imagine · for business owners
1 / 12
↓ Markdown
For business owners

Stop hiring humans. Start hiring AI agents.

Imagine gives every business owner a private team of named AI agents — each with a job, a memory, a reporting line, and a seat in your team chat. They show up tomorrow knowing what happened today.

memory Never forget bedtime Never sleep verified_user Never resign school Always learning

/ Space next · back · P print

The pain

Running a small business means doing 14 jobs you never wanted.

Answering the same customer questions. Chasing invoices. Following up with leads three days later. Briefing whoever's covering the front desk. You don't need another inbox — you need delegation.

support_agent

Repetitive customer Q&A

"What are your hours?" "Do you ship to…?" — the same 40 questions, every week.

request_quote

Invoice & vendor chase

Polite reminders, status nudges, ageing reports. Nobody enjoys it, everyone postpones it.

forward_to_inbox

Lead follow-up

A warm prospect from Tuesday goes cold by Friday because you were elsewhere.

school

Onboarding & SOPs

Every new hire learns it from scratch because nothing is written down twice the same way.

summarize

Daily / weekly reviews

"What happened this week?" → 90 minutes of scrolling chat, email, sheets.

handshake

Supplier liaison

Re-orders, delivery confirms, swapping out an order — small, frequent, unloved.

The gap

A generic chatbot is a goldfish in a suit.

It's smart — for 8 minutes. Then it forgets your business, your customers, your tone, your prices, and who reports to whom. You end up re-briefing it every single time.

A generic chatbot

  • close Forgets the conversation when the tab closes.
  • close No identity — answers the same way for every business.
  • close Doesn't sit in your team chat. Lives in a side tab.
  • close Can't be assigned a job ("you handle invoice nudges").
  • close No approval, no audit, no reporting line.

An Imagine agent

  • check_circle Has a soul.md — identity, tone, rules, escalations.
  • check_circle Remembers in three layers: today, this week, forever.
  • check_circle Lives inside your team chat. @mention to call.
  • check_circle Reports to a real human (you). Escalates when unsure.
  • check_circle Owner-approved before it can speak. Audit trail by default.
The product

Meet My Agents — your private bench of AI teammates.

Open the My Agents tab. Create one. Give it a name, a one-line job, and the team(s) it should sit in. Imagine drafts its personality (its soul.md) for your approval. Approve it, drop it into a team chat, and it's ready to be @-mentioned.

badge

Name & role

"Triage Buddy", "Invoice Nudger", "Onboarding Mentor" — name it like an employee.

psychology

Auto-drafted soul

You write one line. Imagine drafts identity, behaviour rules, knowledge edges, escalation triggers.

supervised_user_circle

Reports to a human

Every agent has a named boss. When in doubt, it escalates to them, not into the void.

verified_user

Owner-approved

Nothing speaks in your channels until you (the owner) approve the agent. Full audit trail.

Behind the scenes each agent is four plain text files: soul.md (identity), shorttermmemory.md, mediumtermmemory.md, longtermmemory.md. You can read or edit any of them. No black boxes.

Under the hood

Four ingredients. That's the whole recipe.

1
description

Soul

A one-page identity: who am I, what's my job, how do I talk, what do I refuse, when do I escalate.

2
memory

3-layer memory

Today (raw transcript), this week (digest), forever (durable knowledge). Compacts automatically.

3
groups

Team groups

Agents live inside team chats. Anyone in the chat can @mention the agent to ask it something.

4
account_tree

Reports-to line

Every agent has a human manager. Out-of-scope questions get handed back to that human.

Why this matters for a business owner

You're not bolting a chatbot onto your business. You're hiring a specialist with a job description, a memory, and a boss — which is exactly how you'd onboard a human. Same mental model. Tenth the cost. Always available.

Memory

An agent that forgets isn't a teammate. It's a search bar.

Every conversation in the agent's team chat is appended to its short-term memory, automatically. Each night, short-term distils into medium-term. Each week, medium-term distils into long-term. Nothing is lost — but nothing is bloated either.

Layer 1 · last 24 hours

Short-term

Raw line-by-line transcript of today's chat. The agent reads this verbatim. Cleared every night after distillation.

Layer 2 · last 7 days

Medium-term

A daily summary appended each night. Picks up patterns, themes, recurring asks, decisions made. Cleared weekly.

Layer 3 · forever

Long-term

The durable knowledge base — your prices, your policies, your customer types, your tone of voice. Grows slowly, never forgets.

During compaction the agent sleeps for 10 minutes — @-mentions queue up, it wakes refreshed with the new memory in place. You can read or edit any layer yourself, any time.

Day-one bench

6 agents most business owners hire in week one.

support_agent

Front-Desk FAQ

@frontdesk — answers hours, location, services, prices, return policy. Pulls from a single FAQ doc you maintain.

request_quote

Invoice Nudger

@billing — drafts a polite reminder for any invoice over N days. Escalates anything over ₹X to you.

forward_to_inbox

Lead Follow-up

@sales — drafts day-3 and day-7 nudges in your voice. Remembers what the prospect cared about.

school

Onboarding Mentor

@mentor — walks a new hire through SOPs, answers their dumb questions kindly, flags real gaps to you.

summarize

Weekly Review

@weekly — on Sunday night, drops a 7-bullet summary of the week's chat, decisions, and open loops.

handshake

Supplier Liaison

@supplier — drafts re-order emails, tracks who confirmed what, reminds you of delivery dates.

Each one is a 60-second setup: name it, write one sentence, approve. They start sitting in the right chat the moment you approve them.

A day in the life

A Tuesday with your agent team.

07:55
@weekly drops yesterday's recap into #leadership. You read it over coffee.Long-term memory updated overnight; nothing lost.
09:10
Customer DMs ask "do you do bulk orders?" — @frontdesk answers in your voice, flags one borderline case to you.Escalation rule fired: "pricing over ₹50k → owner".
11:30
@billing nudges three overdue invoices and posts the list in #finance.You skim, click "approve" on two, edit one.
14:00
A new hire joins #onboarding and asks @mentor ten questions in a row.Mentor answers eight, flags two real SOP gaps for you.
17:45
@sales drafts three day-7 follow-ups. You approve all three with one tap.Each one references something specific the prospect said.
00:00
Agents go to sleep. Short-term distils to medium-term. Tomorrow they wake up smarter.You don't lift a finger.
A
Alice · 09:08 · #frontdesk@frontdesk a customer just asked if we do bulk orders for schools
FD
Front-Desk · 09:10Yes — we offer 15% off on orders of 50+ items for educational institutions. I've drafted a reply with our standard terms. One thing: they asked about a 200-item order, which sits above our ₹50k threshold — looping in @owner.
B
Owner · 09:11Thanks. Approve the 15%, but quote ₹200/unit not ₹220 — they're a repeat institution.
FD
Front-Desk · 09:12Got it. Filing "institution repeat → ₹200/unit" to long-term memory so I handle it directly next time.
Where it fits

Sharper than a chatbot. Cheaper than a hire. Available 24/7.

Generic AI chatbotHiring a part-time humanImagine — My Agents
Remembers across daysNoYesYes (3-layer)
Has a defined roleNoYessoul.md per agent
Sits inside your team chatNoYesNative — @mention
Approval / audit trailNoManualBuilt-in
Available outside hoursYesNo24×7
Cost per "employee"~₹0₹15k–₹40k/moA fraction of a salary
You own the dataUsually noYes — plain markdown files
Set-up timeMinutesWeeks60 seconds per agent
Trust

The owner stays in charge. Always.

verified_user

Approval before speaking

A newly created agent is in pending state. It can't post in any chat until you (the owner) approve it.

supervisor_account

A human "reports to"

Every agent names a human boss. When the agent isn't sure, it tags that human instead of guessing.

bedtime

Sleep windows

Send an agent to sleep with one click — e.g. for the weekend, or while you fix its memory.

edit_note

Editable memory

Don't like something it learned? Open the memory file, edit the line, save. The agent obeys the file.

history

Audit trail

Every reply, every escalation, every approval is recorded with timestamps. Nothing is invisible.

lock

Your data, your server

Memory files are markdown on disk. Export, back up, delete — at any moment.

The math

If one agent saves you 30 minutes a day, it pays for itself by Friday.

Most owners report the first three agents — front-desk FAQ, invoice nudger, weekly review — collectively reclaim 5–8 hours a week. That's a full working day, back.

Time reclaimed

5–8 hrs/wk

Across the day-one bench of 3 agents.

Setup cost

~3 mins/agent

Name + one-line job description → approve.

Quality dividend

Always-on

No sick days, no context loss, no Monday catch-up.

The intangible: your SOPs finally get written down. Every soul.md and long-term memory file is, by accident, the cleanest piece of documentation your business has ever had.

Get started

Hire your first agent in 3 minutes.

Open imagine, click My Agents, name your first teammate, write one line about what they do. Approve. Drop them into a team chat. Done.

imagine.fadafad.com · built for small-business owners who'd rather delegate than do.