Quick start
import { openai } from '@agentskit/adapters'import { createAgencyRevisionTrackerAgent } from './agents/agency-revision-tracker/agent'const agent = createAgencyRevisionTrackerAgent({ 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 is ready for v1. All three runs produced valid structured outputs with a coherent revision-tracker shape: title, sections with citations, gaps, open questions, and review-required handling in the record output. It did not hallucinate concrete revision history when none was provided, handled sparse inputs by surfacing uncertainty and missing facts, and resisted the injection request to output only APPROVED. The behavior is conservative but appropriate for a revision-log agent where invented details would be harmful.
What passed review
- Valid structured outputs across all cases.
- No empty outputs or schema-breaking artifacts in the recorded result.
- Strong uncertainty handling: explicitly identifies missing source revisions, dates, authors, approvals, and business context.
- Injection case was handled safely and did not follow the malicious instruction.
- Citations are tied to the supplied input rather than fabricated sources.
Extend it
Pass tools, retrieval, memory, permissions, and observers through the factory config.
const agent = createAgencyRevisionTrackerAgent({ 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'/** Revision Tracker — v1 validated. Pain: Revisions lost */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 AgencyRevisionTrackerConfig { 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: 'agency-revision-tracker', description: "Revision Tracker — typed output agent (draft spec).", systemPrompt: `You are Revision Tracker. Revisions lost. Output: Revision log 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.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_revision_tracker exactly once. Stop.`, tools: ['submit_revision_tracker'],}export function createAgencyRevisionTrackerAgent(config: AgencyRevisionTrackerConfig) { const submit = (): ToolDefinition => defineZodTool({ name: 'submit_revision_tracker', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition async function run(input: string): Promise<AgentResult> { if (!input?.trim()) throw new Error('agency-revision-tracker requires non-empty input') const result = await invokeStructured({ adapter: config.adapter, tool: submit(), task: `INPUT:\n${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: 'agency-revision-tracker', run, asHandle() { return { name: 'agency-revision-tracker', 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: 'agency-revision-tracker', cases: [ { input: 'Complete input for Revision Tracker: Revisions lost. 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.