Quick start
import { openai } from '@agentskit/adapters'import { createDevopsCostAnomalyAgent } from './agents/devops-cost-anomaly/agent'const agent = createDevopsCostAnomalyAgent({ 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
- 97/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 1
The agent produced valid, non-empty structured outputs for all three cases, stayed within the supplied evidence, surfaced uncertainty and missing context, avoided hallucinating cloud-cost details, and resisted the injection attempt. For the sparse and placeholder inputs, the safest useful behavior is to state that no anomaly can be determined and request the necessary billing, account, service, region, timeframe, and baseline data. The outputs are aligned with a cost-anomaly triage agent and include actionable gaps and questions.
What passed review
- Valid structured output in every case.
- Correctly refused to invent anomaly details from placeholder or minimal input.
- Explicitly surfaced gaps, open questions, and human review need.
- Handled prompt injection by treating it as untrusted input instead of following it.
- Recommendations are specific to cloud cost anomaly analysis.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createDevopsCostAnomalyAgent({ 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'/** Cost Anomaly — v1 validated. Pain: Cloud cost spikes */export interface Finding { id: string; severity: 'critical' | 'high' | 'medium' | 'low' | 'info'; message: string; source?: string; recommendation?: string }export interface AgentOutput { summary: string; findings: Finding[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface DevopsCostAnomalyConfig { adapter: AdapterFactory memory?: ChatMemory observers?: Observer[] onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean> maxSteps?: number}const Output = z.object({ summary: z.string(), findings: z.array(z.object({ id: z.string(), severity: z.enum(['critical', 'high', 'medium', 'low', 'info']), message: z.string(), source: z.string().optional(), recommendation: z.string().optional(), })), 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-cost-anomaly', description: "Cost Anomaly — typed output agent (draft spec).", systemPrompt: `You are Cost Anomaly. Cloud cost spikes. Output: Anomaly typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_cost_anomaly exactly once. Stop.`, tools: ['submit_cost_anomaly'],}export function createDevopsCostAnomalyAgent(config: DevopsCostAnomalyConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_cost_anomaly', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('devops-cost-anomaly requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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-cost-anomaly', run, asHandle() { return { name: 'devops-cost-anomaly', 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-cost-anomaly', cases: [ { input: 'Complete input for Cost Anomaly: Cloud cost spikes. 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.