SIRT Triage Agent Workshop
~10 min

What is SIRT and why agentic triage

Understand the security incident response use case, the before/after value proposition, and preview the finished demo.

What does a SIRT team do?

A Security Incident Response Team (SIRT) is the group of analysts responsible for detecting, triaging, investigating, and responding to security incidents across an organization. When an alert fires — malware detected on a workstation, a phishing email reported, suspicious login activity from an unusual country, or data leaving the network in unexpected volumes — SIRT is on the clock.

Their job is to answer three questions as fast as possible:

  1. Is this real? — Distinguish true positives from noise.
  2. How bad is it? — Determine scope, severity, and blast radius.
  3. What do we do? — Recommend containment, remediation, and escalation steps.

Every minute matters. A delayed triage can mean the difference between isolating a compromised host and watching an attacker pivot laterally across the network.

The problem: manual triage is slow

Today, most SIRT workflows look like this:

StepWhat the analyst doesTime
1. Read the alertOpen the SIEM, read raw log data3–5 min
2. Pivot to identity toolsLook up the user in Active Directory, check MFA status5–8 min
3. Check network reputationQuery VirusTotal, AbuseIPDB, or internal threat intel feeds5–10 min
4. Analyze command-line activityReview EDR telemetry for suspicious processes5–10 min
5. Correlate across sourcesMentally stitch together findings from 4+ tools5–10 min
6. Write the triage cardSummarize findings, assign severity, recommend actions5–10 min
Total~30–60 min

That’s 30–60 minutes per incident, with constant context-switching between tools. Analysts handle dozens of alerts per shift. Fatigue leads to missed signals. Burnout is real.

The agentic solution: parallel AI analysis

What if you could throw the incident at a team of specialized AI agents that work in parallel — each one analyzing a different dimension of the incident — and synthesize the results into a triage card in under 60 seconds?

That’s what you’ll build in this workshop.

Before (manual):

  • One analyst, working serially across 4+ tools
  • ~45 minutes per incident
  • High cognitive load, easy to miss correlations

After (agentic):

  • A Coordinator agent dispatches 4 specialist sub-agents in parallel
  • A Triage Synthesizer combines their findings into a structured triage card
  • A Response Agent generates a concrete action plan
  • ~60 seconds end-to-end

Manual vs Agentic Triage

flowchart LR
subgraph manual["Manual — ~45 min (serial)"]
  direction LR
  A1[Analyst] --> A2[EDR]
  A2 --> A3[SIEM]
  A3 --> A4[Threat Intel]
  A4 --> A5[DNS/WHOIS]
  A5 --> A6[Write Report]
end

subgraph agentic["Agentic — <60s (parallel)"]
  direction LR
  B1[Incident] --> B2[Coordinator]
  B2 --> B3[Cmd-Line]
  B2 --> B4[Identity]
  B2 --> B5[Network]
  B2 --> B6[Activity]
  B3 --> B7[Synthesizer]
  B4 --> B7
  B5 --> B7
  B6 --> B7
  B7 --> B8[Action Plan]
end

The four incident scenarios

Throughout this workshop, you’ll work with four realistic incident scenarios seeded into your database:

  1. Malware + Command & Control — A workstation running encoded PowerShell commands and beaconing to a known C2 IP address.
  2. Phishing + Business Email Compromise — A user clicked a credential-harvesting link and their mailbox is now forwarding to an external address.
  3. Anomalous Authentication — A service account authenticating from three countries within 10 minutes with impossible travel patterns.
  4. Data Exfiltration — Large volumes of data uploaded to an unapproved cloud storage provider outside business hours.

Each scenario exercises different analytical dimensions and will be analyzed by different combinations of sub-agents.

What you’ll build with — the Cloudflare primitives

Each lesson introduces one Cloudflare building block. Here’s a preview:

PrimitiveWhat it does in this workshop
WorkersHosts your analyst console app at the edge — both the UI and the API
D1Stores the incident queue in a serverless SQL database accessed via binding
Durable ObjectsGives each incident its own persistent stateful session that survives reloads
Workers AIRuns LLM inference at the edge for analyzing incident telemetry
Agents SDKOrchestrates the multi-agent harness — coordinator, sub-agents, and synthesis
Sandbox SDKExecutes CLI commands (network lookups, hash checks) in an isolated sandbox
Dynamic WorkersGenerates and deploys custom Worker code at runtime for automated response

You don’t need to know any of these in advance. Each lesson introduces one primitive with hands-on exercises.

Knowledge check