> ## Documentation Index
> Fetch the complete documentation index at: https://backstop.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Platform capabilities

> Every TrueFoundry and AWS Bedrock capability Backstop uses — and where it lives.

Backstop is built to exercise the **full TrueFoundry AI Gateway surface over AWS Bedrock** — not one feature deeply, but the whole platform, end to end. Every capability below is wired through the platform and verifiable in a run; none is faked.

## At a glance

| Capability                             | How Backstop uses it                                                                                                                                              | Where                        |
| -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------- |
| **AI Gateway**                         | Every diagnosis call routes through the gateway via the OpenAI SDK pointed at the gateway base URL.                                                               | `prod-triage` virtual model  |
| **Virtual Models — priority fallback** | One virtual model with a four-hop chain: **Claude Sonnet → Llama 4 Maverick → Amazon Nova Pro → Claude Haiku**, with retry/fallback on `401/403/404/408/429/5xx`. | gateway config               |
| **Rate-limit policy**                  | A limit on the primary target so a live run visibly fails Sonnet over to Llama.                                                                                   | gateway policy               |
| **Budget / cost policy**               | A daily spend cap across the chain.                                                                                                                               | gateway policy               |
| **Observability**                      | `X-TFY-LOGGING-CONFIG` on every call → request traces, fallback events, and per-model cost in AI Monitoring.                                                      | gateway                      |
| **MCP Gateway — official remote MCP**  | On resolution, the agent files an incident ticket in **Linear** through a curated virtual MCP server.                                                             | `backstop-notify`            |
| **MCP Gateway — custom MCP server**    | A read-only "infra" MCP server exposes live cluster signals (`get_signals`, `deployment_status`, `namespaces`) over streamable-http.                              | `backstop-infra`             |
| **MCP — tool scoping / toggling**      | Destructive Linear tools are toggled off; only ticket creation is exposed.                                                                                        | virtual MCP                  |
| **Guardrails — native**                | **Secrets Detection** + **PII/PHI** redaction on the input hook, masking credentials before the model sees them.                                                  | input hook                   |
| **Guardrails — custom**                | A hosted guardrail validates the model's diagnosis on the output hook.                                                                                            | output hook · `/tfy/quality` |
| **Prompts registry**                   | The diagnosis system prompt is versioned in the registry and fetched at runtime (with a local fallback).                                                          | prompt FQN                   |
| **AWS Bedrock**                        | Foundation models (Claude, Llama, Nova) served through Bedrock's managed inference, proxied by the gateway.                                                       | provider                     |

## What this demonstrates

<CardGroup cols={2}>
  <Card title="AI Gateway" icon="bolt">
    Routing, the priority fallback chain, rate-limit and budget policies, and full request tracing in AI Monitoring.
  </Card>

  <Card title="MCP Gateway" icon="plug">
    Scoped, audited tool access — an official remote MCP (Linear) and a custom read-only infra MCP, with destructive tools removed.
  </Card>

  <Card title="Guardrails" icon="shield-halved">
    Native Secrets + PII redaction on the way in, a custom groundedness check on the way out, plus in-agent gates that block destructive actions.
  </Card>

  <Card title="Auditability" icon="receipt">
    Every run emits a tamper-evident receipt — every model, fallback, guardrail decision, and action, with a recomputable hash.
  </Card>
</CardGroup>

In-agent logic — the groundedness and action gates, the LLM-as-judge, and the cascade circuit breaker — sits on top of the platform as defense-in-depth. See [Guardrails](/guardrails) and [Resilience](/resilience).