Policy System

The policy system is the core of Conto’s spending controls. Policies define rules that govern how AI agents can spend funds.

What is a Policy?

A policy is a set of rules that determine whether a payment should be:

APPROVED - Payment can proceed
DENIED - Payment is blocked
REQUIRES_APPROVAL - Manual approval needed

Policy Types

Spend Limit

Control maximum amounts per transaction, day, week, or month

Time Window

Restrict transactions to specific hours and days

Counterparty

Control which recipients are allowed based on trust

Geographic

OFAC sanctions screening and country restrictions, built-in and configurable

AgentScore Compliance

Require verified humans, enforce jurisdiction allowlists, and trigger identity step-up before settlement

Contract Allowlist

Restrict interactions to approved smart contracts and protocols via Contract Registry

Approval Threshold

Require manual approval above certain amounts

Velocity

Limit transaction frequency to prevent rapid drain

Whitelist

Only allow specific pre-approved addresses

x402 Controls

Price ceilings, service allowlists, and session budget caps for x402 micropayments

MPP Controls

Session budgets, concurrency limits, and duration caps for MPP payments

Budget Allocation

Allocate budgets by department or project with period tracking

Expiration

Time-limited permissions with start and end dates

Card Payment

MCC restrictions, merchant filtering, and amount limits for card payments

Policy Evaluation

Policies are evaluated fail-closed. When multiple policies are assigned, all must pass. The first DENY stops evaluation immediately.

Evaluation Order

Pre-checks: Agent must be ACTIVE with linked wallets
Geographic & Sanctions: OFAC country check + address sanctions screening (always active, no policy needed)
Counterparty Trust: Pre-fetch trust level and network trust score for use in policy rules
Wallet Policies: Spend limits, wallet-level time windows (timezone-aware), and other configured policy rules
Merchant Identity Gates: Optional AgentScore assess results can add verified-human, KYC, sanctions, and jurisdiction context before final settlement
Counterparty Rules: Block list, trust requirements, network intelligence
Relationship Limits: Per-counterparty spend limits from AgentRelationship records
Final Decision: Aggregate results

Protocol-specific budget rules only count matching protocol transactions. x402 session budgets use the x402 sessionId recorded with each payment, and MPP session budgets use the MPP sessionId, so ordinary wallet transfers do not reduce protocol session allowance.

The default local sanctions provider now reads from Conto’s SanctionedAddress table instead of a hardcoded demo list. That table is seeded by migration with known high-confidence OFAC matches and refreshed by the sanctions-list-refresh background job, so sanctions screening starts with a safe baseline even before the first feed sync completes.

Outcome	Condition
DENIED	Any check denies
REQUIRES_APPROVAL	No denial, and at least one rule or workflow requires approval
APPROVED	All checks pass

Evaluation Semantics

Policy rules use simple AND logic. Every active policy assigned to the selected agent or wallet is evaluated, and every rule inside those policies must pass unless it is a DENY or REQUIRE_APPROVAL trigger that does not match.

Action	Meaning
`ALLOW`	The condition describes what is permitted. If the condition does not match, the payment is denied.
`DENY`	The condition describes what is blocked. If the condition matches, the payment is denied.
`REQUIRE_APPROVAL`	The condition describes what needs review. If it matches and no DENY fires, the payment requires approval.

priority is sort order, not override precedence. A higher-priority ALLOW cannot override a lower-priority deny or a failed allowlist. Use one wider allowlist rule when you need alternatives, not two competing policies.

For a hands-on walkthrough of how evaluation works, see the Policy Testing guide.

Creating Policies

Via Dashboard

Navigate to Policies

Go to Policies in the sidebar and click New Policy.

Configure Policy

Field	Description
Name	Human-readable name
Type	Policy type (spend limit, time window, etc.)
Priority	0-100 (higher = evaluated first, but never overrides a failing rule)
Description	What this policy does

Add Rules

Define the specific rules for this policy.

Assign to Agents

Select which agents this policy applies to.

Via API

curl -X POST https://conto.finance/api/policies \
  -H "Authorization: Bearer $CONTO_ORG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Daily Spend Limit",
    "description": "Limits daily spending to $1000",
    "policyType": "SPEND_LIMIT",
    "priority": 50,
    "isActive": true
  }'

Policy Properties

Property	Type	Description
`name`	string	Human-readable name
`description`	string	Detailed description
`policyType`	enum	Type of policy
`priority`	number	Evaluation order (0-100), not override precedence
`isActive`	boolean	Whether policy is enforced
`rules`	array	Specific rules for this policy

Assigning Policies

Policies can be assigned to:

Agents - Apply to specific agents
Wallets - Apply to specific wallets
Cards - Apply to specific payment cards

Assign to Card

curl -X POST https://conto.finance/api/cards/{cardId}/policies \
  -H "Authorization: Bearer $CONTO_ORG_API_KEY" \
  -d '{
    "policyId": "cmm5c0pol000l49h7dmsuc11p"
  }'

Assign to Agent

curl -X POST https://conto.finance/api/agents/{agentId}/policies \
  -H "Authorization: Bearer $CONTO_ORG_API_KEY" \
  -d '{
    "policyId": "cmm5c0pol000l49h7dmsuc11p"
  }'

Example: Standard Agent Setup

A typical agent configuration with multiple policies:

[
  {
    "name": "Spend Limits",
    "policyType": "SPEND_LIMIT",
    "priority": 50,
    "rules": [
      { "ruleType": "MAX_AMOUNT", "operator": "LTE", "value": "200", "action": "ALLOW" },
      { "ruleType": "DAILY_LIMIT", "operator": "LTE", "value": "1000", "action": "ALLOW" },
      { "ruleType": "MONTHLY_LIMIT", "operator": "LTE", "value": "10000", "action": "ALLOW" }
    ]
  },
  {
    "name": "Business Hours",
    "policyType": "TIME_WINDOW",
    "priority": 50,
    "rules": [
      {
        "ruleType": "TIME_WINDOW",
        "operator": "BETWEEN",
        "value": "{\"start\": \"09:00\", \"end\": \"18:00\"}",
        "action": "ALLOW"
      },
      {
        "ruleType": "DAY_OF_WEEK",
        "operator": "IN",
        "value": ["Mon", "Tue", "Wed", "Thu", "Fri"],
        "action": "ALLOW"
      }
    ]
  },
  {
    "name": "Trusted Vendors Only",
    "policyType": "COUNTERPARTY",
    "priority": 50,
    "rules": [{ "ruleType": "TRUST_SCORE", "operator": "GTE", "value": "0.6", "action": "ALLOW" }]
  }
]

Best Practices

Layer Your Policies

Create policies at different priority levels to make evaluation and debugging easier:

HIGH (90-100): Security/Compliance (sanctions, blocked addresses)
MEDIUM (40-60): Business Rules (limits, time windows)
LOW (0-20): Defaults (catch-all rules)

Priority changes evaluation order only. It does not let an allow rule override a stricter rule that runs later.

Start Restrictive

Begin with strict policies and relax based on operational needs. Recommended starting limits for new agents:

100/tx,

500/day, $5,000/month.

Day 1: $100/day limit, 3 trusted vendors
Week 2: $500/day, add 5 more vendors
Month 2: $1,000/day, category-based restrictions

Note: Auto-created wallet defaults are higher (daily:

1,000, weekly:

5,000, monthly: $20,000). Override these with policy-level limits for tighter control.

Use Approval Thresholds

Don’t block high-value transactions entirely - require approval:

{
  "policyType": "APPROVAL_THRESHOLD",
  "rules": [
    { "ruleType": "REQUIRE_APPROVAL_ABOVE", "operator": "GREATER_THAN", "value": "500", "action": "REQUIRE_APPROVAL" }
  ]
}

Document Your Policies

Use descriptions to explain policy intent:

{
  "name": "OFAC Compliance",
  "description": "Blocks transactions to OFAC-sanctioned countries. Required for regulatory compliance. Do not modify without legal approval."
}

Available Rule Types

The value formats, operators, and caveats for every rule type live in Advanced Policies. Quick index:

Category	Rule Types
Spend limits	`MAX_AMOUNT`, `DAILY_LIMIT`, `WEEKLY_LIMIT`, `MONTHLY_LIMIT`, `BUDGET_CAP`
Time controls	`TIME_WINDOW`, `DAY_OF_WEEK`, `DATE_RANGE`, `BLACKOUT_PERIOD` (aliases: `MAINTENANCE_WINDOW`, `BLOCKED_TIME_WINDOW`)
Counterparty & address	`ALLOWED_COUNTERPARTIES`, `BLOCKED_COUNTERPARTIES`, `TRUST_SCORE`, `COUNTERPARTY_STATUS`
Category & contract	`ALLOWED_CATEGORIES`, `BLOCKED_CATEGORIES`, `CONTRACT_ALLOWLIST` (aliases: `ALLOWED_CONTRACTS`, `PROTOCOL_ALLOWLIST`)
Geographic & compliance	`GEOGRAPHIC_RESTRICTION`, `VELOCITY_LIMIT`, `REQUIRE_APPROVAL_ABOVE`, `FAIRSCALE_MIN_SCORE`
Card payment	`CARD_MAX_AMOUNT`, `CARD_ALLOWED_MCCS`, `CARD_BLOCKED_MCCS`, `CARD_ALLOWED_MERCHANTS`, `CARD_BLOCKED_MERCHANTS`
x402 protocol	`X402_MAX_PER_REQUEST`, `X402_PRICE_CEILING`, `X402_MAX_PER_ENDPOINT`, `X402_MAX_PER_SERVICE`, `X402_ALLOWED_SERVICES`, `X402_BLOCKED_SERVICES`, `X402_ALLOWED_FACILITATORS`, `X402_VELOCITY_PER_ENDPOINT`, `X402_SESSION_BUDGET`
MPP protocol	`MPP_MAX_PER_REQUEST`, `MPP_PRICE_CEILING`, `MPP_MAX_PER_ENDPOINT`, `MPP_MAX_PER_SERVICE`, `MPP_ALLOWED_SERVICES`, `MPP_BLOCKED_SERVICES`, `MPP_VELOCITY_PER_ENDPOINT`, `MPP_SESSION_BUDGET`, `MPP_MAX_SESSION_DEPOSIT`, `MPP_MAX_CONCURRENT_SESSIONS`, `MPP_MAX_SESSION_DURATION`, `MPP_BLOCK_SESSION_INTENT`
AgentScore commerce	`AGENTSCORE_REQUIRE_VERIFIED`, `AGENTSCORE_ALLOWED_JURISDICTIONS`, `AGENTSCORE_BLOCKED_JURISDICTIONS`

Violation Details

When a payment is denied, detailed violation info is returned:

{
  "status": "DENIED",
  "reasons": ["Would exceed daily limit"],
  "violations": [
    {
      "type": "DAILY_LIMIT",
      "limit": 1000,
      "current": 1150,
      "message": "[Wallet limit] Would exceed daily limit: $-150.00 remaining of $1000 daily limit",
      "source": "wallet_limit"
    },
    {
      "type": "PER_TX_LIMIT",
      "limit": 200,
      "current": 300,
      "message": "[Policy: High-Value Guard] Amount 300 exceeds per-transaction limit of 200",
      "source": "policy_rule",
      "policyName": "High-Value Guard"
    }
  ]
}

Each violation includes a source field indicating whether the denial came from a wallet-level limit ("wallet_limit") or a policy rule ("policy_rule"). Policy rule violations also include policyName.

Engine Architecture

Each rule type is evaluated by a dedicated strategy module. The engine looks up the strategy for a rule’s ruleType from a registry and delegates evaluation. New rule types can be added without modifying the core engine, register a new strategy and update the SKILL.md docs.

Policy Overview

Policy System

What is a Policy?

Policy Types

Spend Limit

Time Window

Counterparty

Geographic

AgentScore Compliance

Category

Contract Allowlist

Approval Threshold

Velocity

Whitelist

x402 Controls

MPP Controls

Budget Allocation

Expiration

Card Payment

Policy Evaluation

Evaluation Order

Evaluation Semantics

Creating Policies

Via Dashboard

Via API

Policy Properties

Assigning Policies

Assign to Card

Assign to Agent

Example: Standard Agent Setup

Best Practices

Available Rule Types

Violation Details

Engine Architecture

Next Steps

Spend Limits

Time Windows

​Policy System

​What is a Policy?

​Policy Types

Spend Limit

Time Window

Counterparty

Geographic

AgentScore Compliance

Category

Contract Allowlist

Approval Threshold

Velocity

Whitelist

x402 Controls

MPP Controls

Budget Allocation

Expiration

Card Payment

​Policy Evaluation

​Evaluation Order

​Evaluation Semantics

​Creating Policies

​Via Dashboard

​Via API

​Policy Properties

​Assigning Policies

​Assign to Card

​Assign to Agent

​Example: Standard Agent Setup

​Best Practices

​Available Rule Types

​Violation Details

​Engine Architecture

​Next Steps

Spend Limits

Time Windows

Policy System

What is a Policy?

Policy Types

Policy Evaluation

Evaluation Order

Evaluation Semantics

Creating Policies

Via Dashboard

Via API

Policy Properties

Assigning Policies

Assign to Card

Assign to Agent

Example: Standard Agent Setup

Best Practices

Available Rule Types

Violation Details

Engine Architecture

Next Steps