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.
You ship the Tuesday issue at midnight Monday because research, drafting, and the social cutdown all land on the same person, and the Friday issue slips one week in three.
A 2,500 dollar sponsor read goes out with a wrong product link because nobody proofread the placement, and the brand asks for a partial refund inside an hour.
Reader replies pile up in the inbox for three weeks, the paid tier gets one Q and A instead of four, and churn ticks up the next renewal cycle.
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.
ContentStrategist mines your reader replies, RSS feed list, and the last 20 issues for the angles that already converted, then proposes four ranked drafts with a hook line each. Static context pins your voice guide so the brainstorm never drifts off brand.
Pull source articles, founder posts, and sponsor context into a structured brief with cited paragraphs and quote candidates. The rag_retrieve tool reads your back catalog so the angle does not repeat what you already shipped last quarter.
Copywriter writes the subject line, three A/B variants, body copy, and CTA grounded in the issue brief. The rag_retrieve tool reads your top performing issues so phrasings reuse what already earned opens. HITL gate on send before anything reaches the ESP.
GrowthEngineer scores inbound sponsor leads, drafts the rate card pitch, and writes the in issue read with product links cited from the sponsor brief. HITL gate blocks gmail_send until you approve copy, placement, and the disclosure line.
Sweep the inbox and reader replies for the week, cluster the top questions, and draft answers grounded in your archive. Cross-run memory carries which questions you answered last month so the paid tier never gets the same answer twice.
SocialMediaEngineer cuts the issue into an X thread, a LinkedIn version, a TikTok script, and three meme angles drafted by MemeArtist. Every publish tool stages through pause_for_human so the cutdown does not ship a stale hook.
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.
Designs the issue concept, writes the cold open hook, structures the section flow, and times CTAs so the send lands instead of getting archived.
Writes the subject line, three A/B variants, body copy, and CTA in the direct response voice trained on the Ogilvy and Halbert tradition.
Designs the referral loop, seed list, sponsor pitch sequence, and paid amplification plan against a target K factor above 1.2.
Checks every asset against your stated voice, banned phrases, and visual hierarchy, and names the inferred assumptions when guidelines are missing.
Turns each issue into per platform threads, hashtag plans, and posting windows for X, LinkedIn, TikTok, and YouTube Shorts.
Picks the canonical meme template that fits the issue angle, writes original captions inside the slot count, and renders one image per turn.
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.
Load your back catalog, voice guide, banned phrases, top performing tweets, and reader replies into the per workflow store. Writes happen at build time, no HITL gate needed because nothing leaves your tenant.
Pull source articles, sponsor product pages, and competitor sends for ContentStrategist briefs. Read only, scoped per agent to the allowlist you set.
Track a curated feed list for the weekly brainstorm and the link section. Read only, no publish path from this bundle.
Mine X for angles and reader questions, then stage the issue thread cutdown. twitter_post is HITL by default so you pull the draft before it ships.
Search LinkedIn for the right surface and stage a personal page version of each issue. linkedin_create_post is HITL by default for this crew.
Mine talks and podcast appearances for quote candidates and angle research. Read only, no publish path from this bundle.
Read sponsor threads and reader replies, prep the sponsor pitch and the paid tier Q and A, and stage every send. gmail_send is HITL by default for this crew.
Generate header art for the send, describe uploaded references for brand QA, and convert long issues to PDF for a paid tier download. openai_image_generate is HITL gated when a publish tool consumes the output.
Let MemeArtist pick the canonical template that fits the issue 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.
General research, structured fetch, and Slack handoff for your own queue. pause_for_human is the explicit approval node you drop on the canvas before any send.
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.
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.
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.
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.
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