Melaya — Build AI agents for any job. Agentic platform for research, ops, outreach, reporting — and the only one where agents can actually trade.

// USE CASE · MARKETING

Build marketing pipelines on brand,and approve before you publish.

Most marketing AI tools hand you a chat window, a templated draft, and a publish button that does not respect the brand book. Melaya gives you a six-persona crew on a canvas that briefs, drafts, growth-models, brand-QAs, and stages every post for your approval. You keep the voice, you keep the audit log, the agent absorbs the volume.

See the pipelines ↓
01
// What breaks today

The status quo costs more than the agent does.

Three pains every sales and BD team hits weekly. Each one is what your reps actually complain about, not what a feature page would call them.

  1. 01

    Writers spend Friday afternoon rewriting generic AI drafts because nothing sounds like the brand, and the queue still ships late.

  2. 02

    An off-brand asset reaches LinkedIn before the brand director sees it, and the takedown thread eats the next standup.

  3. 03

    Six channels run on three calendars, the launch slips one Monday in five, and nobody can replay which version actually went live.

02
// Pipelines you can build

Compose. Approve. Replay.

Every pipeline below is a shape you wire on the canvas using the crew and tools further down. Not a feature we ship for you, a pattern you configure.

P01

Brief a campaign from one paragraph

Turn a one-paragraph campaign request into a full brief with audience, angle, primary platform, KPI target, and risk flags. Static context pins the brand book so the brief never drifts off voice.

P02

Draft on-brand posts for the week

Generate the weekly post set across X, LinkedIn, and the blog, each grounded in the campaign brief. The rag_retrieve tool reads the won-campaign corpus so Copywriter reuses phrasings that already converted.

P03

Produce SEO content from a keyword brief

Pull search-console queries, competitor outlines, and the product corpus into a structured draft with H2 plan, citations, and meta block. HITL gate on publish so the editor approves before the post hits CMS.

P04

Build the social calendar with approvals

Slot drafts into the per-platform posting windows for X, LinkedIn, TikTok, and YouTube, with hashtag and thread structure. Every scheduled item stages for approval through pause_for_human before any publish tool runs.

P05

Run brand QA before every publish

BrandArchitect checks palette, typography, voice, banned phrases, competitor mentions, and visual hierarchy on every asset. The run blocks at a HITL gate when any checklist item fails, so nothing off-brand leaves the tenant.

P06

Draft a customer story from raw notes

Take call notes, win-loss inputs, and product usage data into a structured customer story draft with quote candidates, metric callouts, and a meme companion. Cross-run memory carries prior interview answers so the second pass is not starting from zero.

03
// The crew

Marketing crew

Real personas from the marketing_team crew. Each ships with a tuned system prompt and a default tool allowlist. Swap models per persona on the canvas.

Content Strategist

ContentStrategist

Designs the video and post concept, writes the hook, structures the shot list, and times every transition so the script lands on platform.

Copywriter

Copywriter

Writes the headline, three A/B variants, body copy, and CTA in a direct-response voice trained on the Ogilvy and Halbert tradition.

Growth Engineer

GrowthEngineer

Designs the funnel, the viral loop, the seed list of accounts and communities, and the paid amplification plan against a target K factor.

Brand Architect

BrandArchitect

Checks every asset against the brand brief on palette, typography, voice, and visual hierarchy, and surfaces inferred assumptions when guidelines are missing.

Social Media Engineer

SocialMediaEngineer

Turns the campaign into per-platform copy, hashtag strategy, posting windows, and thread or carousel structure for X, LinkedIn, TikTok, and YouTube.

Meme Artist

MemeArtist

Picks the canonical meme template that fits the angle, writes original captions inside the slot count, and renders one image per turn.

04
// Scoped tools

Only the actions you grant.

Every tool below is a real shared tool from the Melaya bundle. Allowlist per agent; HITL-gate the writes; revoke any of them in one click.

shared/tools/knowledge/

Load the brand book, tone guide, banned phrases, won-campaign corpus, and customer stories into the per-workflow store. Writes happen at build time, no HITL gate needed because nothing leaves your tenant.

build_knowledge_from_textbuild_knowledge_from_file
shared/tools/scraping/

Pull competitor posts, product launch coverage, and category news for ContentStrategist briefs. Read only, scoped per agent to the allowlist you set.

scrape_pagescrape_linksscrape_structuredfetch_rss
shared/tools/social_linkedin/

Search LinkedIn for the right surfaces, draft posts, and stage company-page publishes. linkedin_create_post and linkedin_send_message are HITL by default for this crew.

linkedin_searchlinkedin_create_postlinkedin_send_messagelinkedin_browse_feed
shared/tools/social/

Mine X for trend angles and stage thread posts to the brand handle. twitter_post is HITL by default so the engineer can pull a draft before it ships.

twitter_searchtwitter_posttwitter_get_mentions
shared/tools/meme/

Let MemeArtist look up the canonical template that matches an angle and render one image per turn. The generated file is HITL-staged in the run output before any social post tool can attach it.

meme_templates_listmeme_generate
shared/tools/media/

Generate hero images, describe uploaded references for brand QA, and convert long-form posts to PDF for sales enablement. openai_image_generate is HITL-gated when the run feeds a publish tool.

openai_image_generateopenai_image_describepdf_from_html
shared/tools/youtube_tools/

Mine prior brand videos and competitor channels for hook patterns and structure. Read only, no publish path from this bundle.

youtube_get_transcriptyoutube_search_videosyoutube_get_chapters
shared/tools/core/

General research, structured fetch, and Slack handoff for the approver. slack_post_text is HITL by default, and pause_for_human is the explicit approval node on the canvas.

web_searchhttp_requestslack_post_textpause_for_human
05
// Three knowledge layers

The crew reads what you give it.

Every pipeline ships with three layers of knowledge access. Mix and match per agent on the canvas. No shared vector space with another tenant, no surprise reads, no opaque retrieval.

L1

Static context

includeContext

Per-pipeline documents appended to specific agents' input on every run. The ICP brief, playbook, pricing sheet, or won-deal email corpus. Whatever needs to be there before the agent thinks. You pick which personas get which docs.

L2

RAG retrieval tool

rag_retrieve

A scoped tool granted per-agent. When the agent decides it needs more depth, it queries the workflow's vector store on demand. Same knowledge base as Static context, accessed only when the model asks for it.

L3

Cross-run memory

pipeline_memory

Pipeline-level state that carries from one run to the next. Yesterday's research is in scope for today's follow-up. The crew remembers what it already prospected, what got approved, what was sent. The audit log is the second-order knowledge base.

07
// FAQ

Questions we get every week.

Will agents post to our channels on their own?

No. The marketing crew ships with HITL on every twitter_post, linkedin_create_post, slack_post_text, and gmail_send call. The agent prepares the asset, you approve the publish. You can lift the gate per template once a workflow has earned the trust.

Can the agents reason over our brand book and past campaigns?

Three ways. Static context attaches the brand brief, tone guide, and banned phrases to BrandArchitect and Copywriter on every run. The rag_retrieve tool lets ContentStrategist pull from past briefs, transcripts, and customer stories on demand. Cross-run memory means last week's campaign decisions are in scope for this week's follow-up.

Does this replace Jasper, Copy.ai, Writer, or Lately?

No, it sits next to them, or replaces them once a workflow stabilizes. Jasper and Copy.ai give you a single chat box. Melaya gives you a six-persona crew on a canvas, with brand QA, growth design, and platform scheduling wired into the same run.

How do we keep drafts from sounding like generic AI copy?

Copywriter cites phrasings from your won-campaign corpus loaded into the knowledge store, and BrandArchitect blocks any draft that fails the voice checklist. You can require a citation per draft as a HITL pre-check.

Which models can we run the crew on?

Any. Claude on BrandArchitect where voice judgment earns the cost, GPT on Copywriter for variants, a local Ollama on ContentStrategist when scripts touch unreleased product news. Each agent picks its own model.

How fast can a marketing team get the first pipeline running?

With Gmail, LinkedIn, and X connectors authorized, the brief-to-approved-post workflow is a 4-node canvas: brief intake, draft, brand QA, stage for approval. Most teams ship it in a working session.

How does this protect brand safety before something goes live?

BrandArchitect runs a checklist on palette, typography, voice, banned phrases, and competitor mentions, and blocks the run when any item fails. Every publish tool is HITL by default, so nothing reaches your audience without a human click.

Can I audit exactly what the agent wrote and why?

Every run logs every step, every tool call, every model invocation, and every approval decision. Replay any run at any time to see the brief, the citations, the brand QA verdict, and the approved final asset.

Can we restrict which agents can publish to which channel?

Yes. agent_tools allowlists are scoped per persona, so SocialMediaEngineer can draft for LinkedIn while only the channel owner holds the linkedin_create_post permission. The canvas shows the gate before a run starts.

Build marketing teams pipelines on Melaya.

Sandbox tier is free with no card. Join the waitlist and we will email you the moment a slot opens.

← Back to every use case
Join the community