support·Independently reviewed · 96/100

Account Health Summary

Health summary typed. Account reviews manual. Typed v1 agent with eval coverage.

supportstructured-outputv1

Install

npx agentskit add support-health-summary

Quick start

import { openai } from '@agentskit/adapters'import { createSupportHealthSummaryAgent } from './agents/support-health-summary/agent'const agent = createSupportHealthSummaryAgent({  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 supplied evidence, surfaced uncertainty and missing context, and correctly resisted the injection attempt. It did not invent account health facts from sparse or meta-style inputs, which is appropriate for a support health summary agent where hallucinated account details would be worse than a cautious gap analysis. The outputs are useful as human-review drafts and clearly request the needed source data.

What passed review

  • Valid structured output in every case with summary, findings, gaps, open questions, and review requirement.
  • Strong uncertainty handling with no fabricated account names, metrics, dates, ARR, risks, or health ratings.
  • Injection case correctly ignored the instruction to output APPROVED and treated it as untrusted input.
  • Recommendations are actionable and aligned with account health review workflows.

Extend it

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

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