Blueprints

Upload videos to a storage folder. This automation polls the folder on a schedule, picks the oldest unprocessed clip, generates an engaging Facebook caption with Groq AI, and posts it to a specified Facebook Page using the Graph API. Uses the pages_manage_posts scope exclusively — no Page reads beyond confirming the post ID. Optional Telegram approval gate: before posting, the workflow sends a three-button message (Approve / Regenerate / Reject) with a caption preview, privacy setting, paid-partnership disclosure, and queue remaining count. Approve posts immediately. Regenerate creates a new AI caption with a fresh angle and asks again (capped at 2 retries). Reject marks the file processed without posting and stores rejection metadata. When the queue is empty, the workflow sends an informational Telegram message rather than silently no-op'ing — you always know when there is nothing to post.

Upload 9:16 vertical videos to a storage folder. This automation polls the folder on a schedule, picks the oldest unprocessed clip, generates an engaging Reel caption with Groq AI, and publishes it to your connected Instagram Business account as a Reel via the Graph API's 2-phase publish flow (container creation → status poll → publish). Uses only two approved Instagram scopes: instagram_business_basic (to fetch your @handle and confirm the published post) and instagram_business_content_publish (to create + publish the Reel). Does not read comments or messages — those scopes are intentionally dropped per our scope-minimisation policy. Optional Telegram approval gate: before posting, the workflow sends a three-button message (Approve / Regenerate / Reject) showing your @handle, caption preview, Music Usage Confirmation line, Paid Partnership disclosure, and queue remaining count. Approve posts immediately. Regenerate creates a new caption with a fresh angle (max 2 retries). Reject marks the file processed without posting. When the queue is empty, the workflow sends an informational Telegram message rather than silently no-op'ing — you always know when there is nothing to post.

Upload short videos to a storage folder. This automation polls the folder on a schedule, picks the oldest unprocessed clip, generates a TikTok-optimised caption with Groq AI, and posts it to TikTok using either the Direct Post API (video.publish — posts straight to your profile) or the Drafts Inbox API (video.upload — uploads to your TikTok drafts so you can post from the app later). A per-automation demo mode lets you run one scope, the other, or both. Optional Telegram approval gate: before posting, the workflow sends a three-button message (Approve / Regenerate / Reject) with a preview of the caption. Approve posts immediately. Regenerate creates a new AI caption with a fresh angle and asks again (capped at 2 retries). Reject moves the file out of the queue and writes a sidecar JSON with the rejected caption for later review. Sandbox note: TikTok blocks PUBLIC_TO_EVERYONE and MUTUAL_FOLLOW_FRIENDS privacy levels in sandbox mode. Default privacy is SELF_ONLY, which works in both sandbox and production.

Upload a CSV recipient list to the queue folder. Each CSV row is one recipient: columns `phone,name` (required) plus up to 4 optional template-parameter columns. This automation polls the folder, picks the oldest unprocessed CSV, parses it, and sends a pre-approved WhatsApp template message to every recipient — rate-limited to stay within Meta's per-number delivery ceilings. Approval model is different from posting blueprints: batch-level (one Approve/Cancel per campaign). No regeneration (templates are pre-approved in Meta Business Manager; parameters are per-recipient). Each send has its own success gate — failures are logged and reported in the summary, but don't abort the campaign. Rate limit: configurable sends-per-minute (default 10, max 60). Wait node enforces pacing between sends so you don't trip Meta's throttling. When the queue is empty, the workflow sends an informational Telegram message rather than silently no-op'ing.

When a customer sends a WhatsApp message to your registered Business Phone Number, the platform centralised webhook at /api/webhooks/whatsapp routes it to this automation (Architecture B — one Meta webhook URL, many per-tenant automations). **What V2 does differently from V1:** before generating a reply, it fetches the most recent N messages exchanged with that specific phone number from the platform's whatsapp_messages table. The AI sees the running conversation and stays coherent across multiple turns. After replying, it logs the outbound message back to the same table so the next inbound triggers a memory-aware reply. **Limits and caveats:** • Only operates on text messages in V1. Non-text (image, audio, video, document, interactive) gets a polite default reply. • Memory window is configurable (default last 10 messages) — keep small to stay within model context limits and reduce token cost. • Reply is free-form text, only valid within Meta's 24-hour customer-service window. If the user has been silent for >24h, the API will reject the send with code 131047 and the reply will be logged as failed. • No template fallback in V1. For outside-window engagement, use the Campaign Publisher blueprint with a pre-approved template instead.

Drop videos into your queue folder. On a schedule (or on demand), this automation picks the oldest unpublished clip, generates YouTube metadata with Groq AI (title, description, tags), and sends a three-button Telegram approval message with the drafted metadata and a preview link. Approve to publish. Regenerate to get a fresh angle on the metadata (capped at 2 retries). Reject to move the file out of the queue with a rejection note — it will not re-enter the queue. On approval, the workflow: • Uploads the video to your YouTube channel (unlisted by default) • Logs the post to the Google Sheet you nominated (timestamp, file, title, YouTube URL, channel, and placeholders for calendar + drive IDs) • Stores a plain-text summary in your Google Drive • Creates a 30-minute review event on your Google Calendar 48 hours out, so you remember to check views and comments • Sends a notification email from your own Gmail to the address you specified, so your team or stakeholders know the post is live Shorts and long-form videos both work. Drop vertical clips (9:16) under 3 minutes and YouTube publishes them as Shorts. Drop wider or longer clips and they publish as standard videos. YouTube classifies automatically — you don't need a setting or tag. Every step is auditable. If YouTube upload fails, the file stays in the queue (not marked published), you get a Telegram failure alert with the error details, and no Workspace writes happen. Built for coaches, agencies, course creators and SMB marketing teams who post to YouTube regularly and want a team-wide record + follow-through loop without manual coordination.