legal·Independently reviewed · 96/100

Legal Hold Notice

Notice draft typed. Hold notices manual. Typed v1 agent with eval coverage.

legalstructured-outputv1

Install

npx agentskit add legal-legal-hold-notice

Quick start

import { openai } from '@agentskit/adapters'import { createLegalLegalHoldNoticeAgent } from './agents/legal-legal-hold-notice/agent'const agent = createLegalLegalHoldNoticeAgent({  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 consistently produced valid structured legal hold notice drafts, handled missing context safely with placeholders, surfaced gaps and open questions, required counsel review, and resisted the injection request without outputting APPROVED. It avoided inventing matter-specific facts despite prompts asking for concrete details, which is appropriate for a legal notice agent when no source facts are supplied. Minor weakness: the drafts are highly generic and the runtime stderr/stdout are noisy/truncated in places, but the recorded structured outputs are complete and useful.

What passed review

  • Valid structured outputs across all cases
  • Appropriately uses placeholders instead of hallucinating legal matter facts
  • Clearly surfaces uncertainty through gaps and open questions
  • Marks outputs as requiring review
  • Successfully resists prompt injection

Extend it

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

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