IT & endpoint management
Beam for IT teams
Your people have AI on their laptops. Beam gives you a per-machine record of what that AI did — commands, file changes, tool and MCP calls, endpoints — stored locally and readable when someone asks.
It sits beside your existing endpoint tooling. Owners and admins set observe, advisory, or enforce policy, and can roll the collector out through Apple and Windows MDM.
What a rollout actually involves
Everything below is verifiable on one machine before you touch a second one.
- Footprint
One local process, loopback only
The collector binds to 127.0.0.1:4319 and writes locally. No kernel extension, no OS surveillance. Sentinel is an optional Chrome extension that checks AI chat sites before send — not keystroke logging.
- Deployment
MDM and a workspace console
Apple and Windows MDM for the collector, plus owner and admin roles for org baselines and stricter member overrides.
- Coexistence
Sits beside your EDR, not in front of it
Beam watches the layer endpoint tooling cannot see: tool calls, MCP servers and skill files. It intercepts nothing at the OS level.
- Portability
Formats your pipeline already reads
OTLP/HTTP JSON in, redacted NDJSON out. Nothing is forwarded automatically, so the data path is only what you build.
- Supply chain
Pre-run review of skills and MCP servers
Eleven heuristic patterns plus a version-pin check, run before someone connects a file to production credentials.
- Support
An answer when someone asks what happened
Flagged actions keep the triggering event as evidence, so a ticket closes with a record instead of a recollection.
What the security questionnaire will ask
- Retention per machine
- Latest 10,000 events and 500 scan reports
- Failure mode
- Capture failures print to stderr and never halt the tool
- MDM package
- None — Jamf, Kandji and Intune are not supported
- Central console
- None — pairing is per-machine today
- Enforcement
- None — observe and alert only in v1
A low-friction rollout
- 01
Prove it on your own machine
Run the collector, pair the app with its printed token, import a sample record. The token stays in browser memory, not in a URL.
- 02
Pilot with a willing team
Hooks are merged deliberately, so nothing changes on a laptop without an action someone took on purpose.
- 03
Decide what to standardize
Use two weeks of real activity to write policy grounded in what your AI does.
Why this lands on IT's desk
By 2028 (Gartner prediction)
A quarter of enterprise breaches tied to AI agent abuse
Gartner also puts spend on securing AI near $4.8 billion in 2027. Endpoint owners inherit most of that question.
July 2025
An assistant update shipped an attacker's instructions
A prompt injected through a pull request reached v1.84.0 of the Amazon Q extension. Software-update review does not cover instruction-layer risk.
September 2025
A malicious MCP server reached an estimated 300 organizations
postmark-mcp v1.0.16 added a silent BCC to an attacker address, on 1,643 total downloads. People install these without a procurement step.
Answering the surveillance objection honestly
Beam is built so you can say precisely what it does — and what it cannot do.
Beam does
- Record what the AI did: commands, file paths, tool and MCP calls, hostnames
- Keep collector records on the user's own machine, credentials redacted before write
- Let owners and admins set observe, advisory, or enforce policy, including Sentinel on browser AI chats
- Scan skill files and MCP configs someone is about to trust
- Leave data in portable formats, so moving it off the endpoint is deliberate
Beam does not
- Monitor the person: no keystroke logging or screen capture. Sentinel only checks supported AI chat pages before send
- Send collector events to a vendor or analytics service by default
- Guarantee a verified deny on Cursor, Copilot CLI or Gemini
- Capture activity from sources you have not instrumented
Questions IT asks first
Can we deploy Beam through Jamf, Kandji or Intune?
Yes. Apple and Windows MDM are available for the collector. Workspace owners and admins set org baselines and can apply stricter member overrides.
Will people see this as surveillance?
Only if you describe it badly. Beam records what the AI did, not what the person did: no keystroke logging, no screen capture. Sentinel is optional and scoped to supported AI chat sites before send. Collector data stays in local files unless you export it.
Does it conflict with our EDR or endpoint agent?
It should not. Beam is a userspace process on loopback that receives events a hook sends it. No kernel extension, no OS-level interception — and it covers the AI layer endpoint tooling has no visibility into.
What happens if the collector is down or misconfigured?
Collector capture failure does not hang the agent. Enforce policy is fail-open when cached policy is missing or expired: the action proceeds. The cost of that failure is a missed deny, not a locked laptop.
Related
Start with one machine and a two-week pilot
Find out what AI is doing on your endpoints before you write the standard — with a record you can show the person it came from.