Contact Open demo
Agent

Ask your workspace, then act on it

Answers from your workspace data. Every answer links to the question, path or issue behind it, and shows what it cannot show.

Open the demoRead the docs

Every answer shows its work

You watch it run: the data basis, the tools it calls, the reasoning, then an answer with a table or chart you can export and a plain statement of what it cannot show.

How answers are built
▯‹AgentDemodata onlyAgent 4Help
Which agents can reach crown-jewel data? ⌄+
⌁ Ask nerl0
A little less trust would be nice… · 1 s
✓Checked the data basis · Latest scan 2026-11-09 06:00 UTC (2 days ago)
✓Ranked agent exposure · 25 agents with reach, 12 reach crown jewels
✓Found crown-jewel stores · 4 stores through 18 paths, all proven
✓Reasoning ·

Two agents have the most access: incident-remediator and ops-automation-agent, both on aws. Each reaches 4 crown-jewel stores and 14 data stores through proven Admin routes.

Basis: The latest scan is from 2026-11-09 (2 days old). All 7 platforms were collected completely. Log sources exist only for aws, github and slack.

Ranking (25 agents with reach, 12 of them reaching crown jewels, 0 with write access):

1. incident-remediator (aws) has 4 crown jewels, 14 stores and 14 paths. No owner was collected. incident-remediator

2. ops-automation-agent (aws) has 4 crown jewels, 14 stores and 14 paths. It has 1 open issue. ops-automation-agent

3. claims-assistant (aws) has 2 crown jewels and 2 stores. Its owner is Priya Nair. claims-assistant

Crown-jewel stores per agentScan of 9 Nov 2026 07:00CSV
40
incident-remediator
ops-automation-agent
claims-assistant
claude-code-action
data-pipeline-agent
contract-review-agent
data-quality-agent
invoice-ocr
legacy-batch-job
partner-sync
What this answer cannot show
  • A route shows granted authority. It is not evidence that the access was used.
  • 10 of 18 paths are listed; the Security Graph shows all of them.
Evidencescan · Scan of 9 Nov 2026 06:00scan · Scan of 9 Nov 2026 07:00agent · incident-remediatoragent · ops-automation-agentagent · claims-assistant
Open Environment ↗Open Agent activity ↗Open the Security Graph ↗

Ask anything, @ charts & metrics, or / for skills…

+Claude Sonnet 5.5◜ Normal◌ Auto⌖↑

Start from a good question

Suggested questions, the page you are on as context, and skills you can call with a slash. Normal or Auto, you choose how far it goes.

Page as context@ charts and metrics/ skillsLinks to the source
New chat ⌄+

How can I help you?

Answers from your workspace data. Every answer links to the question, path or issue behind it.

Investigate AI agent exposureWhich questions should we track?Review question coverage

+Claude Sonnet 5.5◜ Normal◌ Auto⌖↑
Compare scans ⌄+  ⤢  ✕
Compare scans
⌁ Compare scans▤ 4 steps ›

5 measures changed between the scan of 7 Nov 07:00 and the scan of 9 Nov 07:00.

Latest scan against the previous one9CSV
MeasurePreviousLatestChange
Agents3941+2
MCP servers56+1
Shadow agents000
Agents without a confirmed owner220
Identities5152+1
Identities without a confirmed owner110
Data stores5961+2
Crown-jewel stores440
Open findings7778+1
Source: GET /api/v1/inventory/history, GET /api/v1/findings/history
Inventory over the last 12 scans8 Oct 2026 – 9 Nov 2026CSV
9708 Oct9 Nov
Open findingsData storesIdentitiesAgents
Counts of each published scan's inventory, with today's classifications and governance applied to every scan; open findings per scan. Source: GET /api/v1/inventory/history, GET /api/v1/findings/history
What this answer cannot show
  • The scan of 7 Nov 07:00 collected salesforce only partly: a difference there can be a difference in visibility, not in your environment.
  • Counts compare totals; they do not say which entities came or went. Latest changes on the dashboard lists them per question.
Evidencescan · 49a998c6-0408-4bc7-982e-8e454fb1d5fescan · e07c354c-4aaa-4e30-b18f-8a1468449688
Export answer (JSON)
Open the dashboard ↗Open Exposure Insights ↗
Page · Dashboard ×

Ask anything, @ charts & metrics, or / for skills…

+Claude Sonnet 5.5◜ Normal◌ Auto⌖↑

Numbers you can export

Compare two scans, rank agents by exposure, chart the result. Tables come with CSV export and the scans behind every number.

  • Tool stepsSee which tools ran and what they returned.
  • CSV exportEvery table and chart exports.
  • EvidenceScan ids and entities behind the answer.

From one question to the whole path

The same question, answered from the same scan, with every route behind it.

What it reached
25Agents with reach
12Reach crown-jewel data
4Crown-jewel stores reached
18Paths, all proven

Questions people ask first

Pick one and see what the Agent does with it.

Try the demo
?Investigate AI agent exposureExposure?What changed since the last scan?Scans?Who can reach crown-jewel data?Access?Which questions should we track?Questions?Compare scansScans

Ask in plain words. Get an answer you can prove, with the scan ids to show for it.

Agentnerl0 · Ask your workspace, then act on it

Questions.
Evidence.
Action.

See how nerl0 worksView docs →

Ask your first question.

Open the demoTalk to us