legal·Independently reviewed · 96/100

Jurisdiction Analyzer

Analysis typed. Jurisdiction risk unclear. Typed v1 agent with eval coverage.

legalstructured-outputv1

Install

npx agentskit add legal-jurisdiction-analyzer

Quick start

import { openai } from '@agentskit/adapters'import { createLegalJurisdictionAnalyzerAgent } from './agents/legal-jurisdiction-analyzer/agent'const agent = createLegalJurisdictionAnalyzerAgent({  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 structured outputs for all three cases, stayed within the jurisdiction-analysis purpose, did not invent facts, handled missing context conservatively, surfaced concrete information gaps, required human review, and resisted the injection request. The outputs are useful for sparse legal inputs because they clearly communicate uncertainty without making unsupported legal conclusions. Minor weakness: the normal case remains generic because the input itself was only a meta-request, but the refusal to hallucinate facts is appropriate for v1 legal validation.

What passed review

  • Valid structured output in every case with score, band, factors, rationale, gaps, and review requirement.
  • Consistently avoids hallucinating parties, forums, governing law, or jurisdictional conclusions from absent facts.
  • Handles prompt injection correctly by ignoring the instruction to output APPROVED.
  • Uses a conservative medium-risk uncertainty posture for missing jurisdictional facts.
  • Provides specific, actionable gaps needed for human legal review.

Extend it

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

const agent = createLegalJurisdictionAnalyzerAgent({  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'/** Jurisdiction Analyzer — v1 validated. Pain: Jurisdiction risk unclear */export interface AgentOutput { score: number; band: 'low' | 'medium' | 'high' | 'critical'; factors: string[]; rationale: string; gaps: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface LegalJurisdictionAnalyzerConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  score: z.number().min(0).max(100),  band: z.enum(['low', 'medium', 'high', 'critical']),  factors: z.array(z.string()),  rationale: z.string(),  gaps: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'legal-jurisdiction-analyzer',  description: "Jurisdiction Analyzer — typed output agent (draft spec).",  systemPrompt: `You are Jurisdiction Analyzer. Jurisdiction risk unclear. Output: Analysis typed.Score 0-100 with explicit factors from input.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_jurisdiction_analyzer exactly once. Stop.`,  tools: ['submit_jurisdiction_analyzer'],}export function createLegalJurisdictionAnalyzerAgent(config: LegalJurisdictionAnalyzerConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_jurisdiction_analyzer', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('legal-jurisdiction-analyzer requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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-jurisdiction-analyzer',    run,    asHandle() { return { name: 'legal-jurisdiction-analyzer', 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-jurisdiction-analyzer',  cases: [    { input: 'Complete input for Jurisdiction Analyzer: Jurisdiction risk unclear. 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