Your AI incident lead, running the response in your team chat
It declares the incident, loads the right playbook, keeps the timeline, scopes with Wazuh and writes the post-incident report. Containment and IRIS escalation wait for your Approve click
Incident Response Commander: $99.99, one-time. Product details
In an incident, the record is the first thing to fall apart
- Before: Findings and decisions scattered across threads
- Before: Tasks and owners tracked from memory
- Before: The report rebuilt by hand after it is over
- After: Timeline, tasks, IOCs, hosts and phase, logged as you talk
- After: The right playbook loaded as tasks with due times
- After: The post-incident report built from the record
An incident commander that never loses the thread
- Declares the incident: Sets type and severity and loads one of 8 playbooks as a task list with due times
- Keeps the record: Timestamped timeline, tasks with owners, IOCs, affected hosts and accounts, and the phase. Stored in n8n Data Tables, not chat memory
- Scopes with Wazuh: "Where else did this IP, hash or user show up?" Alert counts, first and last seen, every agent involved and hosts not yet in the incident
- Threat intel: IPs, domains and hashes checked with VirusTotal, AlienVault OTX and AbuseIPDB
- Contains, with approval: Blocks an IP, disables a user or isolates a host through Wazuh Active Response, only after someone clicks Approve
- Stakeholder updates: Plain-language drafts on cadence: critical every hour, high every 4 hours, medium every 24 hours
- DFIR-IRIS escalation: Creates the case after approval, then pushes only what is new: IOCs, assets, timeline, tasks and status
- Post-incident report: A branded HTML report with the timeline, tasks, IOCs and time to contain, delivered in your chat
- Reminders: A schedule with no AI pages the team about overdue tasks, quiet incidents and updates that are due
One command, about ten minutes
- Install: Run one command on Linux, macOS or Windows. It deploys n8n too if you need it
- Connect: Add your AI model key, Wazuh and your chat app. Threat intel keys and DFIR-IRIS are optional
- Respond: Tell it what happened. It declares the incident and gives you the first tasks
What you need
- n8n
- n8n 2.34 or newer with Agents and Data Tables, or let the installer deploy it
- Wazuh
- Wazuh 4.x indexer and manager API with read access. Active Response only if you enable containment
- Chat app
- Telegram, Slack, Discord or Linear. A Telegram bot takes a minute with @BotFather
- AI model
- An API key from any provider in the n8n Agent model picker
- Optional
- DFIR-IRIS 2.4+ and free VirusTotal, OTX and AbuseIPDB keys
Built to act only when you say so
Containment ships in dry-run mode, and every outward action waits for a human click
- Facts come from tools: The model orchestrates and writes prose. Incident facts and reports come straight from the record
- Approve before anything runs: Containment and IRIS escalation both wait for an Approve click in chat
- Dry run by default: Containment ships with dry run on, so nothing is blocked until you switch it off
- Never contains on a guess: It proposes containment only with evidence and refuses internal IPs, protected IPs and protected accounts
- No raw queries: Chat text never reaches Wazuh as a raw query. Every filter is a typed clause
- Private IPs stay private: Internal addresses are never sent to threat-intel services or to IRIS
What you get
- 10 tool workflows plus the reminder schedule
- The agent with 12 skills: 8 playbooks, severity matrix, containment decision, stakeholder updates and the post-incident report
- One-command installer for Linux, macOS and Windows
- Setup guide and example conversations
- Single-organization commercial license
- 7-day money-back guarantee
Common questions
- Can it block things on its own?
- No. Blocking an IP, disabling a user or isolating a host runs only after a human clicks Approve in chat. Containment also ships in dry-run mode, and it refuses internal IPs and protected accounts
- Where is the incident record kept?
- In n8n Data Tables on your own server, not in chat memory. The timeline, tasks, IOCs, hosts, accounts and phase are all stored there
- Which incidents does it cover?
- It ships with 8 playbooks: ransomware, business email compromise, compromised account, malware, data exfiltration, web compromise, insider threat and a generic one for everything else
- Do I need DFIR-IRIS?
- No, IRIS is optional. When it is connected, the Commander creates the case after your approval and later pushes only what is new
- Does it only work in Telegram?
- No. It runs in Telegram, Slack, Discord or Linear, so your team can use the chat it already works in
- Which AI model does it need?
- An API key from any provider in the n8n Agent model picker, such as Anthropic, OpenAI, OpenRouter or Google
- How long does setup take?
- About ten minutes with the one-command installer on Linux, macOS or Windows. It deploys n8n too if you need it
- What if it is not for me?
- You get a 7-day refund. If it does not fit your SOC, you get your money back
All AI agents