SOCPilots
AI investigation model / synthetic illustration

AI-powered investigation. Human-led decisions.

Multi-Layer AI™

Your analysts.
Better prepared.

Help your team understand an alert, gather the surrounding evidence and decide what to do next. Keep every finding open to human review.

Built around your SIEMWazuhElasticSplunkQRadarCapabilities vary

Multi-Layer AI™

From a warning
to a clearer decision.

Give your team a head start: gather context, connect the evidence and prepare the investigation for review. Available checks depend on your connected services and AI configuration.

SOCPilots AI agentOne connected investigation
1 / 6

A security alert starts the investigation.

Example investigation with synthetic data. This animation does not access your systems or take action.

  • Less manual gatheringBring relevant context into the investigation.
  • Clearer handoversKeep observations and findings together.
  • Decisions you can explainReview the evidence before approving a response.
Example investigationAnalyst-led response

An alert. A place to start.

A suspicious attempt to access credentials arrives from your SIEM. SOCPilots keeps the original event attached, so the investigation starts with evidence.

What it brings together
The original alert and its timeline
For your team
Your team knows what happened and where to look

Automation with accountability

Move the work forward.
Keep the decision yours.

From a source alert to a recorded outcome, with a clear point for human review. Connector actions depend on your environment and policy.

  1. 01 / TRIGGER

    Alert received

    Source and event context

  2. 02 / INVESTIGATE

    Enrich evidence

    Tools and entity relationships

  3. 03 / APPROVAL

    Awaiting review

    Analyst evaluates the proposal

    PAUSED
  4. 04 / RESPONSE

    Connector action

    Only after required approval

    NOT EXECUTED
Illustrative workflow / no containment executedReview the safety model ↗

More of the investigation.
Less of the legwork.

Help your analysts gather the context they need, understand related activity and prepare a finding they can explain. Connected services determine which checks are available.

What SOCPilots helps your team investigate

Related alerts

What happened

Bring relevant security events together so an analyst can see the sequence, not just one isolated warning.

investigation support

Reputation checks

What is known

Check available threat-intelligence sources for information about an address or file. Reputation supports an investigation; it does not decide the outcome.

investigation support

Earlier investigations

What came before

Find similar cases and earlier decisions to give the team useful history.

investigation support

Account activity

Who is involved

Understand relationships and unusual behaviour around the affected account.

investigation support

Business context

What matters

Bring device ownership and business importance into the investigation so the team can prioritize.

investigation support

Internet exposure

What is visible

Review available information about externally exposed services as part of the wider picture.

investigation support

Checks and observations stay with the case, so your team can review how a finding was reached.

Grounded in ATT&CK and in what you already decided

Retrieval sits underneath the agent. Technique descriptions, detection content and the SOC’s own written procedures are embedded and searched semantically, so an answer about lateral movement is anchored to the framework rather than improvised.

Uploaded evidence is indexed the same way. A document attached to a case last quarter is findable during an investigation this quarter, including text pulled out of screenshots.

retrievaltop 4 of 1,120
  • T1003.001LSASS memory0.89
  • T1550Alternate material0.81
  • proc-14Credential theft response0.77
  • SP-1904Prior case, same host0.74
interface illustration

Automation that survives a restart

Playbooks are drawn on a canvas and stored as a graph. Runs are persisted, so a playbook waiting three days for an approval is still waiting after a deploy, and a step that was half-finished when a container restarted does not silently vanish.

Sixteen step types are available on the canvas: calling the agent, invoking a connector, asking a human to approve, branching on a condition, waiting, notifying, updating the case. Five trigger types start a run — a person, an incoming alert, a record event, a schedule, or a signed webhook.

Durable execution

Pause. Review. Resume.

Keep the execution record attached to the work, including the point where human approval is required.

View the response flow

Where the models come from

bring your own key

Your account, your spend

Model access runs on keys you supply. Self-hosted deployments keep that relationship entirely between you and the provider, and nothing is routed through us.

multi-provider

More than one provider, by design

Different work is routed to different models, and a provider outage falls through to another rather than taking investigation offline. Provider choice is configuration, not a rebuild.

cost visibility

You can see what it cost

Model calls are traced and priced, per case and per tenant, because “the AI feature” turning into an unexplained invoice is how these programmes get cancelled.

off is a setting

The AI parts are optional

Automated disposition and agent investigation can be turned off entirely and the platform still works as a SIEM-agnostic console. Nothing depends on a model being available.

Watch it investigate something real

The demo we would rather give you is one where the agent runs against your own alerts and you get to disagree with it.