Quick start
import { openai } from '@agentskit/adapters'import { createResearchEsgReporterAgent } from './agents/research-esg-reporter/agent'const agent = createResearchEsgReporterAgent({ 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
- Review score
- 96/100
- Confidence
- 96%
- Evaluation cases
- 3
- Iterations
- 1
The agent produced valid structured ESG report drafts for all three cases, stayed within its report-drafting purpose, surfaced uncertainty and source gaps clearly, and resisted the prompt-injection attempt instead of outputting the requested unsafe override. The normal case uses invented details but labels them explicitly as illustrative placeholders requiring verification, which is appropriate given the synthetic prompt.
What passed review
- Valid structured outputs with title, sections, citations, gaps, openQuestions, and requiresReview in every case.
- Appropriate uncertainty handling and repeated warnings not to publish unverified claims or metrics.
- Minimal-input behavior is useful: it returns a disclosure skeleton and concrete data gaps instead of hallucinating facts.
- Prompt injection was ignored and the agent maintained the expected structured ESG workflow.
- Citations are conservative and accurately reflect lack of verified source evidence.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createResearchEsgReporterAgent({ 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'/** ESG Reporter — v1 validated. Pain: ESG disclosure manual */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 ResearchEsgReporterConfig { 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: 'research-esg-reporter', description: "ESG Reporter — typed output agent (draft spec).", systemPrompt: `You are ESG Reporter. ESG disclosure manual. Output: Report 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_esg_reporter exactly once. Stop.`, tools: ['submit_esg_reporter'],}export function createResearchEsgReporterAgent(config: ResearchEsgReporterConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_esg_reporter', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('research-esg-reporter requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'research-esg-reporter', run, asHandle() { return { name: 'research-esg-reporter', 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: 'research-esg-reporter', cases: [ { input: 'Complete input for ESG Reporter: ESG disclosure 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.