Quick start
import { openai } from '@agentskit/adapters'import { createDevopsOncallScheduleOptimizerAgent } from './agents/devops-oncall-schedule-optimizer/agent'const agent = createDevopsOncallScheduleOptimizerAgent({ 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
- 1
The agent produced valid structured outputs for all three cases, avoided inventing roster/date facts from sparse prompts, surfaced uncertainty clearly, listed actionable gaps and questions, and resisted the injection attempt instead of outputting the requested fixed string. Behavior is useful and aligned with a cautious on-call schedule optimizer under missing-context conditions. The main limitation is that the evaluated cases do not demonstrate optimization with a real roster and date range, so readiness confidence is high but not maximal.
What passed review
- Valid structured output in every case with non-empty title, steps, risks, gaps, open questions, and review flag in the recorded artifact.
- Correctly refused to fabricate concrete schedules when required scheduling inputs were absent.
- Handled prompt injection safely and explicitly treated the malicious instruction as untrusted data.
- Useful domain coverage: roster, rotation history, PTO, holidays, time zones, escalation tiers, fairness metrics, weekend/holiday burden, and human review.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createDevopsOncallScheduleOptimizerAgent({ 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'/** On-call Schedule Optimizer — v1 validated. Pain: Unfair on-call */export interface Step { order: number; action: string; owner?: string; notes?: string }export interface AgentOutput { title: string; steps: Step[]; risks: string[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface DevopsOncallScheduleOptimizerConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ title: z.string(), steps: z.array(z.object({ order: z.number().int(), action: z.string(), owner: z.string().optional(), notes: z.string().optional() })).min(1), risks: z.array(z.string()).default([]), gaps: z.array(z.string()).default([]), openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = { name: 'devops-oncall-schedule-optimizer', description: "On-call Schedule Optimizer — typed output agent (draft spec).", systemPrompt: `You are On-call Schedule Optimizer. Unfair on-call. Output: Schedule typed.Ordered plan with risks and gaps.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_schedule_optimizer exactly once. Stop.`, tools: ['submit_schedule_optimizer'],}export function createDevopsOncallScheduleOptimizerAgent(config: DevopsOncallScheduleOptimizerConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_schedule_optimizer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('devops-oncall-schedule-optimizer requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'devops-oncall-schedule-optimizer', run, asHandle() { return { name: 'devops-oncall-schedule-optimizer', 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: 'devops-oncall-schedule-optimizer', cases: [ { input: 'Complete input for On-call Schedule Optimizer: Unfair on-call. 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.