P01
Post queue with a veto
Agents post your queued content from your real accounts, in your real apps, at a natural, human pace. Every post stops for your approval before it goes out.
01
// What breaks today
Manual workflows cost 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.
- 01
Audiences expect daily posts and constant engagement across TikTok, Instagram, and YouTube Shorts.
- 02
You have content, not 12 spare hours a day.
- 03
Agencies multiply that across dozens of client accounts.
02
// Pipelines you can build
Agent workflows: 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.
P02
Replies in your voice
Comments and DMs get drafted in your voice and queued for review. Nothing ships in your name that you did not sign off.
P03
One agent per client account
Agencies run one agent per client account in parallel, each scoped to its own apps, each with its own approval queue.
P04
Warm-up you control
New accounts warm up on a slow, steady schedule you control, with every action visible and every write gated.
03
// The multi-agent crew
Social growth 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.
Social Media Engineer
SocialMediaEngineerDrives the apps: posts, replies, and DMs, one verified action at a time.
Content Strategist
ContentStrategistPlans the queue and keeps the posting cadence natural and consistent.
Copywriter
CopywriterDrafts posts and replies in your voice, ready for your approval.
Growth Engineer
GrowthEngineerRuns account schedules, parallel client queues, and warm-up plans.
Brand Architect
BrandArchitectKeeps every account on-brand across platforms and clients.
04
// Scoped tools
Tool allowlists: 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.
01shared/tools/phone/
Works TikTok, Instagram, and X from your real device. Posting and commenting are approval-gated by the platform.
phone_open_appphone_get_screen_treephone_create_postphone_post_commentphone_scrollphone_screenshot
02shared/tools/social/
Covers X where the API route is open: search, mentions, posting.
x_searchx_postx_get_mentions
03shared/tools/social_linkedin/
LinkedIn feed, posts, and messages for professional accounts.
linkedin_searchlinkedin_create_postlinkedin_browse_feed
04shared/tools/media/
Generates and checks visuals before they enter the queue.
openai_image_generateopenai_image_describe
05shared/tools/core/
Research plus the approval gate on every outbound write.
web_searchpause_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
includeContextPer-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_retrieveA 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_memoryPipeline-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
AI agent questions we get every week.
Will it post without my approval?
No. Every post and comment stops for your approval before it goes out. Approve from your desk or from the overlay on the phone.
Can an agency run many client accounts?
Yes. One agent per client account, each scoped to its own apps, each with its own approval queue, all running in parallel.
Can I automate TikTok and Instagram posting without an API?
Yes. Melaya's Device Control operates a real Android phone: the Social Media Engineer opens TikTok or Instagram, reads the screen, taps and types, and pauses for on-device approval before publishing. The phone bundle covers TikTok, Instagram, and X, so no official posting API is required.
How is Melaya different from Zapier or n8n for social media automation?
Zapier, n8n, and Make execute predefined trigger-action steps and depend on each platform's API. Melaya, the visual AI agent builder, runs autonomous multi-agent workflows: agents plan across steps, work TikTok and Instagram from a real phone, and pause for human-in-the-loop approval on every write. Zapier and Make still win on connector breadth for simple linear automations.
How do I audit what an AI agent posted for a client?
Melaya records full run traces: every screen read, tap, draft, and outcome is logged per step, and every published post maps to an approval a human granted. Agencies review traces per client account, and deterministic-first evaluation runs rule-based checks on drafts before any model-graded scoring.
Can I reuse the same posting workflow across client accounts?
Yes. Save any run as a reusable template on Melaya's canvas of agents, tools, triggers, and approval gates. The Content Strategist plans the cadence once, then the Growth Engineer clones the pipeline per client, each copy scoped to its own apps and holding its own approval queue.
How does the agent write replies in my voice?
The Copywriter drafts posts and replies grounded in your past content and brand guidelines through Melaya's RAG memory, and the Brand Architect keeps every account on-brand across platforms and clients. Each draft still waits in your approval queue, so you edit tone before anything ships in your name.
Will automated posting get my accounts flagged?
Melaya reduces that risk by behaving like a person: the Social Media Engineer opens the real app on a real phone, posts at a natural pace, and the Growth Engineer runs warm-up schedules you control for new accounts. No tool can guarantee platform decisions, so keep cadence conservative and approve every post.
Which AI models plan and write the content?
You choose per step. Melaya routes each step across 49 providers, cloud or local: a strong model can plan the queue while a cheaper one drafts replies, and sensitive steps can run on your local runner. Per-step model routing keeps cost per accepted result low, and full run traces show what each step spent.
How do I set up a social growth crew in Melaya?
Drop the Social growth crew onto Melaya's visual canvas: the Content Strategist plans the queue, the Copywriter drafts posts, the Social Media Engineer works TikTok, Instagram, and X from your phone, and the Growth Engineer sets the schedule. Attach the phone, social, media, and core bundles, then approve the first posts from your queue.
Build creators, influencers & social agencies 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
// Cookies
Melaya uses a small set of first-party cookies that are strictly necessary to authenticate you, maintain your session, and protect the platform from abuse. We do not use advertising cookies, cross-site trackers, or third-party analytics by default. The full cookie list is in our Privacy Policy.