support·Independently reviewed · 96/100

CSAT Response Drafter

Response draft typed. Negative CSAT slow. Typed v1 agent with eval coverage.

supportstructured-outputv1

Install

npx agentskit add support-csat-response-drafter

Quick start

import { openai } from '@agentskit/adapters'import { createSupportCsatResponseDrafterAgent } from './agents/support-csat-response-drafter/agent'const agent = createSupportCsatResponseDrafterAgent({  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, non-empty structured outputs for all three cases, stayed aligned with the CSAT response drafting purpose, and handled sparse input and prompt injection safely. The normal case introduced illustrative customer details, but it explicitly labeled them as assumed, required human review, and surfaced verification gaps, so this is not a material hallucination for the provided eval prompt.

What passed review

  • Valid structured output shape in every case with title, sections, gaps, openQuestions, and requiresReview.
  • Appropriate cautious tone for negative CSAT response drafts.
  • Minimal and injection cases surface missing context instead of overcommitting.
  • Prompt injection was ignored and the output remained task-aligned.
  • Human review requirement is consistently set for uncertain or assumed details.

Extend it

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

const agent = createSupportCsatResponseDrafterAgent({  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'/** CSAT Response Drafter — v1 validated. Pain: Negative CSAT slow */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 SupportCsatResponseDrafterConfig {  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: 'support-csat-response-drafter',  description: "CSAT Response Drafter — typed output agent (draft spec).",  systemPrompt: `You are CSAT Response Drafter. Negative CSAT slow. Output: Response draft 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_response_drafter exactly once. Stop.`,  tools: ['submit_response_drafter'],}export function createSupportCsatResponseDrafterAgent(config: SupportCsatResponseDrafterConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_response_drafter', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('support-csat-response-drafter requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-csat-response-drafter',    run,    asHandle() { return { name: 'support-csat-response-drafter', 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-csat-response-drafter',  cases: [    { input: 'Complete input for CSAT Response Drafter: Negative CSAT slow. 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