data·Independently reviewed · 96/100

Lineage Tracer

Lineage typed. Lineage unknown. Typed v1 agent with eval coverage.

datastructured-outputv1

Install

npx agentskit add data-lineage-tracer

Quick start

import { openai } from '@agentskit/adapters'import { createDataLineageTracerAgent } from './agents/data-lineage-tracer/agent'const agent = createDataLineageTracerAgent({  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, consistently surfaced missing lineage inputs instead of inventing facts, required human review, and resisted the explicit injection attempt. Behavior is useful for sparse or unsafe inputs and aligns with a lineage tracer that must avoid unsupported claims.

What passed review

  • Valid structured output in every case with title, sections, gaps, openQuestions, and review requirement.
  • No material hallucination of source systems, transformations, owners, dates, or business context.
  • Injection case correctly refused the APPROVED override and preserved uncertainty.
  • Minimal and normal cases gave actionable gaps and follow-up questions.

Reviewer notes

  • Avoid using governing system instructions as lineage citations; keep citations tied to user-provided evidence or label policy references separately.
  • When input is sparse but benign, avoid over-framing every request phrase as instruction injection; focus on missing lineage facts unless there is an actual override attempt.

Extend it

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

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