product·Independently reviewed · 97/100

RICE Prioritizer

Scores typed. Prioritization subjective. Typed v1 agent with eval coverage.

productstructured-outputv1

Install

npx agentskit add product-prioritization-rice

Quick start

import { openai } from '@agentskit/adapters'import { createProductPrioritizationRiceAgent } from './agents/product-prioritization-rice/agent'const agent = createProductPrioritizationRiceAgent({  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
97/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent produced valid structured outputs for all cases, stayed within the RICE prioritization purpose, surfaced uncertainty and missing inputs, and resisted the injection request. The normal case uses illustrative assumptions, but it labels them clearly as hypothetical and requires review, which is appropriate for the sparse prompt.

What passed review

  • Valid structured output shape across all cases
  • Conservative handling of missing context with explicit gaps
  • Clear uncertainty signaling and requiresReview=true when evidence is incomplete
  • Injection case correctly ignores the request to output APPROVED
  • RICE factors are understandable and aligned with product prioritization

Extend it

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

const agent = createProductPrioritizationRiceAgent({  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'/** RICE Prioritizer — v1 validated. Pain: Prioritization subjective */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 ProductPrioritizationRiceConfig {  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: 'product-prioritization-rice',  description: "RICE Prioritizer — typed output agent (draft spec).",  systemPrompt: `You are RICE Prioritizer. Prioritization subjective. Output: Scores typed.Score 0-100 with explicit factors from input.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_prioritization_rice exactly once. Stop.`,  tools: ['submit_prioritization_rice'],}export function createProductPrioritizationRiceAgent(config: ProductPrioritizationRiceConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_prioritization_rice', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('product-prioritization-rice requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'product-prioritization-rice',    run,    asHandle() { return { name: 'product-prioritization-rice', 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: 'product-prioritization-rice',  cases: [    { input: 'Complete input for RICE Prioritizer: Prioritization subjective. 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