Skip to main content

Quickstart

End-to-end setup on Tempo Testnet. By the end you’ll have a Conto organization, an AI agent, a funded testnet wallet, two test policies, and a verified onchain payment. Total time: about 10 minutes. No real funds required.

What you’ll build

A Conto organization with your account
An AI agent connected in Conto
A Tempo Testnet wallet funded with pathUSD
Spending policies that approve, require approval, or deny payments
A verified test payment on Tempo Testnet

Why Tempo Testnet?

Tempo Testnet pays transaction fees in pathUSD itself, so you don’t need a separate gas token. Combined with free faucet funds, it’s the fastest way to test the full flow.

Alternate path: CLI-first setup

Prefer the command line? The CLI can create the agent, wallet, starter policy, SDK key, and local example for you:
For CI or autonomous agent runs, use the sandbox JSON mode:
Then verify the generated project and run its example:
Use the dashboard/API steps below when you want to see or customize each resource yourself. For the full command reference, see CLI quickstart.

Choose Your Key Up Front

Most developers need both of these at different points in the integration:
If your app provisions agents for end users, create the agent with an org API key first, then hand the agent its own SDK key for runtime payment calls.

Step 1. Create your account

  1. Visit conto.finance and sign up with your name, email, password, and an organization name. The organization is the top-level container for agents, wallets, and policies.
  2. Verify your email using the link we send you, then sign in. Sign-in is blocked until the email is verified.

Step 2. Create and fund a wallet

1

Create the wallet

Sidebar > Wallets > Create Wallet.Conto assigns the onchain address as soon as the wallet is created; the dialog shows it immediately.
After creation, the dialog offers an inline Assign to Agent step. You can skip it for now. Step 4 links the wallet from the agent’s side.
2

Fund with the faucet

On the wallet card, open the menu and click Fund Wallet, then Request Testnet Tokens. Free testnet pathUSD arrives in seconds.
For Sponge-managed custody, smart-contract wallets, or importing an existing external wallet (watch-only), see Custody modes.

Step 3. Connect an agent

1

Open Agents

Sidebar > Agents > Connect Agent.
2

Fill in details

Owner, Environment, and Risk Tier are pre-filled with sensible defaults.
3

Connect

Click Connect Agent. The agent starts in ACTIVE status.
Connect Agent is a short wizard: after the details step it offers to link a funding wallet and assign policies inline. Completing those there is equivalent to Steps 4 and 6 below.
Via API: If you create agents through the API, every agent gets an owner. Omit ownerMembershipId and Conto assigns the organization’s highest-priority member (owner first). To pick a specific owner, first fetch one stable membership id for your org:
Pick members[].id for the org member or service account that should own the agent, then create the agent:
Valid agentType values: OPENAI_ASSISTANT, ANTHROPIC_CLAUDE, LANGCHAIN, AUTOGPT, CUSTOM. Agent statuses: ACTIVE, PAUSED, SUSPENDED, REVOKED.
1

Link the wallet

Open the agent detail page. In the Wallets tab, click Link Wallet and pick the Tempo Testnet wallet.
2

Set spending limits

Recommended for the quickstart:
Don’t use Per Transaction 0 as a kill switch. Wallet-level spend limits treat 0 as unlimited. Use a positive limit for a cap, or suspend the agent when you need to block spend.
Default limits, time windows, and other agent-wallet link defaults are listed on the Defaults page.

Step 5. Generate an SDK key

1

Open SDK Integration

On the agent detail page, click the SDK Integration tab.
2

Generate the key

Click Generate SDK Key. Name it (e.g. Testnet Key). Keep the default expiration (1 year) and the default Standard key type. Standard keys cover everything in this guide: they include payments:request for policy evaluation and payments:execute for Step 8’s POST /api/sdk/payments/{requestId}/execute call. Reserve Admin keys for agents that also manage agents, wallets, or policies.
3

Store the key immediately

The full key is shown once. Save it to your environment:
For scopes and key types (standard vs admin), see Authentication. Verify the setup:
You should see:
  • agent.status is "ACTIVE"
  • wallets contains your Tempo Testnet wallet with a balance
  • scopes includes payments:request and payments:execute (both are part of the standard preset)

Step 6. Create two test policies

These two policies together produce three different payment outcomes:

Policy A: spend limit

1

Create the policy

Sidebar > Policies > Create Policy.
2

Set the limit

Set Max Transaction ($) to 15. Leave the daily, weekly, and monthly fields empty.The Rules to be created preview shows the generated rule: MAX_AMOUNT / LTE / 15 / ALLOW. Amounts at or under $15 pass; anything above is denied.

Policy B: approval threshold

1

Create the policy

Sidebar > Policies > Create Policy.
2

Set the threshold

Set Require Approval Above ($) to 10.The generated rule is REQUIRE_APPROVAL_ABOVE / GREATER_THAN / 10 / REQUIRE_APPROVAL: anything over $10 pauses for human approval.

Assign both to the agent

Open the agent detail page > Permissions tab > Assign Policy > assign Test Spend Limit and Test Approval Threshold. Policies combine with AND logic. The most restrictive outcome wins. Higher priority numbers evaluate first (default priority is 50).

Step 7. Run three test transactions

With both policies active you should see three different outcomes:

Test 1. $5 should be APPROVED

Response: "status": "APPROVED", "currency": "pathUSD".

Test 2. $12 should REQUIRE_APPROVAL

Response: "status": "REQUIRES_APPROVAL" with a violation referencing the approval threshold.

Test 3. $20 should be DENIED

Response: "status": "DENIED" with a violation referencing the spend limit.

Step 8. Execute the approved payment

This step uses the payments:execute scope, which your standard SDK key already includes. Capture the requestId from the approved request instead of copy-pasting it. Approved requests expire after 5 minutes, so re-requesting like this always gives you a fresh id. This re-runs Test 1 and saves the id with jq:
Then execute it:
The response includes:

Step 9. Same flow via the SDK

For one-call request + execute, set autoExecute: true on the request. The response comes back with status EXECUTED and an execution object carrying txHash and explorerUrl. It works with any key that has payments:execute, which the standard preset includes.

Verify in the dashboard

After Step 8:
  1. Dashboard > Transactions. The transaction shows Confirmed; open it to see the network (Tempo Testnet) and the explorer link.
  2. Click the explorer link to verify onchain.
  3. Analytics > Audit Trail tab. See the full policy evaluation trail.
You’ve verified policy enforcement and made a real onchain payment on Tempo Testnet.

Troubleshooting

Wallet-level per-transaction limit 0 means unlimited. Edit the wallet limits on the agent detail page and set a positive cap, or suspend the agent if all payments should stop.
Policies combine with AND logic. If one policy denies while another requires approval, the denial wins. Check the Permissions tab for every assigned policy.
The testnet wallet needs funding. On the wallet card, click Fund Wallet > Request Testnet Tokens.
Invalid or expired SDK key. Generate a new one from the agent detail page.

Moving to production

Once the testnet flow works:
  1. Create a production wallet on Tempo Mainnet (USDC.e), Base (USDC), or Solana (USDC).
  2. Fund it with real stablecoins.
  3. Link the production wallet to your agent with production-sized limits.
  4. Update or create production policies. The test policies can remain for reference.
Your SDK integration code does not change. Only the wallet and chain change.

Next steps

Agent sandbox quickstart

Let an autonomous agent create a test-mode sandbox without human signup

Connect your framework

OpenAI, Claude, LangChain, Python integration snippets

SDK payments reference

Full method signatures, options, error model

Policy overview

Every policy type and rule type

Defaults

Every default value in one place