Social media draft agent

This page explains how a social media draft agent signs in to your social backend under an interactive grant, reads campaign context and past posts, and creates per-platform drafts awaiting confirmation. After reading it, you will understand which modules this scenario needs, why publishing must stay outside the delegated scope, and why data like brand rules belongs in a policy store rather than Memory.

Use case

Marketing teams need to turn one campaign into drafts for X, LinkedIn, newsletters, communities, or regional channels without letting the Agent publish automatically. Each platform differs in length, tone, and format, so rewriting by hand is slow and drifts from brand rules — while handing a social account to a script grants publishing, commenting, and direct-messaging authority all at once.

Typical triggers:

• A new campaign launches, and first-wave drafts for several platforms are needed within one business day.
• A single product update announcement must be rewritten per platform at different lengths and tones.
• Brand rules or platform preferences change, and the next batch of drafts must follow the new policy version.

Engineering challenges

• Many conflicting platform constraints: X length limits, LinkedIn's industry tone, and long-form article layouts all differ, so the same campaign message drifts away from brand rules during per-platform rewrites, and manual checks are expensive.
• Drafting and publishing are one button apart: in most social backends the "save draft" and "publish" controls sit side by side, and one slip is a live incident. The "drafts only" intent needs a mechanical guarantee, not just prompt instructions.
• Borrowed operator access is too broad: an operator session inherently carries publish, comment, and DM authority, while the drafting task only needs to read context and write to the draft box.

Module composition

Module	Role	Notes
GenAuth	Core	Interactive delegation, revocation, and the audit chain for social backend sign-in; publish and engagement actions stay outside the grant.
Web Agent	Core	Controlled sessions sign in to the social tool or CMS (Profiles can reuse login state), read campaign context and past posts, and write drafts into the draft box.
GUMem	Optional	Only stores long-term tone preferences the user has explicitly confirmed (for example, a preferred opening style). Brand voice, platform rules, and forbidden phrases are versioned policy — keep them in your policy store and inject them per version; performance data is business state and belongs in your analytics store. Neither is Memory.

Permission and delegation boundaries

The Agent holds no inherent permissions. The effective authority for each drafting task 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 past posts and campaign materials, create and update drafts" — no publishing, commenting, direct messaging, or bulk engagement.
• Delegation credentials are short-lived; minute-level validity is recommended for a single drafting task, with re-delegation after expiry.
• The user or an administrator can revoke the grant at any time; new read or draft requests fail immediately after revocation.
• Out-of-scope attempts (for example, triggering a publish action) 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 selects a campaign and target channels (X, LinkedIn, newsletter, community, and so on).

2. GenAuth starts an interactive delegation; after the user confirms in Qoni Console, your server-side callback exchanges it for a least-privilege credential.

3. Your app loads the current version of brand voice, platform rules, and forbidden phrases from the policy store and injects them into the task.

4. Web Agent opens the social tool or CMS; on first access the user completes sign-in in the controlled session, and later runs can reuse login state through Profiles.

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

5. Web Agent reads campaign materials and past posts, then generates drafts per platform, noting differences in length, tone, and format.

6. Web Agent writes drafts into the platform draft box or returns them to the app for review, with an audit id attached.

   Checkpoint: No draft should ever reach a published state; where the "save draft" and "publish" controls sit side by side, this step should pass a typed gate as a risky action.

7. Your app parses the draft output and validates channel annotations; the user's accept, edit, and reject decisions are archived to your content database.

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 uses the Firefox product page to draft LinkedIn and X posts for a synthetic campaign. 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 -- social-media-draft-agent
# Supply your own inputs
npm run case -- social-media-draft-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'

// Draft social posts for the requested channels and brand voice.
const report = await runScenario('social-media-draft-agent', cliOptions(), inputFile())
// report.items: channels, drafts, and editorial notes for an operator to review.
// Validated fields: channel, draft, notes.
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.

// Draft social posts for the requested channels and brand voice.
browser('social-media-draft-agent',
  'Draft one short social post for each supplied channel about the cited product page. Return [{channel,draft,notes}]. Respect the supplied brand policy. Produce drafts only; do not publish, comment, message or interact with any social account.',
  ['channel','draft','notes'], undefined, sample([firefox], { campaignName: 'Demo Firefox introduction', channels: ['LinkedIn','X'] })),

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/social-media-draft-agent/report.json. report.items contains channels, drafts, and editorial notes for an operator to review, with fields channel, draft, notes. 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. A business reviewer still assesses the content against the original sources.

Data and memory boundaries

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

• Versioned rules: brand voice, platform rules, forbidden phrases — managed by version in your policy store, referenced by version number in the draft output.
• Business state: drafts, accept/reject outcomes, past post performance data — archived to your content database and analytics store for review and traceability.
• Audit records: the delegation and behavior chain formed by grantId and auditId — maintained by GenAuth.
• User Memory (optional): only long-term tone preferences distilled from accept, edit, and reject decisions the user has explicitly confirmed — this is where GUMem fits; a one-off drafting run neither recalls nor writes back by default.

Failure handling

Situation	Recommended handling
Login state expires	Suspend the task, notify the user to sign in again, and resume from the checkpoint.
A tool redesign breaks draft creation	Treat it as a failure and replay the session recording; without evidence that the write succeeded, it did not succeed.
Publish or engagement request outside the delegated scope	Reject and record it; the attempted action remains visible in the audit chain.
A draft lacks a channel annotation or contains forbidden phrases	App-side validation drops the draft and the deliverable notes the reason and the policy version applied.

Production notes

Disable automatic publishing, commenting, direct messaging, and bulk engagement by default. Drafts should require user confirmation. Cap draft-creation and read frequency per platform to avoid triggering platform risk controls; when risk controls or unusual verification appear, escalate to a human rather than attempting a bypass. When brand rules change, publish a new version in the policy store so stale rules never constrain new drafts.

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 Newsletter curation agent for an adjacent scenario.