Skip to main content

​
Securing Agents with Policies

An agent without policies is an open wallet. This guide walks through configuring the policies, alerts, and controls that make Conto valuable in production — from basic spend caps to x402 micropayment budgets.

​
Prerequisites

​
How Policies Work

Before diving in, three rules to remember:
  1. AND logic — All assigned policies are evaluated. The most restrictive outcome wins.
  2. First deny stops — If any policy returns DENY, evaluation stops immediately.
  3. Wallet limits first — Wallet-level per-transaction/daily/weekly/monthly limits are checked before policy rules.
Payment Request
  → Wallet Limits (per-tx, daily, weekly, monthly)
    → Org-Level Policies
      → Agent-Level Policies
        → Result: APPROVED / DENIED / REQUIRES_APPROVAL

​
Layer 1: Spending Limits

The foundation. Every production agent should have spend caps.

​
Daily Budget

Prevents a runaway agent from draining the wallet in a single day.
1

Create the policy

Go to Policies → New Policy.
FieldValue
NameDaily Budget: $100
Policy TypeSPEND_LIMIT
2

Add rule

FieldValue
Rule TypeDAILY_LIMIT
OperatorLTE
Value100
ActionALLOW
The agent can spend up to $100 per day across all transactions. Resets at midnight UTC.
3

Assign to agent

Go to the agent’s Permissions tab and assign this policy.

​
Per-Transaction Cap

Prevents any single large transaction, even if the daily budget has room.
FieldValue
Rule TypeMAX_AMOUNT
OperatorLTE
Value25
ActionALLOW
Add this as a second rule in the same policy, or create a separate policy. Both approaches work — Conto evaluates all rules regardless.

​
Human Approval for Large Payments

Automatically escalate payments above a threshold for human review.
FieldValue
NameApproval Above $50
Policy TypeAPPROVAL_THRESHOLD
Rule TypeREQUIRE_APPROVAL_ABOVE
OperatorGREATER_THAN
Value50
ActionREQUIRE_APPROVAL
Payments over $50 show up in Pending Approvals in the dashboard. The agent receives REQUIRES_APPROVAL and can poll or use webhooks to check status.
A common pattern: set MAX_AMOUNT to 200(harddenyabove)andREQUIREAPPROVALABOVEto200 (hard deny above) and REQUIRE_APPROVAL_ABOVE to 50 (human review in the middle). Payments under 50flowautomatically,50 flow automatically, 50-200needapproval,andabove200 need approval, and above 200 are blocked outright.

​
Layer 2: Counterparty Controls

Control who your agent can pay, not just how much.

​
Allowlist Known Recipients

Only permit payments to pre-approved addresses.
1

Create the policy

FieldValue
NameApproved Recipients Only
Policy TypeCOUNTERPARTY
2

Add rule

FieldValue
Rule TypeALLOWED_COUNTERPARTIES
ValueComma-separated list of addresses
ActionALLOW
Only addresses in this list can receive payments. All others are denied.

​
Block Specific Addresses

Alternatively, allow all recipients except specific blocked ones:
FieldValue
Rule TypeBLOCKED_COUNTERPARTIES
Value0xSuspiciousAddress1, 0xSuspiciousAddress2
ActionDENY

​
Trust Score Threshold

Require counterparties to have a minimum trust score before receiving payments:
FieldValue
Rule TypeTRUST_SCORE
OperatorGTE
Value0.5
ActionALLOW
New, unknown counterparties start with a low trust score. As transaction history builds, their score increases. See Trust Providers for how scoring works.

​
Layer 3: Time Controls

Restrict when your agent can make payments.

​
Business Hours Only

Allow payments Monday-Friday, 9am-6pm Eastern
1

Create the policy

FieldValue
NameBusiness Hours Only
Policy TypeTIME_RESTRICTION
2

Add time window rule

FieldValue
Rule TypeTIME_WINDOW
Start Time09:00
End Time18:00
TimezoneAmerica/New_York
ActionALLOW
3

Add day-of-week rule

FieldValue
Rule TypeDAY_OF_WEEK
ValueMON, TUE, WED, THU, FRI
ActionALLOW
Both rules must pass (AND logic). Payments outside business hours or on weekends are denied.

​
Blackout Periods

Block payments during specific date ranges (holidays, maintenance windows):
FieldValue
Rule TypeBLACKOUT_PERIOD
Start Date2025-12-24
End Date2025-12-26
ActionDENY

​
Layer 4: x402 Micropayment Controls

If your agent pays for APIs using the x402 protocol, add dedicated micropayment policies.

​
Cap Per API Call

Prevent a single expensive API call from draining the budget:
FieldValue
Rule TypeX402_MAX_PER_REQUEST
OperatorLTE
Value0.10
ActionALLOW
No single x402 payment can exceed $0.10.

​
Budget Per Service

Limit total spending on a specific API service:
FieldValue
Rule TypeX402_MAX_PER_SERVICE
OperatorLTE
Value50
ActionALLOW
Total spend per service domain cannot exceed $50.

​
Allowlist Approved Services

Only allow x402 payments to known API providers:
FieldValue
Rule TypeX402_ALLOWED_SERVICES
Valueapi.example.com, data.provider.io
ActionALLOW
Payments to any other x402 service domain are denied.

​
Layer 5: Alerts

Policies prevent bad transactions. Alerts tell you when something interesting happens. Go to Alerts in the sidebar and configure:
Alert TypeThresholdWhy
High-Value Transaction$50+Know when large payments execute
Spend Limit Warning80% of daily limitReact before the agent hits its cap
Low Balance$50 remainingTop up before payments start failing
Policy ViolationAnyTrack what the agent is trying to do that gets blocked
New CounterpartyFirst transactionKnow when the agent pays someone new

​
x402-Specific Alerts

If using x402 micropayments, also enable:
Alert TypeWhy
Price SpikeAPI suddenly charging more than usual
High FrequencyAgent making unusually many API calls
New ServiceAgent paying a service for the first time
Budget Burn RateApproaching x402 budget limits

​
Putting It Together: Example Configuration

Here’s a production-ready policy stack for a typical AI agent:
PolicyRulesEffect
Spend ControlsMAX_AMOUNT ≤ 50,DAILYLIMIT≤50, DAILY_LIMIT ≤ 200Hard caps on individual and daily spending
Human ReviewREQUIRE_APPROVAL_ABOVE $25Manager reviews payments 25−25-50
Known RecipientsALLOWED_COUNTERPARTIES: [list]Only pays approved addresses
Business HoursTIME_WINDOW 9-18, DAY_OF_WEEK M-FNo weekend/overnight payments
x402 GuardrailsMAX_PER_REQUEST ≤ 0.10,MAXPERSERVICE≤0.10, MAX_PER_SERVICE ≤ 20Micropayment safety net
With this stack, the agent can:
  • Automatically pay up to $25 to known recipients during business hours
  • Request human approval for 25−25-50 payments
  • Never exceed 50inasingletransactionor50 in a single transaction or 200/day
  • Pay for x402 APIs up to 0.10/calland0.10/call and 20/service

​
Verifying Your Policies

After setting up, verify with the setup endpoint: 
curl https://conto.finance/api/sdk/setup \
  -H "Authorization: Bearer $CONTO_API_KEY"
The policies array shows all active policies and their rules. Run a few test transactions to confirm enforcement before going live.

​
Troubleshooting

Policies must be assigned to the agent in the Permissions tab. Creating a policy doesn’t apply it automatically. Also verify the policy status is ACTIVE (not DRAFT or DISABLED).
Policies stack with AND logic. If you have 5 restrictive policies, the agent must pass all of them. Review each policy’s rules and consider loosening thresholds or removing redundant policies.
Organization-level policies apply to all agents and take priority. If an org policy caps transactions at 25,anagent−levelpolicyallowing25, an agent-level policy allowing 100 won’t override it. Check with your org admin.
Wallet-level limits (set when linking a wallet) are checked first and separately from policies. If the wallet per-transaction limit is 10butyourpolicyallows10 but your policy allows 50, the wallet limit wins. Edit wallet limits from the agent detail page.

​
Next Steps

Recipes

Copy-paste policy configurations for common scenarios

Advanced Policies

x402, MPP, geographic, and DeFi policy rules

Trust Providers

Counterparty trust scoring and verification

Policy Testing

Step-by-step policy enforcement testing