~3 min to deploy

AI Agency Pack

Token budgets, approved tool use, and brand-safe output — prove every client-facing agent action stayed inside the agreed rules.

For: Agencies and teams shipping client agents

SOC 2 CC7.2ISO 27001 A.8.9Client assurance

What it enforces

Ethics and Tone Filter

Checks agent output against client brand and safety constraints.

Token Budgeting

Restrains agent runs that exceed the allocated project token wallet.

Tool-Use Whitelist

Blocks tool calls outside the approved client software list.

Deploy in Shadow Mode

ai-agency-pack.yaml

# AI Agency Pack
# Fork: the three gates from the ai_agency starter pack, with your budgets.
apiVersion: decionis.dev/v1
kind: PolicyPack
metadata:
  name: ai-agency-pack
  surface: langchain
  policy_pack_id: ai_agency
  standards: [SOC2-CC7.2, ISO27001-A.8.9]
defaults:
  mode: shadow
  emit_dossier: true
rules:
  - name: ethics_and_tone_filter
    when: "action == 'agent.publish_output'"
    decision: |
      BLOCK IF output.violates_brand_constraints == true
      ESCALATE IF output.tone_confidence < 0.8
      ALLOW OTHERWISE
    reason_code: output_outside_brand_constraints
  - name: token_budgeting
    when: "action == 'agent.run'"
    decision: |
      RESTRAIN IF token_count > 50000
      ALLOW OTHERWISE
    reason_code: project_token_wallet_exceeded
  - name: tool_use_whitelist
    when: "action == 'agent.tool_call'"
    decision: |
      BLOCK IF tool_approved == false
      ALLOW OTHERWISE
    reason_code: tool_not_on_approved_list

Fork it, change the thresholds to match your environment, and deploy in shadow mode first — it defaults to listen-only so nothing in your live pipeline changes.

How to install it

Wraps any LangChain BaseTool. The LLM still picks the tool on the same prompt; Decionis decides if the call fires.

LangChain (Python) — shadow mode

# pip install decionis-langchain
from decionis import DecionisClient
from decionis_langchain import DecionisGateTool

client = DecionisClient(api_key="...", base_url="https://api.decionis.com")

gated_refund = DecionisGateTool.wrap(
    inner_tool=send_refund,
    client=client,
    tenant_id="org-uuid",
    workflow_key="refund_execution",
    shadow_mode=True,     # ← every verdict recorded; inner tool always runs
    site_base_url="https://decionis.com",
)
agent.bind_tools([gated_refund])

Install decionis-langchainShips in shadow mode — every verdict is recorded, nothing is blocked.

Loading…

Open-Policy Exchange