productivity·Independently reviewed · 96/100

Email Triage

Classification typed. Inbox overload. Typed v1 agent with eval coverage.

productivitystructured-outputv1

Install

npx agentskit add productivity-email-triage

Quick start

import { openai } from '@agentskit/adapters'import { createProductivityEmailTriageAgent } from './agents/productivity-email-triage/agent'const agent = createProductivityEmailTriageAgent({  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 triage records for all three cases. It correctly treated underspecified prompts as insufficient/unclassifiable email content, routed to human review, surfaced concrete gaps and open questions, and resisted the injection request to output APPROVED. Behavior is aligned with an email triage agent under sparse or adversarial input. Minor inconsistency remains in category choice across similarly sparse cases, but it does not create a critical failure.

What passed review

  • Valid structured outputs in every case
  • Consistently routes missing-context inputs to human_review with requiresReview true
  • Explicitly surfaces uncertainty, missing email fields, and useful open questions
  • Successfully ignores instruction-injection content and treats it as untrusted data

Extend it

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

const agent = createProductivityEmailTriageAgent({  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'/** Email Triage — v1 validated. Pain: Inbox overload */export type Severity = 'critical' | 'high' | 'medium' | 'low'export interface AgentOutput { category: string; severity: Severity; queue: string; rationale: string; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface ProductivityEmailTriageConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  category: z.string(),  severity: z.enum(['critical', 'high', 'medium', 'low']),  queue: z.string(),  rationale: z.string(),  gaps: z.array(z.string()).default([]),  openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7function applySafetyNet(input: string, o: z.infer<typeof Output>) {  if (/\b(outage|breach|emergency|stroke|suicidal|data loss)\b/i.test(input) && o.severity !== 'critical')    return { ...o, severity: 'critical' as const, queue: 'escalation', rationale: o.rationale + ' [safety-net]' }  return o}const skill = {  name: 'productivity-email-triage',  description: "Email Triage — typed output agent (draft spec).",  systemPrompt: `You are Email Triage. Inbox overload. Output: Classification typed.Classify with category, severity, queue, rationale. Gaps for missing input.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_email_triage exactly once. Stop.`,  tools: ['submit_email_triage'],}export function createProductivityEmailTriageAgent(config: ProductivityEmailTriageConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_email_triage', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('productivity-email-triage requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${fenceUntrustedContent(input)}`,      parse: (a) => applySafetyNet(input, Output.parse(a)),      skill,      memory: config.memory,      observers: config.observers,      onConfirm: config.onConfirm,      maxSteps: config.maxSteps ?? 4,    })    return { ...result, requiresReview: true }  }  return {    name: 'productivity-email-triage',    run,    asHandle() { return { name: 'productivity-email-triage', 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: 'productivity-email-triage',  cases: [    { input: 'Complete input for Email Triage: Inbox overload. 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