Talk to an engineer

Guardrails for the agent harness.

AI Traffic Control keeps regulated data on your machine and checks every prompt and tool call before it runs.

Talk to an engineer Try AI-TC
ai-tc enforced locally
prompt pci/card-number in pasted log redacted
tool call shell: rm -rf in /prod blocked
file read phi/patient-record in fixtures redacted
tool call fetch → untrusted model API blocked
response secret/aws-key in output warned
file read src/api/webhooks.ts allowed
PCI, PHI and PII never reach a model or a third party, unless you turn on setup calibration.

One control point for every event.

Prompts and tool inputs are checked before they reach the model. Responses and file reads are checked after. Each match becomes a finding, and policy decides the outcome.

prompttool callresponsefile read
ai-tc
rule packs · policy
monitorwarnredactblockexception

Runs next to the agent.

No backend to stand up and nothing leaves the machine to be scanned, unless you turn on setup calibration. Claude Code and Claude Desktop are supported today.

Documentation AI-TC Enterprise 
$ /plugin marketplace add akasecurity/marketplace
$ /plugin install ai-tc@akasecurity
$ /aka:setup

Build Your Own Security

How we build
or