AI
Atlas AI
JK
← Template library
Industry-specifichighv1.0.0 · System

Attorney-Client Privilege Protection

Detects attorney-client privileged communication and blocks transmission to non-privileged AI systems.

📘Clone & start observing

Creates a Guideline policy. Observation only — nothing is blocked until you promote to Strict.

Mode on clone: log
Defaults to template name. Customise to distinguish multiple instances of the same template.
Leave empty to apply broadly via the template's default data-classification / risk-tier filters.
Rationale

Privileged communication transmitted to a third-party LLM may waive privilege. Legal teams need a hard guard against accidental disclosure.

Example violation
Prompt: "Summarise this privileged memo from outside counsel re Smith v. Acme litigation strategy"
Triggers (1)
  • inputScan prompts for privilege markers
Detectors (2)
  • keyword_listprivilege-markers
    Common privilege headers/footers
  • llm_judgelitigation-context
    LLM judges if content is litigation strategy
Actions (2)
  • blockBlock with privilege warning
  • require_reviewAllow only with GC sign-off
Tunable parameters (2)
Privilege marker phrases
basickeywords
Phrases indicating privileged content.
Default: ["attorney-client privileged","work product","privileged and confidential","subject to legal privilege"]
Context judge threshold
advancednumber
Confidence above which content is judged privileged.
Default: 0.8
Regulatory references
Common-law privilegeBar association rules
Template defaults (suggested target after promotion)
Suggested mode
block
Risk tiers
Data classifications
Departments
Legal

Cloned policies start in Guideline mode. Use the promotion wizard to flip to Strict once you trust the false-positive rate.