Marketing leadHuman
run the blog workflow for the spring launch, audience is ops leads
Case Study
A multi agent content system that lives in Slack. It keeps the calendar full, researches, drafts, reviews its own work, and files the finished piece to Notion with a full audit trail. A person approves every step.
One run, start to finish
01
The old shape of the work: research the topic in a browser, write the draft, paste it into Notion in the right place, then log what was done. Several times a week, across three brands.
Marketing leadHuman
run the blog workflow for the spring launch, audience is ops leads
02
Workflows are Notion pages, not code. The team writes new ones themselves, so the system grows without waiting on a developer.
AgentOrchestrator
Loaded the blog generation playbook. Twelve steps, with approval points along the way.
Confirming brand, topic, audience and publish date before I start.
03
One agent, and only one, is allowed to read Notion. It returns source material verbatim, without interpreting it, so nothing is invented on the way in.
AgentFetcher
Pulled brand strategy, the ICP, voice guidelines and competitor references.
04
Every brand accumulates near duplicate posts over time. The agent checks the existing library and the dedup ledger before writing a word.
AgentOrchestrator
This overlaps an existing post. Proposing a different angle instead.
Want me to go ahead with the new angle?
05
The validator reviews the draft against the source material and returns approve or revise with specifics. That loop runs inside the agent team, so a person never sees a raw first draft.
AgentValidator
REVISE. Some claims are not supported by the retrieved sources, and the intro drifts from the brand voice.
Redrafted and rechecked. Approved on the second pass.
06
This is the whole safety model. The agent pauses and asks in the thread, and the run stops there until someone answers. Gates ship on by default, and only the client decides if the agent has earned looser ones.
AgentOrchestrator
Draft is ready for review.
Waiting on a person
Feedback sends the step back to be redone. Nothing is written anywhere until someone approves.
07
Alongside the deliverable the agent keeps a task log in Notion, a step by step record of exactly what it did. Publishing stays a human step. The agent stops at ready to publish.
AgentOrchestrator
Filed the deliverable, wrote the task log, marked the card ready to publish.
Under the hood
Splitting the work across specialists is what makes it affordable and what makes it checkable. The cheapest model that can do a step is the one that does it, and the most capable one is spent on review.
Runs the thread
Receives the Slack message, steps through the playbook, coordinates the three specialists, and manages the approval cycle.
Fast model
Retrieval only, and the only agent allowed to read Notion. Returns source material verbatim, without interpreting it.
Mid tier model
The writer. Drafts the piece, prepares the metadata, writes the art direction brief, and assembles the handoff package.
Highest capability, used sparingly
Quality control before a person is involved. Returns approve, or revise with a specific list of problems to fix.
A second workflow acts as the planner. It keeps each brand's content calendar populated, runs dedup across the whole calendar rather than one post at a time, and dispatches the production workflow when a scheduled slot comes due. The team asks for a batch of content instead of a post.
How it went
01
Under two weeks, four working sessions to map the bottleneck.
We watched the real workflow and found the one that ate the most time.
02
Built, deployed and tested in two weeks.
Built against their actual Slack and Notion setup, with approval gates from day one.
03
Running in their workspace, tuned with their feedback.
Doing real work, refined from how the team actually uses it.
Your team has a workflow shaped like this one. The first step is finding out which one is costing you the most.
Start with the €500 Audit