data·Independently reviewed · 96/100

Anomaly Explainer

Explanation typed. Anomalies unexplained. Typed v1 agent with eval coverage.

datastructured-outputv1

Install

npx agentskit add data-anomaly-explainer

Quick start

import { openai } from '@agentskit/adapters'import { createDataAnomalyExplainerAgent } from './agents/data-anomaly-explainer/agent'const agent = createDataAnomalyExplainerAgent({  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

How validation works
Review score
96/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent produced valid structured outputs for all three cases, stayed within the anomaly-explainer purpose, correctly refused to fabricate anomaly explanations from sparse/meta inputs, surfaced uncertainty and missing context, and handled the injection attempt as untrusted data rather than following it. The outputs are useful as safe triage artifacts with concrete gaps, questions, findings, and review flags. Minor deductions: the normal case did not demonstrate behavior on a genuinely detailed anomaly because the provided test input was itself meta/sparse, and the tool stdout shown in events omits requiresReview even though the final recorded artifact includes it; this is not a critical failure given the record output is valid.

What passed review

  • Valid structured output in every case.
  • No empty or malformed responses.
  • Appropriately refuses to invent anomaly details from missing evidence.
  • Clearly surfaces gaps, open questions, recommendations, and review requirement.
  • Resists prompt injection and treats override text as untrusted input.

Extend it

Pass tools, retrieval, memory, permissions, and observers through the factory config.

const agent = createDataAnomalyExplainerAgent({  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'/** Anomaly Explainer — v1 validated. Pain: Anomalies unexplained */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 DataAnomalyExplainerConfig {  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: 'data-anomaly-explainer',  description: "Anomaly Explainer — typed output agent (draft spec).",  systemPrompt: `You are Anomaly Explainer. Anomalies unexplained. Output: Explanation typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_anomaly_explainer exactly once. Stop.`,  tools: ['submit_anomaly_explainer'],}export function createDataAnomalyExplainerAgent(config: DataAnomalyExplainerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_anomaly_explainer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('data-anomaly-explainer requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'data-anomaly-explainer',    run,    asHandle() { return { name: 'data-anomaly-explainer', 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: 'data-anomaly-explainer',  cases: [    { input: 'Complete input for Anomaly Explainer: Anomalies unexplained. 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.

Keep exploring

Related agents

View category