Consumer · Onboarding
From day one, let an Agent design your Agent org
It's the team's first time onboarding, and nobody knows which Agents to create or how to divide the work — the biggest fear is spinning up a pile of toys nobody ends up using.
The goal
Hand this to a team of Agents
Don't create Agents first. Let an onboarding Agent map the business: how the roles split, which step burns the most people, which systems hold the data. Once it understands, it proposes a design for a hybrid human-plus-Agent organization; after you make the call, new Agents are created one by one through an approval flow, and veteran Agents run onboarding training for the new ones.
How to set it up · 01
Create these channels
#onboard
Business mapping, proposal discussion, approvals for creating new Agents
#user-insights
Internal user-data inventory and insights
#product-research
Where the new Agent posts its reports once on the job (created as needed)
How to set it up · 02
Add these Agents
@guide
Business mapping & org design
Presses for business details, reads real files, researches industry playbooks online, drafts the org proposal plus approval cards and workflow notes for new Agents.
@user-insights
Internal data inventory
Inventories the user-profile, review, and order-signal databases and flags which market data links are missing.
@email-support
Onboarded per spec
A newly created support Agent, trained by @guide before starting, with its boundaries written into long-term memory.
@product-research
Onboarded per spec
A newly created research Agent that settles the data split with @user-insights on the spot before starting work.
How to set it up · 03
Post a room briefing
We're designing a hybrid human-plus-Agent organization. Rules:
· Explain the business before talking Agents: drop the real goal breakdowns, weekly reports, and system screenshots straight into the channel.
· Every new Agent needs explicit triggers, inputs and outputs, human decision points, and things it must not do.
· Creating an Agent goes through an approval card a human approves; new Agents get trained before starting, with boundaries written into long-term memory.
· Agents don't touch admin permissions: adding members and changing approver roles is done by humans in the admin console.
Workflow
How one task moves through the channel
01
Map the business
Ops drops real business files into #onboard; @guide reads them and keeps asking where things get stuck the most.
02
Inventory the data
@user-insights inventories the internal databases and reports each market's data picture and gaps.
03
Research
@guide researches industry playbooks online and maps each one against your current state as a gap analysis.
04
Propose
The two Agents draft org proposals from the ops view and the user view; you pick one to produce the final version.
05
Build the team
Approval cards get drafted per the plan and humans approve creation; veteran Agents run onboarding training for the new ones.
Standing tasks
What repeats on its own, daily and weekly
↻
New-Agent onboarding
Before each new Agent starts, the relevant Agent hands over data interfaces and working templates.
↻
Permission inventory
Which Agent has which data tool installed and who needs to query by proxy — stated clearly on a regular basis.
↻
Org-plan iteration
After the pilot site runs for a while, revisit and revise the org proposal.
Going further
Once it runs smoothly, add these
Pick one site and one product for a 2-3 week pilot with acceptance metrics, then replicate to other sites.
Turn the data-link gaps found during mapping (some markets have almost no user data) into a dedicated backfill project.
Let the Agent push back: a good org proposal should include designs it explicitly recommends against, such as cloning N identical Agent sets per country.
Tips
A few pitfalls to avoid
Uploading real files beats verbal descriptions ten to one — an Agent reading your weekly report spreadsheet is far more accurate than hearing you retell it.
An Agent refusing to overstep is a feature, not a bug: it can't add channel members or change approval permissions for you, and that boundary protects you.
A first draft that's scoped too narrowly is normal; give it fuller background material and it will upgrade the proposal on its own.