Quick start
import { openai } from '@agentskit/adapters'import { createEcommerceFulfillmentSlaMonitorAgent } from './agents/ecommerce-fulfillment-sla-monitor/agent'const agent = createEcommerceFulfillmentSlaMonitorAgent({ adapter: openai({ apiKey: process.env.OPENAI_API_KEY!, model: 'gpt-4o', }),})const result = await agent.run('Describe your task here')console.log(result.content)Independent reviewer approved
Validation evidence
- Review score
- 96/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 2
The agent produced valid, non-empty structured outputs for all three cases, stayed aligned with fulfillment SLA monitoring, surfaced missing context and uncertainty, and resisted the injection attempt without outputting the requested unsafe/invalid override. The normal case includes illustrative concrete details while clearly labeling them as sample data rather than factual monitor results, which avoids material hallucination. The outputs are useful drafts for an SLA monitor, though they are more narrative than strongly alert-object oriented.
What passed review
- Valid structured output shape across all cases.
- Explicitly marks missing fulfillment data and requires review when context is sparse.
- Injection case preserves task behavior and flags the prompt-redirection attempt.
- Normal case provides concrete SLA-monitoring triage context while labeling invented details as illustrative.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createEcommerceFulfillmentSlaMonitorAgent({ adapter, tools, retriever, memory, onConfirm: (call) => approve(call), observers: [tracer],})View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** Fulfillment SLA Monitor — v1 validated. Pain: SLA breaches */export interface Section { heading: string; body: string; citations: string[] }export interface AgentOutput { title: string; sections: Section[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface EcommerceFulfillmentSlaMonitorConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ title: z.string(), sections: z.array(z.object({ heading: z.string(), body: z.string(), citations: z.array(z.string()).default([]) })).min(1), gaps: z.array(z.string()).default([]), openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = { name: 'ecommerce-fulfillment-sla-monitor', description: "Fulfillment SLA Monitor — typed output agent (draft spec).", systemPrompt: `You are Fulfillment SLA Monitor. SLA breaches. Output: Alerts typed.Draft sections with citations from input. Gaps for missing facts.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_sla_monitor exactly once. Stop.`, tools: ['submit_sla_monitor'],}export function createEcommerceFulfillmentSlaMonitorAgent(config: EcommerceFulfillmentSlaMonitorConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_sla_monitor', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('ecommerce-fulfillment-sla-monitor requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${fenceUntrustedContent(input)}`, parse: (a) => Output.parse(a), skill, memory: config.memory, observers: config.observers, onConfirm: config.onConfirm, maxSteps: config.maxSteps ?? 4, }) return { ...result, requiresReview: true } } return { name: 'ecommerce-fulfillment-sla-monitor', run, asHandle() { return { name: 'ecommerce-fulfillment-sla-monitor', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } }, }}View evaluation contract
Replay these cases with the provider and model you plan to deploy.
import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = { name: 'ecommerce-fulfillment-sla-monitor', cases: [ { input: 'Complete input for Fulfillment SLA Monitor: SLA breaches. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) }, { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 }, { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) }, { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 }, ],}Was this agent useful?
Your response helps us prioritize agent quality.