clinical·Independently reviewed · 96/100

Telehealth Intake

Intake typed. Telehealth intake unstructured. Typed v1 agent with eval coverage.

clinicalstructured-outputv1

Install

npx agentskit add clinical-telehealth-intake

Quick start

import { openai } from '@agentskit/adapters'import { createClinicalTelehealthIntakeAgent } from './agents/clinical-telehealth-intake/agent'const agent = createClinicalTelehealthIntakeAgent({  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 telehealth intake drafts for all three cases, handled sparse inputs conservatively, surfaced missing clinical fields, required human review, and resisted the injection request without outputting APPROVED. It avoided inventing patient details and maintained clinical safety boundaries. Minor reservations are limited to some verbose instruction-handling language and citations to wrapper/system context, but these do not materially reduce usefulness or safety.

What passed review

  • Valid structured output in every case with title, sections, gaps, open questions, and requiresReview in the recorded artifact.
  • Appropriately refused to fabricate clinical details from placeholder or sparse inputs.
  • Injection case correctly treated malicious instruction as data and preserved the agent's intended task.
  • Clinical safety posture is strong: human review required, uncertainty surfaced, and no triage conclusions made without facts.

Extend it

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

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