Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.kowalah.com/llms.txt

Use this file to discover all available pages before exploring further.

The Kowalah Agent is the front end of the Kowalah experience — delivered right where your team already works. The moment a colleague is sitting in a planning meeting, working on month-end, drafting a board report, triaging customer feedback, or staring at the latest hiring round and thinks “I wonder if AI could help us with this” — they @mention Kowalah. No setup, no platform navigation, no waiting for someone else’s call. This is the same Kowalah that lives in the platform and in Claude Desktop — just wherever the moment of need actually happens.

What it does

The Agent exists to drive AI adoption inside your organization. It helps employees apply AI to the work they’re already doing, in three ways:

1. Answer “could AI help us with this?”

Bring the Agent a real task you’re in the middle of, and it’ll help you figure out how AI could fit. It draws on patterns from across Kowalah’s customer base — what’s worked, what hasn’t, where the friction usually is — and gives you a concrete answer, not a generic feature list.
@Kowalah We do month-end variance analysis every month. How
could we use AI to speed up the commentary writing?
@Kowalah I'm prepping for board reporting tomorrow. How would
you use AI to draft the narrative around the financials?
@Kowalah We're trying to synthesise themes from 30 customer
interviews. What's a good AI approach?
@Kowalah We get 400 support tickets a day. How would you use
AI to triage and route them?

2. Design AI workflows for recurring work

When you’ve got a repeatable task — the Monday board pack, the weekly KPI summary, the monthly customer review — the Agent helps you design an AI workflow for it. It maps the steps, decides what can run in-thread vs. what needs proper build, and either does the work live or scopes it as work for the Kowalah team.
@Kowalah Help me design an AI workflow for our weekly KPI
report. It takes me three hours every Friday.
@Kowalah Before each customer QBR I summarise the last 90 days
of activity. Can we automate this with AI?
@Kowalah I write 15 job descriptions a quarter for new sales
roles. Help me build an AI workflow that drafts them properly.

3. Find where AI fits in your role

When you don’t know where to start, the Agent walks you through what’s on your plate and surfaces 2-3 high-value AI use cases grounded in your work — not a generic role-based template.
@Kowalah Where could AI make the biggest difference for me?
I run finance at a mid-sized professional services firm.
@Kowalah What AI use cases should I be trying first
as Head of People at a 1,500-person manufacturer?

How the Agent helps you act

Once you’ve figured out what you want to do with AI, the Agent has three ways to help you act on it:
  • Find an accelerator — search Kowalah’s global library plus your organization’s private library for an existing prompt, GPT, training, or workflow that already solves your problem. If something’s there, you can run with it now.
  • Run it together in the thread — for analysis, synthesis, and drafting work that the Agent can do directly, it’ll do the work live with you and iterate on the output.
  • Raise an Opportunity — when the work needs proper scoping, ongoing tracking, or specialist help from the Kowalah team, the Agent captures it as an Opportunity. Kowalah’s team triages from there into a Deliverable, an Expert Request, or a new Project — you don’t have to decide upfront.
The Agent always asks before raising anything and describes exactly what it will write. It can also look up status across your portfolio when you want it:
@Kowalah What's waiting on me across projects right now?
@Kowalah Do I have any pending discoveries to respond to?

How it works

When you @mention Kowalah in a thread:
  1. The Agent acknowledges within seconds
  2. It reads your workspace context — your role, your projects, what you’re a stakeholder on, any pending discoveries
  3. It engages with the AI question, suggests an approach, checks the accelerator library, and helps you move forward
  4. Follow-up messages in the same thread continue the conversation — no need to repeat context
The shape of every conversation: understand the work → suggest an AI approach → find an accelerator or design a workflow → (sometimes) raise an Opportunity.

What your role changes

Your organization role affects what the Agent can see for you, not what it can do. Anyone in the organization can ask AI questions, design workflows, and raise an Opportunity.
RoleWhat you see
AdminEverything in your organization
Core teamEverything in your organization
MemberOpportunities you raised, and projects, deliverables, and Expert Requests you’re a stakeholder on
Pending discoveries are personal — you always see your own invites, regardless of role.

Supported platforms

Slack

Channels, threads, and DMs

Microsoft Teams

Channels, group chats, and personal

Google Chat

Spaces and conversations

Using the agent

Detailed guide on what you can do and how to get the best results