Landing page audit agent

This page explains how a landing page audit agent reviews the messaging, CTAs, claims compliance, link validity, and conversion elements of your own and competitor landing pages under a read-only grant, and returns an audit report with page sources. After reading it, you will understand which modules this scenario needs, how the permission boundary narrows, and why data like brand rules belongs in a policy store rather than Memory.

Use case

Marketing teams need to check landing pages against product positioning, brand voice, compliance requirements, and conversion goals before publishing. With many pages and frequent redesigns, manually checking copy consistency, claim wording, link validity, and conversion elements page by page is slow and error-prone — and handing CMS preview access to an ungoverned script means unreleased content can leak.

Typical triggers:

• A new campaign is about to launch, and every landing page needs a pre-publish audit within a business day.
• Positioning or pricing changed, and all existing pages must be swept for stale claims and dead links.
• A competitor redesigned, and your pages need a messaging and conversion-element gap check.

Engineering challenges

• High volume, high miss cost: dozens of pages × four dimensions (copy, claims, links, conversion elements). Manual spot checks always leave blind spots, and an out-of-bounds claim reaching production is a compliance incident.
• Evidence is hard to organize: every finding needs "which page, which version, when" — scattered screenshots and links cannot support later review.
• Borrowed CMS preview access is too broad: an editor account can see every collection and carries edit and publish permissions, while the audit only needs to read the pages under review.

Module composition

Module	Role	Notes
GenAuth	Core	Read-only delegation, revocation, and the audit chain for authorized pages such as CMS previews.
Web Agent	Core	Controlled sessions extract headlines, CTAs, claims, and link status page by page, keeping a screenshot and source per page; public competitor pages can be supplemented with WebSearch.
GUMem	Optional	Only stores reviewer-confirmed long-term preferences (for example, preferred rewrite tone). Brand rules and forbidden claims are versioned policy — keep them in your policy store and inject them per version. They are not Memory.

Permission and delegation boundaries

The Agent holds no inherent permissions. The effective authority for each audit is the intersection of three sets: what the user actually holds ∩ what was explicitly delegated for this task ∩ what the enterprise has approved. Applied here:

• The delegated scope covers only "read the specified pages, CMS previews, and competitor comparison pages" — no editing, publishing, or CMS configuration changes.
• Delegation credentials are short-lived; minute-level validity is recommended for a single audit, with re-delegation after expiry.
• The user or an administrator can revoke the grant at any time; new page reads fail immediately after revocation.
• Out-of-scope attempts (for example, a CMS collection outside the delegated list) are rejected and recorded — the audit chain covers all attempts, not just successful actions.

Note: this sample requests doAnything product permissions. Your application and downstream services must configure and enforce business limits such as domain lists, page ranges, action whitelists. Product scopes and prompt rules do not enforce those detailed limits; this sample does not configure them. See Delegate token and attenuation.

Workflow

1. The user provides the list of landing pages or CMS preview links to audit and picks the review dimensions.

2. GenAuth issues a least-privilege, read-only delegation credential for this task.

3. Your app loads the current version of brand rules, forbidden claims, and conversion-element checks from the policy store and injects them into the task.

4. Web Agent opens each target page, extracts headlines, CTAs, proof points, and pricing claims, and keeps a screenshot and source URL per page.

   Checkpoint: When a CMS preview hits a login wall, CAPTCHA, or risk-control page, the Web Agent should escalate to a human instead of silently bypassing it.

5. Web Agent checks in-page link validity and conversion-element completeness; public competitor pages are extracted for comparison as needed.

6. The Agent aggregates findings per page — copy inconsistencies, out-of-bounds claims, dead links, missing conversion elements — each with page source, screenshot evidence, and the policy version.

7. The Agent returns the review checklist, findings, rewrite suggestions, and source list with an audit id; the report and screenshots are archived to your audit storage.

   Checkpoint: Every finding in the report should trace back to a concrete page source and screenshot; conclusions without evidence should not enter the deliverable.

Example code

This example uses @qoniai/qoni 0.9.0, published on npm. The download includes the same SDK version, installed with npm ci. The demo audits the Firefox product landing page against a synthetic evidence rule. The SDK reads real public pages; business inputs in scenarios.ts are labeled public-demo.

This demo does not read or write GUMem; its task uses the supplied page list and explicit business inputs. DoAnything opens the supplied pages and produces the scenario output. Supply your own JSON with --input; use --interactive when the user must consent to delegation. For site sign-in and user responses, see Qoni SDK.

Download the complete runnable examples, or run from the documentation repository:

cd examples/qoni
npm ci
npm run case -- landing-page-audit-agent
# Supply your own inputs
npm run case -- landing-page-audit-agent --input /path/to/input.json

Set server-side QONI_ACCESS_KEY and QONI_SECRET_KEY. QONI_USER_ID can identify your application's current GenAuth user; the local demo otherwise selects a user from the bound pool. Demonstration Memory writes use an isolated user rather than changing a business user's preferences.

This scenario's executable entry point:

import { cliOptions } from '../runtime.js'
import { inputFile, runScenario } from '../run-case.js'

// Inspect page copy and CTAs and request a screenshot artifact.
const report = await runScenario('landing-page-audit-agent', cliOptions(), inputFile())
// report.items: pages, issues or observations, quotes, rule IDs, and sources; the script also checks image delivery.
// Validated fields: page, issue, quote, ruleId, sourceUrl.
console.log(JSON.stringify(report, null, 2))

The entry point loads the definition below by scenario ID. The code is included directly from scenarios.ts, with comments shown in the page language: the task, output fields, source field, Web Search queries (if any), whether Memory is used, and the demonstration input. The pipeline appends the input data, search sources, recalled Memory, and shared safety constraints to the task to build the final prompt; see the pipeline below for the full assembly.

// Inspect page copy and CTAs and request a screenshot artifact.
browser('landing-page-audit-agent',
  'Audit the visible headline, CTA, product claims and evidence on the supplied landing page against the policy. Return [{page,issue,quote,ruleId,sourceUrl}]. Include inspected observations even when no violation is found. Capture a screenshot of the page and attach it. Do not edit, submit forms or change settings.',
  ['page','issue','quote','ruleId','sourceUrl'], 'sourceUrl', sample([firefox], { rules:[{id:'claims-supported',text:'Product claims need visible support.'}] })),

The sample implements runScenario(), browser(), research(), and sample() as application functions. The pipeline below makes the actual SDK calls: delegation and introspection → required Memory/search → browser task or monitor → validation and saving. fields and sourceField define the application's output checks. The complete application helpers are in the package's runtime.ts.

Inspect the actual SDK pipeline

// browser() uses DoAnything; research() searches first; sample() labels public-demo inputs.
const firefox = 'https://www.mozilla.org/en-US/firefox/new/'
const manifesto = 'https://www.mozilla.org/en-US/about/manifesto/'
const privacy = 'https://www.mozilla.org/en-US/privacy/firefox/'
const support = 'https://support.mozilla.org/en-US/kb/get-started-firefox-overview-main-features'
// These copy rules become prompt context; server permissions and business checks remain separate.
const policy = {
  version: 'demo-2026-09',
  approvedClaims: ['Describe only features supported by the cited page.'],
  forbiddenClaims: ['guaranteed security', '100% private', 'unverified pricing or performance'],
  voice: 'concise and warm',
}
const sample = (pages: string[], business: JsonObject = {}): JsonObject => ({
  dataset: 'public-demo', pages, policy, business,
  notice: 'Business records are synthetic demonstration inputs. Referenced websites and SDK execution are real.',
})
// fields lists required output keys; sourceField identifies URL checks; memory enables GUMem calls.
const browser = (id: string, task: string, fields: string[], sourceField: string | undefined, input: JsonObject, memory = false): Scenario => ({
  id, products: ['doAnything'], task, fields, sourceField, input, memory,
})
const research = (id: string, task: string, fields: string[], sourceField: string, queries: string[], input: JsonObject, memory = false): Scenario => ({
  id, products: ['webSearch', 'doAnything'], task, fields, sourceField, queries, input, memory,
})

import { QoniScopes, type JsonObject, type RunResult } from '@qoniai/qoni'
import { readFileSync } from 'node:fs'
import { getScenario, type Scenario } from './scenarios.js'
import { appendTrace, checkInputCoverage, cleanupDemoUser, createContext, delegate, handleInteraction, inputEntryCount, isolateDemoUser, object, readWithRetry, renderScreenshot,
  save, saveArtifacts, searchHits, settled, settleRun, validateItems, withCleanup, type Context, type Options } from './runtime.js'

export async function runScenario(id: string, options: Options = {}, input?: JsonObject) {
  // Load the task definition by ID; --input replaces its business inputs.
  const scenario = getScenario(id)
  const data = input ?? scenario.input
  if (scenario.memory && data.dataset !== 'public-demo' && options.mode !== 'interactive' && !options.userId && !process.env.QONI_USER_ID) {
    throw new Error('Business Memory writes require the current QONI_USER_ID; do not select an arbitrary bound user')
  }
  const context = await createContext(id, { ...options,
    skipUserResolution: scenario.memory && data.dataset === 'public-demo' })
  return withCleanup(context, async register => {
    register('isolated demonstration user', () => cleanupDemoUser(context))
    // Isolate demo preferences; business Memory belongs to the identified current user.
    if (scenario.memory && data.dataset === 'public-demo') await isolateDemoUser(context)
    return await executeScenario(context, scenario, data)
  })
}

export async function executeScenario(context: Context, scenario: Scenario, input: JsonObject) {
  const pages = input.pages
  if (!Array.isArray(pages) || !pages.length || pages.some(page => typeof page !== 'string' || !/^https:\/\//.test(page))) {
    throw new Error('Input pages must be an array of HTTPS URLs')
  }
  if (input.requiresLogin === true && context.mode !== 'interactive') {
    throw new Error('Targets that require sign-in need --interactive and user-controlled login')
  }
  const memoryScopes = scenario.memory
    ? [QoniScopes.GUMEM_MEMORY_READ, QoniScopes.GUMEM_MEMORY_WRITE, QoniScopes.GUMEM_MESSAGE_WRITE] : []
  // delegate() is an application helper around the SDK delegation methods.
  const grant = await delegate(context, scenario.id, scenario.products, memoryScopes)
  // Read the effective scopes; readWithRetry() retries only retryable read failures.
  const { data: tokenInfo } = await readWithRetry(context, 'delegation introspection',
    () => context.qoni.genauth.introspectDelegationToken({ token: grant.token }))
  const info = object(tokenInfo)
  if (info.active !== true) throw new Error('The delegation token is not active')
  const audit = { grantId: grant.grantId, auditId: grant.auditId, scopes: info.scope }
  let memory: unknown
  if (scenario.memory) {
    // A Session associates this conversation with the user; the app chooses sessionId.
    const sessionId = `${scenario.id}-${Date.now()}`
    await context.qoni.gumem.createSession({
      token: grant.token, userId: context.userId, sessionId, title: scenario.id,
    })
    const preferences = object(input.business ?? {}).confirmedPreferences
    if (Array.isArray(preferences) && preferences.length) {
      // Store confirmed preferences only; sync: true requests synchronous processing.
      await context.qoni.gumem.addMessages({ token: grant.token, userId: context.userId, sessionId, sync: true,
        messages: [{ role: 'user', content: `Confirmed demonstration preferences: ${preferences.join('; ')}` }] })
    }
    // Recall relevant preferences for the later task prompt.
    memory = (await readWithRetry(context, 'GUMem recall', () => context.qoni.gumem.recall({ token: grant.token, sessionId,
      query: 'Confirmed preferences relevant to this task', details: true }))).data
    save(context, 'memory.json', { sessionId, context: memory })
    if (Array.isArray(preferences) && preferences.length && !preferences.every(value => JSON.stringify(memory).includes(String(value)))) {
      throw new Error('Recall did not include the confirmed preferences just written by this demo')
    }
  }

  if (scenario.products.includes('track')) return runMonitor(context, scenario, input, grant.token, audit)

  let hits: ReturnType<typeof searchHits> = []
  if (scenario.queries) {
    // Web Search returns results[]; DoAnything receives these sources to inspect.
    const search = await context.qoni.webSearch.run({ token: grant.token, prompt: scenario.queries, maxResultsPerQuery: 3 })
    save(context, 'search-ref.json', { runId: search.id, audit })
    await withCleanup(context, async register => {
      register('Web Search run', () => search.cancel('Documentation demonstration cleanup'))
      const result = await settleRun(context, search)
      save(context, 'search-result.json', result)
      settled(result)
      hits = searchHits(result.output)
    })
  }

  // One-per-entry scenarios request exactly one item per input entry; others at most two.
  const requiredItems = inputEntryCount(scenario.id, input)
  // Assemble the task, inputs, search sources, and Memory as application-defined context.
  const prompt = [scenario.task, `Task inputs: ${JSON.stringify(input)}`,
    `Search sources: ${JSON.stringify(hits)}`, `Confirmed memory: ${JSON.stringify(memory ?? null)}`,
    `Actual collection time: ${new Date().toISOString()}`,
    requiredItems === undefined
      ? 'Inspect the supplied sources. Return at most two items in the requested JSON array, without prose or Markdown.'
      : `Inspect the supplied sources. Return exactly ${requiredItems} item${requiredItems === 1 ? '' : 's'} in the requested JSON array, one per input entry, without prose or Markdown.`,
    'Keep synthetic demonstration data identified as synthetic. Do not send messages, publish, pay, edit accounts or submit forms.',
    input.requiresLogin === true ? 'Request user sign-in through an interaction when required; never enter credentials yourself.' : 'Public demonstration sources only; do not sign in.',
  ].join('\n\n')
  // Start the Agent with this grant; capture receives delivered screenshots, not every step.
  const run = await context.qoni.doAnything.run({ token: grant.token, prompt, capture: { screenshots: true } })
  save(context, 'run-ref.json', { runId: run.id, session: run.sessionRef, audit })
  let result: RunResult
  const trace = (event: { type: string; data: unknown }) => {
    context.eventCounts[event.type] = (context.eventCounts[event.type] ?? 0) + 1
    if (['progress','message','done'].includes(event.type)) appendTrace(context, event)
    if (event.type === 'browserLiveUrlChanged') {
      const liveUrl = object(event.data).liveUrl
      if (typeof liveUrl === 'string') context.browserUrl = liveUrl
    }
  }
  return withCleanup(context, async register => {
    register('DoAnything run', () => run.cancel('Documentation demonstration cleanup'))
    if (context.delivery === 'events') {
      // --events streams updates; wrap interaction data in an SDK handle for user handling.
      for await (const event of run.events({ signal: AbortSignal.any([context.abort.signal, AbortSignal.timeout(context.timeoutMs)]) })) {
        trace(event)
        if (event.type === 'screenshot') renderScreenshot(context, event.image)
        if (event.type === 'interaction') await handleInteraction(context, run.interactionHandle(event.data))
      }
      result = await settleRun(context, run)
    } else {
      // Callback mode receives this run's events inside wait; helpers save images and ask the user.
      result = await settleRun(context, run, { onEvent: trace,
        onScreenshot: (image, index) => renderScreenshot(context, image, index),
        onInteraction: interaction => handleInteraction(context, interaction) })
    }
    save(context, 'result.json', result)
    settled(result)
    await saveArtifacts(context, result)
    if (scenario.id === 'landing-page-audit-agent' && context.screenshots === 0) throw new Error('The landing-page audit did not deliver the requested screenshot')
    // The app checks required fields and source URL formats; a reviewer still checks facts.
    const items = validateItems(result.output, scenario.fields, scenario.sourceField)
    // Scenarios that require one item per input entry are checked against the input.
    checkInputCoverage(scenario.id, items, input)
    const report = { scenario: scenario.id, dataset: input.dataset, passed: true, runId: run.id,
      status: result.status, items, audit, screenshots: context.screenshots, interactions: context.interactions,
      events: context.eventCounts, artifactIds: result.artifacts.map(artifact => artifact.id) }
    save(context, 'report.json', report)
    return report
  })
}

async function runMonitor(context: Context, scenario: Scenario, input: JsonObject, token: string, audit: JsonObject) {
  // Track creates a monitor with targets, extraction fields, and hourly scheduling.
  const monitor = await context.qoni.track.create({ token, prompt: scenario.task,
    targetUrls: input.pages, extractionSchema: { heading: 'string', source_url: 'string' },
    tickInstructions: `Open the target URLs and read the actual visible heading. Return a JSON object with heading and source_url. ${scenario.task}`,
    triggerDsl: { on: 'change' }, schedule: { kind: 'interval', intervalSeconds: 3600 } })
  save(context, 'monitor-ref.json', { id: monitor.id, audit })
  return withCleanup(context, async register => {
    register('Track monitor', () => monitor.delete())
    const definition = await monitor.get()
    save(context, 'monitor-definition.json', definition)
    if (object(definition.schedule).intervalSeconds !== 3600) throw new Error('Track did not persist the requested schedule interval')
    // Run one tick and inspect its extraction by runId; completed alone does not prove success.
    const tick = await monitor.runNow()
    save(context, 'tick.json', tick)
    if (tick.state !== 'completed') throw new Error(`Track execution failed: ${tick.state} / ${tick.error ?? ''}`)
    const runId = tick.runId
    if (typeof runId !== 'string') throw new Error('Track tick did not return a runId')
    const detail = await monitor.run(runId)
    save(context, 'tick-detail.json', detail)
    if (detail.state !== 'completed' || !detail.extracted || !Object.keys(object(detail.extracted)).length) {
      throw new Error('Track did not extract page data')
    }
    const extracted = object(detail.extracted)
    if (typeof extracted.heading !== 'string' || !extracted.heading.trim() ||
      typeof extracted.source_url !== 'string' || !/^https:\/\//.test(extracted.source_url)) {
      throw new Error('Track extraction is missing a heading or source URL')
    }
    const normalizeUrl = (value: string) => { const url = new URL(value); url.hash = ''; return url.href.replace(/\/$/, '') }
    if (!(input.pages as string[]).some(url => normalizeUrl(url) === normalizeUrl(String(extracted.source_url)))) {
      throw new Error('The Track source URL is not a configured target')
    }
    // Check persisted pause/resume state; withCleanup() deletes the monitor on exit.
    await monitor.pause()
    if ((await monitor.get()).status !== 'paused') throw new Error('Track did not persist the paused state')
    await monitor.resume()
    if ((await monitor.get()).status !== 'active') throw new Error('Track did not persist the active state')
    const report = { scenario: scenario.id, dataset: input.dataset, passed: true, monitorId: monitor.id,
      runId, state: detail.state, outcome: detail.outcome, extracted: detail.extracted, audit }
    save(context, 'report.json', report)
    return report
  })
}

export function inputFile(): JsonObject | undefined {
  const index = process.argv.indexOf('--input')
  return index >= 0 ? object(JSON.parse(readFileSync(process.argv[index + 1], 'utf8'))) : undefined
}

Results are written to output/landing-page-audit-agent/report.json. report.items contains pages, issues or observations, quotes, rule IDs, and sources; the script also checks image delivery, with fields page, issue, quote, ruleId, sourceUrl. audit links the grant ID, audit ID, and effective scopes; http.json records redacted request statuses. The application parses DoAnything output and checks required fields and source URL formats. A business reviewer still assesses the content against the original sources.

Data and rule boundaries

This scenario touches four kinds of data; only the last belongs in GUMem:

• Versioned rules: brand voice, forbidden claims, conversion-element checklists — managed by version in your policy store, referenced by version number in every report.
• Business state: audit reports, findings, page screenshots — archived to your audit storage for review and traceability.
• Audit records: the delegation and behavior chain formed by grantId and auditId — maintained by GenAuth.
• User Memory (optional): reviewer-confirmed long-term preferences, such as rewrite-tone preferences — this is where GUMem fits; a one-off audit neither recalls nor writes back by default.

Failure handling

Situation	Recommended handling
CMS preview login state expires	Suspend the task, notify the user to sign in again, and resume from the checkpoint.
Page structure changes break extraction	Treat it as a failure and replay the session recording; never emit findings without evidence.
Request for a CMS collection outside the grant	Reject and record it; the attempted access remains visible in the audit chain.
An output entry lacks a source or rule id	App-side validation drops the entry and the report notes how many were dropped.

Production notes

Never send unreleased page content to ungoverned external services. Rewrite suggestions must keep the original page source. The Agent only outputs reports and suggestions — it does not modify live pages or CMS content; any page change is made manually by the content owner based on the report and then reviewed. Extraction of public competitor pages should respect the target site's terms of service and be rate-limited.

Next steps

• Read the Quickstart to run the shortest path for Agent identity and delegation.
• Read Authorization and browser sandbox for the security boundaries of controlled sessions.
• Continue with the Brand consistency agent for an adjacent scenario.