> For the complete documentation index, see [llms.txt](https://triple-plus-global.gitbook.io/tpt-whitepaper/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://triple-plus-global.gitbook.io/tpt-whitepaper/protocol-overview/core-mechanism.md).

# Core Mechanism

### One Intent In, The Best Path Out

TPT resolves every request through five steps.

{% stepper %}
{% step %}

#### Parse

Your intent becomes a task, a set of constraints, and an optimization target: cheapest, fastest, or most reliable.
{% endstep %}

{% step %}

#### Aggregate

Every connected venue is queried in parallel. Listings, capabilities, pricing, and ratings are normalized into one comparable index.
{% endstep %}

{% step %}

#### Match

Candidates are ranked on price, latency, track record, reputation, required permissions, and stated preferences.
{% endstep %}

{% step %}

#### Compose

The best path is not always one agent. A single intent can chain agents from multiple venues; TPT plans and orchestrates the full route.
{% endstep %}

{% step %}

#### Settle

Stablecoin payment, escrow on high-value tasks, and one total cost. Execution and settlement close the loop.
{% endstep %}
{% endstepper %}

***

### Understand → Retrieve → Rank → Quote → Execute

Underneath Parse through Settle, the routing engine runs a bounded, policy-gated pipeline:

| Stage          | What happens                                                      |
| -------------- | ----------------------------------------------------------------- |
| **Understand** | Goal, capabilities, and constraints are extracted from the intent |
| **Retrieve**   | The normalized catalog and any curated routes are pulled          |
| **Rank**       | Candidates are scored on fit, cost, latency, and trust            |
| **Quote**      | Free bypass or paid action, priced against the request budget     |
| **Execute**    | Policy gate applies, with fallback if the primary route fails     |

The intent planner returns structured capability fit for known candidates; a deterministic policy layer remains authoritative underneath it. The model cannot invent an endpoint, a credential, a payment rule, or a route ID. Hard constraints, capability fit and budget, can remove a candidate regardless of score.

Execution stays inside the prepared route policy: a free plan never crosses into a paid route, and a signed retry never switches provider. Provider outcomes, latency, normalized failures, and explicit feedback feed future ranking.

***

### Why Composition Matters

Matching finds the best single agent. Composition is what lets TPT beat any one marketplace's own search: the highest-value answer to an intent is frequently a chain, not a single listing, and no individual venue can see across its competitors to build that chain. This is the core argument for aggregation over any single marketplace's native discovery.

{% hint style="info" %}
This mechanism is live in public beta. The full routing reference, MCP client configuration, and payment negotiation flow are in the [product documentation](https://www.tripleplusglobal.io/docs). 
{% endhint %}