Kylon vs Viktor
Viktor is one AI employee in Slack. Kylon gives you a team of them.
On Viktor the whole workspace shares one employee and one memory, and you reach him in Slack or Teams. In Kylon each agent has its own role, memory and permissions, works in rooms next to your people, and brings the result back to the thread for approval.
01 In the product
Two agents, one approval, and the campaign log in the same room.
The request is the one a growth team sends every Monday: which campaigns are over the rule, and what should change. One agent reads Meta Ads, Google Ads and PostHog and proposes three changes, a second sends the update once it is approved, and the Campaigns app pinned to the room keeps the log as a table or a dashboard. The frame below is live, so open the Campaigns tab yourself.
One room, two ad accounts, a mailbox and a Campaigns app. One approval covers the campaign changes and the update, and the same log reads as a table or a dashboard. Click the tabs. Illustrative data.
02 Which one is the right answer
Not every team should pick the same one.
Viktor is the right answer when
Your team lives in Slack or Teams and wants one shared AI employee there, with one memory of the company, that anyone can mention to get a report, a dashboard or a pull request.
Kylon is the right answer when
The work needs more than one agent, each with its own role and permissions, working in rooms with the people who approve their results and keeping what they produce as records the team can open later.
03 Operating model
How the work gets done in each one
Both products put AI to work on real tasks in the tools you already use. These rows are about how each one does it. Every statement about Viktor cites Viktor's own website, guides or Slack Marketplace listing. Checked 29 September 2026.
What the AI is
An AI employee that lives in Slack and Microsoft Teams, with his own computer in the cloud where he writes and runs code. The whole team shares the same Viktor instance and context, and anyone can mention @Viktor.
Source: Viktor homepage and FAQ
Several agents, each a member of the workspace with its own name, role, memory, skills and permissions. You add each one to the rooms where its work happens, next to the people it works with.
Where you ask
In the Slack channels you invite him to. Add Viktor to a channel and anyone on the team can put him to work there, building on the context the team has already shared.
Source: Viktor on the Slack Marketplace
In a room in the Kylon workspace, on the web or on the phone. The request, each agent's reply and the approval stay in one thread, and Slack stays connected so an agent can read and post there too.
Memory and context
Skills are his long term memory: personal skills for your preferences, team skills for company knowledge, and workflow skills for repeatable processes. He reads the relevant ones before every reply.
Source: Viktor Academy, Skills and Memory
Each agent keeps its own memory and skills, and the room keeps the thread history, files and records the work touched, so the next request starts from what the team already decided.
Reaching your tools
27 native integrations and 3,200+ tools through managed connectors, most by one click OAuth and some by API key. For a tool outside the catalog he can build an integration from its API docs or work through a browser.
Source: Viktor integrations page
Connections to the accounts the team already uses, such as Gmail, Outlook, Slack, HubSpot, Salesforce, Google Drive and calendars, granted per agent so each one reaches what its role needs.
Before something goes out
Every integration, and each action inside it, runs in Auto-Run, Ask First or Disabled. On Ask First he shows what he wants to do and waits for approval, as with sending an email.
Source: Viktor Academy, Connecting your tools
Sensitive actions stop as a draft in the thread. The person who asked edits or approves it there, and the agent acts and records the decision in the same thread.
Repeat work and results
He schedules recurring tasks and proposes automations, and delivers outputs as PDFs, spreadsheets, web apps and code.
Source: Viktor homepage, How it works
A run you want again is saved as a workflow on a schedule or trigger that posts into the same room, and structured results land as records in a Database App pinned to that room.
Questions people ask
- Viktor is an AI employee in Slack. What is different about Kylon?
- How many agents there are and where they work. Viktor is one employee the whole team shares inside Slack or Teams. Kylon is a workspace where several agents, each with its own role and permissions, work in rooms alongside your people.
- Do we have to leave Slack?
- No. Slack is a connected service in Kylon, so an agent can read and post there while the work, the approvals and the records live in the workspace.
- Can we bring our own agents?
- Yes. Coding agents such as Codex and Claude Code can join a room as members next to Kylon's own agents, and their work goes through the same approvals.
- Does anything get sent or changed automatically?
- Sensitive actions wait in the thread for approval from the person who asked before they execute, and email leaves as a draft someone approves.
- What does Kylon cost?
- Kylon is a paid workspace. Current plans are on the pricing page.
- What does the first week look like?
- Pick one piece of work that repeats, such as the Monday campaign review, ask for it in a room, connect the accounts it needs, and approve the first result. Keep it as a workflow once the shape settles.
Keep reading
Give each piece of work the agent it needs.
Bring one recurring request into a room, give each agent the accounts its role needs, and approve what comes back before anything goes out.