> ## Documentation Index
> Fetch the complete documentation index at: https://cobo.com/products/agentic-wallet/manual/llms.txt
> Use this file to discover all available pages before exploring further.

# What is a pact

> A pact is a structured delegation agreement between you and your agent — with intent, execution plan, policies, and completion conditions. Enforced by infrastructure, not trust.

## The core idea

Before your agent touches a single token, you set the terms. That's a pact.

In Cobo Agentic Wallet, a pact is a structured delegation agreement between you and your agent. It defines what the agent is authorized to do and enforces those boundaries automatically — at the infrastructure level, not by trusting the agent to follow rules.

Your agent operates within the pact. It cannot go around it — not even if it's compromised.

## Four elements of a pact

Every pact consists of four elements:

| Element                   | What it defines                                                                        | Example                                                              |
| ------------------------- | -------------------------------------------------------------------------------------- | -------------------------------------------------------------------- |
| **Intent**                | The job the agent is being authorized to carry out                                     | "Execute a DCA strategy on Base"                                     |
| **Execution plan**        | A reviewable plan for how the agent intends to carry out that job                      | "Swap USDC → ETH on Uniswap every Monday at 9am"                     |
| **Policies**              | Budgets, approvals, allowlists, chain/token/contract constraints, and other guardrails | "Max \$200 per transaction, only Uniswap on Base, only USDC and ETH" |
| **Completion conditions** | What triggers automatic completion and revocation                                      | "Complete after \$3,000 total spent or 30 days elapsed"              |

When a completion condition is met, access revokes automatically. No zombie permissions. No forgotten API keys.

## How a pact works

See it end-to-end: [Pact flow](/products/agentic-wallet/manual/start-here/pact-flow).

<Steps>
  <Step title="Your agent submits a pact">
    The agent declares its intent, proposes an execution plan, proposes the policies that should govern execution, and specifies completion conditions. You see a plain-language summary alongside the full details.
  </Step>

  <Step title="You review and approve">
    You review the pact in the Cobo Agentic Wallet app. You can approve it as-is, adjust the policies or completion conditions, or reject it. No access is granted until you explicitly approve.
  </Step>

  <Step title="Your agent operates within boundaries">
    Once approved, every transaction the agent submits is checked against the pact's policies before execution. The agent cannot exceed its authorized operations — enforcement is architectural, not best-practice.
  </Step>

  <Step title="The pact completes automatically">
    When a completion condition is met — time elapsed, budget exhausted, or job done — the pact ends and all access revokes instantly. Your agent's next API call returns an authentication error, unless it submits a new pact. Clean exit, every time.
  </Step>
</Steps>

## A pact isn't a leash — it's a license

A pact doesn't restrict your agent. It empowers it.

Without a pact, an agent either has unrestricted access (dangerous) or no access at all (useless). A pact gives your agent a clear operating mandate — "here's what you're authorized to do, here are the guardrails, here's when it ends" — and the infrastructure guarantees those boundaries hold.

Think of it like a corporate expense card — but with a compliance department that cannot be fired, bribed, or overridden. Not even by the agent itself. When the project is over, the card shreds itself. That compliance department? It's the pact.

## Enforced by infrastructure, not trust

The critical difference between a pact and a conventional access-control system: **enforcement is structural**.

* The agent's credentials cannot modify pact policies — credential separation is architectural
* Policy limits use atomic reservation with sliding-window counters — no race conditions, no workarounds
* When a pact ends, the API key is invalidated server-side instantly — there is no grace period

You don't need to trust your agent. You need to set a pact.

## Further reading

* [How pacts work](/products/agentic-wallet/manual/security/pact-mechanism) — the full technical specification: PactSpec fields, state machine, pact-scoped API keys
* [The policy engine](/products/agentic-wallet/manual/security/policy-engine) — how every agent operation is evaluated before execution
* [Spend limits](/products/agentic-wallet/manual/security/spend-limits) — how per-transaction and rolling limits are configured and enforced
* [Freeze and revoke](/products/agentic-wallet/manual/security/freeze-revoke) — how to immediately terminate agent access