5/5 PASS
13:10 WAN failover test: instant switch to backup link and back; tunnel re-established alone
13:20–13:30 Real HA test: hard power cut of the active member → takeover < 10 s, no perceived outage → automatic failback on return
13:35 GO — migration validated (12/13 acceptance tests PASS + 1 reserve out of firewall scope)
13:41 Fresh as-built collection + final verified backup

5. Lessons learned — target firewall serverd API

Generic and reusable. Each finding below was hit for real during the window.

CONFIG IPSEC ACTIVATE is not enough — symptom: MONITOR GETSPD returns 0 entries

If the IPsec engine never loaded a policy, ACTIVATE leaves the SPD empty and no IKE initiation happens, even with keepalive enabled. The fix is CONFIG IPSEC RELOAD. This is the single most expensive finding of the window: the tunnel looked correctly configured and silently did nothing.

CONFIG WEBADMIN ACCESS ADD is positional — host= yields Invalid parameters

Pass the object name positionally: CONFIG WEBADMIN ACCESS ADD <object>. Named parameters are rejected.

CONFIG NETWORK INTERFACE ACTIVATE drops your admin HTTPS session

When the change touches the bridge carrying the admin port, the session dies — but the change still applies. Reconnect and verify; do not replay the command.

Interface addressing uses ADDRESS ADD, not UPDATE

Bridge removal goes through UPDATE ifname=X Bridge= with an empty value.

IPsec gateway policies are indexed by slot=, not index=

LIST returns the active view unless you pass useclone=1. Read after ACTIVATE, never between UPDATE and ACTIVATE, or you will be reading stale state and conclude the write failed.

There is no MONITOR LOG on this firmware

Log review is GUI-only. The API-side observability workhorses are MONITOR HOST and MONITOR CONNECTION (the latter requires at least one filter).

HA "forced active" designation is runtime state

It does not survive a member power-off. Re-apply it after any full restart — including after an intentional HA failure test.

HA Quality is a percentage of link-up enabled interfaces

Un-cabled spare ports make values like 55/44 a healthy reading. Don't chase 100.

6. Related work — how this differs

  • Cisco AgenticOps (2025–2026): agentic AI for network operations (alert triage, troubleshooting, assisted config) within Cisco's ecosystem — not cross-vendor migration cutovers. cisco.com
  • Huawei Autonomous Driving Network / AN Agents (L4, 2024–2025): telco self-healing and assisted operations — same category, same limitation. huawei.com
  • SANS Institute, May 2026Leveraging LLMs for Cross-Vendor Firewall Configuration Migration (Claude vs ChatGPT): the closest published work — an offline configuration translation study; the model generates, a human applies. sans.edu
  • Deterministic converters (FortiConverter, Expedition, SmartMove, DirectFire): rule translation without agency — no audit, no testing, no decisions.
  • TM Forum Autonomous Networks (L0–L5): this operation is best described as supervised L4-style autonomy applied to an infrastructure change. tmforum.org

7. What is deliberately NOT in this repository

No customer configurations, no IP addressing plans, no serial numbers, no credentials, no site or partner names, no vendor or model names, no backups, no exact operation date. This is a methodology and lessons-learned publication; all operational data stays with the customer (NIS2 context).

8. Limitations and open questions

Stated plainly, because a field report that only reports successes is marketing:

  • n = 1. One site, one vendor pair, one operator. Nothing here establishes a success rate.
  • Not independently reproducible. The harness is described, not shipped. A sceptical reader has the methodology and the author's word, not an artefact they can re-run.
  • Small policy surface. 28 filter rules and ~140 objects is a mid-size SMB/industrial policy. Behaviour on a 2,000-rule enterprise rule base is unknown and should not be extrapolated from this.
  • Operator expertise was load-bearing. The human held the GO gates and would have caught an unsafe instruction. This result does not transfer to an unsupervised agent or a non-expert operator.
  • Model dependency untested. One agentic system was used. No comparison against another was run during the window.

How to cite

See CITATION.cff, or:

Ramseyer, B. (2026). Agentic AI–Driven Firewall Migration: A human-in-the-loop production cutover — field report (Version 1.0). Digital-CyberWare.

Author

Bastien RAMSEYER — Digital-CyberWare (DCW) — operation design, window command, physical execution. Agentic system: Claude (Anthropic), operated through Claude Code.

Feedback, corrections, and similar field reports are welcome — please open an issue.


Licence: CC BY 4.0. The lessons and methodology described here are reported from a single operation; they are not a substitute for vendor documentation, professional judgement, or testing in your own environment.

About

Field report: a live production cross-vendor HA firewall cutover driven end-to-end by an agentic AI (Claude Code), human-in-the-loop. Zero incident, GO at T₀+95min.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors