> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ai-stats.phaseo.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Support triage with presets and guardrail-aware failures

> Run a preset-driven support triage agent that returns strict JSON, pauses high-risk cases for review, and keeps guardrail failures visible.

Use this recipe when one support workflow should:

* inherit routing and prompt defaults from a dashboard preset
* return strict structured output
* pause risky cases for human review
* keep gateway failures visible in logs instead of hiding them inside agent code

## 1. Start with a preset

Create a preset such as `support-triage` that owns:

* the default routed model or router target
* provider preferences
* the support-system prompt
* stable decoding parameters

That keeps the agent code focused on workflow control instead of duplicating request policy.

## 2. Define a narrow triage contract

```ts theme={null}
type SupportTriageDecision = {
  queue: "billing" | "reliability" | "product" | "security";
  severity: "low" | "medium" | "high";
  needsHumanReview: boolean;
  summary: string;
};
```

Keep the first output shape small enough that operators can inspect it quickly.

## 3. Create the preset-driven agent

```ts theme={null}
import { createAgent } from "@ai-stats/agent-sdk";

const supportTriageAgent = createAgent<string, SupportTriageDecision>({
  id: "support-triage-agent",
  preset: "support-triage",
  parseOutput(text) {
    return JSON.parse(text) as SupportTriageDecision;
  },
  humanReview: ({ parsedOutput }) =>
    parsedOutput?.needsHumanReview
      ? {
          reason: "support_triage_review_required",
          payload: parsedOutput,
        }
      : null,
});
```

The SDK resolves `preset: "support-triage"` to the gateway alias form `@support-triage`.

## 4. Configure the gateway-backed adapter

Use adapter defaults for the parts that should stay fixed across every triage run:

```ts theme={null}
import {
  createGatewayAgentClient,
} from "@ai-stats/agent-sdk";

const client = createGatewayAgentClient({
  clientOptions: {
    apiKey: process.env.AI_STATS_API_KEY!,
  },
  responseFormat: {
    type: "json_schema",
    name: "support_triage_decision",
    schema: {
      type: "object",
      properties: {
        queue: {
          type: "string",
          enum: ["billing", "reliability", "product", "security"],
        },
        severity: {
          type: "string",
          enum: ["low", "medium", "high"],
        },
        needsHumanReview: { type: "boolean" },
        summary: { type: "string" },
      },
      required: ["queue", "severity", "needsHumanReview", "summary"],
      additionalProperties: false,
    },
  },
  plugins: [{ id: "response-healing", mode: "strict" }],
});
```

## 5. Run the workflow with bounded retries

```ts theme={null}
const result = await supportTriageAgent.run({
  input: "Customer says webhook deliveries failed overnight and asks whether data was lost.",
  client,
  modelRetry: {
    maxRetries: 2,
    backoffMs: 250,
  },
  onEvent(event) {
    console.log(event.type, event.runId, event.attempt);
  },
});
```

If the run pauses for review, resume it explicitly:

```ts theme={null}
if (result.run.status === "waiting_for_human") {
  const continued = await supportTriageAgent.continueRun({
    run: result,
    client,
    humanInput: "Approved. Finalize the triage decision.",
  });

  console.log(continued.output);
}
```

## 6. Treat gateway failures as operational events

Do not hide failures by swallowing them inside the agent callback chain.

Instead, catch `AgentGatewayError` explicitly:

```ts theme={null}
import { AgentGatewayError } from "@ai-stats/agent-sdk";

try {
  await supportTriageAgent.run({
    input: "Customer says webhook deliveries failed overnight and asks whether data was lost.",
    client,
    store,
  });
} catch (error) {
  if (error instanceof AgentGatewayError) {
    console.error("Gateway request failed", {
      status: error.status,
      requestId: error.requestId,
      generationId: error.generationId,
      reason: error.reason,
      providerFailureDiagnostics: error.providerFailureDiagnostics,
      routingDiagnostics: error.routingDiagnostics,
    });
  }
  throw error;
}
```

Then:

1. let the runtime persist `failed` run and step state
2. inspect `loaded.run.errorDetails` or `loaded.steps[n].errorDetails` on later recovery paths when the original exception is no longer in memory
3. inspect the request details for:
   * guardrail enforcement
   * routing details
   * plugin execution
   * request ids and provider data

That is especially important when:

* a guardrail blocks the request
* the preset allowlist rejects the requested model
* provider credentials or enablement filters remove the routed candidate set
* response healing fails to recover schema-valid JSON

## 7. What to verify

After one successful run and one intentionally risky run, confirm:

* the request detail view shows the preset-driven request target
* high-risk cases pause in `waiting_for_human`
* retrying model steps persist `modelAttempts`
* guardrail or preset failures remain visible in request details, not hidden inside agent exceptions

## Related guides

* [TypeScript Agent SDK](../sdk-reference/typescript/agent-sdk.mdx)
* [Presets](../guides/presets.mdx)
* [Routing and fallbacks](../guides/routing-and-fallbacks.mdx)
* [Validate structured outputs](../guides/structured-outputs-validation.mdx)
* [Roll out presets and debug routing](./preset-rollout-and-routing-debug.mdx)
* [Recover malformed structured JSON](./response-healing-for-structured-json.mdx)
* [Build a durable agent loop in TypeScript](./agent-sdk-durable-loop.mdx)