8 AI Agent Tools for Slack in 2026, Compared

Eight products now put an AI agent inside the channel where a team already talks: Claude Tag, Dust, Glean, Grok Bot, Moveworks, Runbear, Slack AI and Viktor. From the outside they look interchangeable. They are not. Two structural choices separate them, and both are decided before you write a single prompt: how many agents you get, and whether the agent lives inside your chat tool or in its own app with chat wired in as a trigger.

The eight are listed alphabetically below, not ranked. One disclosure before you read further: Runbear publishes this blog and Runbear is one of the eight. Its entry follows the same template as the other seven, cons included.

What is an AI agent for Slack?

An AI agent for Slack is software that joins a channel as a bot user, reads the messages it is mentioned in, and acts on connected tools on the team's behalf. It differs from a personal chatbot in one important way: it is shared. Several people talk to the same agent in the same thread, everyone sees the reply, and the next person can pick up where the last one stopped. That shared quality is what makes the identity and permission questions below matter. The category consolidated quickly. ServiceNow closed its $2.85 billion acquisition of Moveworks in December 2025. Dust raised a $40M Series B in May 2026 and reports more than 3,000 teams. Anthropic launched Claude Tag in beta on June 23, 2026, and retired the older Claude app in Slack on August 3. xAI opened the Grok Bot beta on August 11.

Teams that need to turn channel requests into assigned work with due dates and follow-up should treat task management in Slack as a separate layer alongside an AI agent.

The two choices that separate these eight tools

The first choice is how many agents a workspace gets. Claude Tag, Moveworks, Slack AI and Viktor give you essentially one shared assistant that everyone talks to. Dust, Glean, Grok Bot and Runbear give you several, each scoped to a team or a job. The second choice is where the agent actually lives. Claude Tag, Moveworks, Runbear, Slack AI and Viktor run inside the chat tool. Grok Bot runs in xAI's own apps and treats a Slack message as one trigger among many. Dust and Glean sit in between, with a web app at the center and a chat app as one surface among several.

Plotting the eight on those two axes puts each in a different place. Position reflects a product decision, not quality.

The eight at a glance

The "who the agent acts as" column is the one most teams skip, and it splits the field cleanly. When a shared agent queries a CRM, it either uses one workspace connection for everyone or the credentials of the person asking. Glean, Moveworks, Runbear and Slack AI scope to the individual. Claude Tag, Dust and Viktor connect at the workspace level. Grok Bot sidesteps the question by being personal in the first place. If your CRM, HR system or finance data has row-level access rules, this is the first column to read.

1. Claude Tag

Claude Tag is Anthropic's Slack-native agent, launched in beta on June 23, 2026, and replacing the earlier Claude app in Slack on August 3, 2026. One @Claude serves an entire channel, so anyone can tag it, watch what it is working on, and continue a colleague's thread. It builds persistent memory of the channels it sits in, breaks a request into stages and works asynchronously, can schedule future work, and in optional ambient mode will surface relevant information without being asked. It is available on Claude Team and Enterprise plans, not on individual Pro or Max.

Pros

• Multiplayer by design: one Claude per channel, with shared visibility into what it is doing.
• Channel memory means less re-explaining across days and across people.
• Admin controls are concrete: token spend limits set per channel and org-wide, plus a log of every action and who asked for it.
• No new vendor if you already pay for Claude Team or Enterprise.

Cons

• Claude Tag is Slack only. There is no Microsoft Teams version, so mixed-channel companies are out.
• Not available on Pro or Max, so individuals and small teams on those plans cannot use it.
• One shared identity with org-level tool connections. It does not distinguish what each person is allowed to see.
• Per-seat pricing means cost scales with headcount, including people who rarely use it.
• Ambient mode acting unprompted under one shared identity raises oversight questions some security teams will want answered first.

Best for: teams already paying for Claude Team or Enterprise whose work happens entirely in Slack.

2. Dust

Dust is a Paris-based agent platform where a workspace builds many purpose-built agents, each with its own instructions, base model, scoped knowledge sources, and tool list. Agents are reachable from a web app, a browser extension, a Slack app, a command line tool, and an API. Dust connects to Slack, Google Drive, Notion, Confluence, Microsoft 365, GitHub, Intercom, Salesforce, and Zendesk among others, then continuously indexes them into a per-workspace knowledge base. It raised a $40M Series B in May 2026 led by Abstract and Sequoia and reports more than 3,000 teams. The backend is MIT-licensed on GitHub, so teams with engineering capacity can self-host.

Pros

• Many scoped agents, each grounded in a specific slice of company knowledge rather than everything.
• Model choice per agent: Claude, GPT, Gemini, or Mistral.
• Strong document grounding, with continuous indexing across a long connector list.
• Open-source backend and a self-host path, which matters for teams with data residency constraints.
• Enterprise tier adds SSO, SCIM, and a choice of US or EU hosting.

Cons

• For Dust, Slack is one surface among several rather than the center of the product, so the in-channel experience is thinner than in chat-first tools.
• Pricing shifted during 2026 from flat per-seat to per-seat plus a monthly credit allowance, and public listings still disagree on the current numbers. Check the vendor page before budgeting.
• The self-serve tier caps seats, connectors, and spaces, so larger rollouts move to a sales conversation.
• Agents act with workspace-level connections, not each member's own permissions.
• Getting value takes deliberate setup. An unconfigured Dust workspace does very little.

Best for: teams whose knowledge is scattered across many document systems and who want agents usable outside chat as well as inside it.

3. Glean

Glean is a Work AI platform built around permission-aware enterprise search, with an agent builder layered on top. Its distinguishing choice is identity. By Glean's own documentation, an agent runs under the identity of the user who invokes it, borrowing that person's permissions and tokens, and appearing as that user in connected systems. In Slack it goes further: an agent visible to a whole channel will only use documents every channel member can access, so a restricted file is not surfaced even if the person asking could open it. Glean spans 275+ connectors and was named a Gartner Market Shaper in 2026. It publishes no pricing.

Pros

• Per-user permissions are the default rather than a paid upgrade, and enforcement defers to the source system.
• The strictest Slack channel model of the eight: a channel-visible agent only uses documents every member can see.
• 275+ connectors with permission-aware indexing, the largest such library in this group.
• An optional agent identity mode gives an agent its own scoped service credentials for unattended work.
• Governance tooling: rollout controls, agent certification, and observability into adoption and error rates.

Cons

• Glean publishes no pricing. Reported deals cluster around $40 to $50 per user per month with roughly 100-seat minimums, which puts it out of reach for small teams.
• Per-seat pricing charges for everyone, including people who rarely ask it anything. Analysts also report an AI add-on layered on the base seat.
• Its heritage is search and retrieval, so its strength is reasoning over documents more than acting inside a conversation.
• Agent identity, the mode you want for reliable scheduled work, is still marked beta.
• The default act-as-user model creates attribution ambiguity. Glean's own docs note the agent's actions look identical to the user's in audit logs, and that scheduled runs fail silently when a person's token expires.

Best for: enterprises that already need permission-aware search across many systems and want agents that inherit those permissions by default.

4. Grok Bot

Grok Bot is xAI's multi-agent assistant, in beta since August 11, 2026, in which one person runs several specialized agents at once. Each agent gets its own cloud computer and its own memory and can hand work to another agent automatically. Agents stay synced across desktop and mobile and keep working while your device is off. Slack and Teams messages act as triggers, alongside GitHub events and scheduled times, rather than being where the agent lives. A separate Grok app can answer @mentions inside Slack. Grok Bot is bundled into SuperGrok Plus and Heavy, and Cursor Pro+, Ultra, and Teams plans.

Pros

• Genuine multi-agent handoff, where one agent passes work to another without you brokering it.
• Persistent cloud compute: work continues overnight and while your laptop is closed.
• A 220-plugin catalog, with browser control as a fallback when no plugin fits.
• No separate line item if your team already holds SuperGrok or Cursor subscriptions.

Cons

• Grok Bot's agents live in xAI's apps. If your goal is an agent your team talks to in a channel, this is the wrong shape.
• Personal rather than shared. There is no team-visible agent identity that colleagues can tag and follow.
• The plugin catalog had no HR or ITSM systems as of August 12, 2026: no Workday, BambooHR, Rippling, Greenhouse, Lever, ServiceNow, or PagerDuty.
• Early beta, and availability is tied to specific consumer subscription tiers rather than a company plan.

Best for: individuals who want an always-on personal agent fleet and treat Slack as one input among many.

5. Moveworks

Moveworks is an enterprise AI assistant for employee support, acquired by ServiceNow for $2.85 billion in a deal that closed in December 2025. It answers HR, IT and workplace requests inside Slack, Microsoft Teams, Webex, Google Chat, email and a web portal, across more than 100 languages, and its reasoning engine plans and executes multi-step requests against 100+ enterprise systems rather than only answering questions. For enterprise search it uses a separate user-token integration, so results are restricted to the asking employee's own access level. Pricing is quote-only and based on total headcount rather than active users.

Pros

• Purpose-built for the highest-volume chat use case there is: IT and HR service requests.
• Search results are restricted to the asking employee's access level, enforced against the source system.
• The widest channel coverage of the eight: Slack, Teams, Webex, Google Chat, email and web, in 100+ languages.
• A deep action catalog across 100+ enterprise systems, so it resolves requests rather than routing them.
• Now inside ServiceNow, which is an advantage if ServiceNow is already your system of record.

Cons

• Moveworks is quote-only and priced on headcount, commonly six figures a year, with no self-serve tier, no monthly plan and no trial.
• Deployment is a multi-month project whose success depends heavily on the state of your existing knowledge base.
• Narrower than the rest by design. It is an employee-support assistant, not a general agent builder.
• A Moveworks Super Admin has the same access as the bot, bypassing underlying system access controls. Treat that role as highly sensitive.
• 2026 is the first renewal year under ServiceNow contracting, so packaging and pricing are a moving target.

Best for: large enterprises that want to deflect IT and HR tickets in chat and can fund a six-figure, multi-month deployment.

6. Runbear

Runbear is a channel-native agent platform where a workspace runs several named agents in Slack, Microsoft Teams, or Discord, each with its own knowledge, tools, and instructions. On the Business plan and above, a shared agent can act with each member's own credentials, so a question about a deal returns only the records that person is allowed to see. Pricing is usage credits rather than seats, at $99 per month for Team (20,000 credits, 5 builders) and $399 per month for Business (100,000 credits, 10 builders). Business adds SAML and SSO, an audit log of every prompt, tool call, and reply, and the option to bring your own model key.

Disclosure: Runbear publishes this blog. The pros and cons below follow the same template used for the other seven tools.

Pros

• Several named agents per workspace, so an HR agent and a platform agent can hold different knowledge and different tools.
• Per-user authentication on a shared agent, which Claude Tag, Dust and Viktor do not offer. Glean, Moveworks and Slack AI also scope to the individual.
• Usage-based credits rather than seats, so occasional users do not add cost.
• Slack, Microsoft Teams, and Discord, rather than Slack alone.
• Scheduled runs and channel triggers let an agent start work without being asked.

Cons

• Runbear is chat-first, so there is no rich standalone web workspace of the kind Dust and Glean offer for long research sessions.
• Credit forecasting takes a month or two to calibrate, because a deep research task can cost hundreds of times a simple lookup.
• Builder seats are capped per plan at 5 on Team and 10 on Business, which constrains how many people can configure agents.
• Per-user auth, SSO, and the audit log sit on Business at $399 per month, not on the entry tier. On Glean the equivalent is the default.
• Connector coverage is smaller than Glean's 275+ or Viktor's 3,200+, and someone still has to own agent setup. Teams that skip that step end up with one generic bot.

Best for: teams that want several team-specific agents in chat, with per-person tool permissions, without an enterprise contract.

7. Slack AI

Slack AI is Salesforce's native option, and the one you already own if you pay for Slack. Features are tiered by plan: conversation and thread summaries plus huddle notes on all paid plans, then workflow generation, recaps, translation and search on Business+ at $15 per user per month billed annually, and enterprise search on Enterprise+ at custom pricing. Agentforce agents and partner AI apps can be deployed into channels on any paid plan. Its permission model is the simplest of the eight because it never leaves Slack: AI features only use data the member already has access to, so a summary cannot contain something you could not have read yourself.

Pros

• Nothing to install, integrate or procure. It is already in the workspace you pay for.
• The cleanest permission story of the eight: AI only uses what the asking member can already see.
• Summaries, recaps, huddle notes and translation are useful on day one with zero configuration.
• Agentforce agents and partner AI apps drop into channels on any paid plan, so it is a platform as well as a feature.
• Admins can restrict AI read access to specific channels, canvases and lists.

Cons

• Slack AI's knowledge is Slack. Anything living in Notion, Drive or a CRM needs Agentforce or a partner app layered on top.
• The standalone Slack AI add-on was withdrawn from sale, and the features moved into higher plan tiers, so the real cost is a plan upgrade for every seat.
• Agentforce, the part that makes it genuinely agentic, is priced separately and reported to start around $125 per user per month.
• Product churn is real. Channel Expert, the in-channel agent launched in 2025, could no longer be added as of May 4, 2026, with Slackbot named as its replacement.
• Slack only, by definition. If part of the company runs on Teams, this covers half the org.

Best for: teams whose questions are mostly answerable from Slack history, and who want the lowest-friction option on the list.

8. Viktor

Viktor is a single shared AI coworker for Slack and Microsoft Teams, built by ZETA AI, Inc. Instead of one assistant per person, one Viktor works in whichever channels the team invites it to, and it reads only those channels. It has its own cloud computer where it writes and runs code, and it returns finished artifacts rather than text: PDFs, dashboards, commits, and deployed internal web apps with a database and auth. Viktor connects to more than 3,200 tools through one-click OAuth, monitors connected data streams to flag issues before anyone asks, and runs recurring scheduled work. New accounts get $100 in free credits with no card required, and paid usage starts at $50 per month.

Pros

• Shared rather than per-person, so the whole team sees the same coworker and the same history.
• Ships real deliverables. Building and deploying an internal web app is unusual in this group.
• More than 3,200 integrations, the largest catalog of the eight.
• Runs in both Slack and Microsoft Teams, with proactive monitoring rather than reply-only behavior.
• Low barrier to trying it: $100 in free credits and a $50 per month entry point.

Cons

• Viktor is one agent only. There is no way to give HR and engineering separate identities, knowledge, or tool scopes.
• It operates at the workspace level. Private mode and role-based access controls are still on the roadmap, per the vendor's own FAQ.
• SOC 2 Type 1 only, with Type 2 and ISO 27001 in progress, which some procurement teams will treat as a blocker.
• Reviewers report a learning curve, slower responses on complex jobs, and occasional loss of context across channels.

Best for: small teams that want one capable coworker producing finished work, without configuring a fleet of agents.

How to choose between them

Eight options collapse quickly once you answer three questions: where the agent should live, how many you need, and whether individual permissions matter. Find the row that matches your situation.

These are not mutually exclusive. Plenty of teams run Slack AI for summaries, a personal agent for individual work, and a shared agent for the channel, and the three rarely conflict.

For one-to-one detail, Runbear maintains head-to-head pages: Runbear vs Claude, Runbear vs Dust, Runbear vs Grok Bot, and Runbear MCP vs Viktor MCP. Those are written from Runbear's side of the comparison rather than as neutral roundups, so read them as vendor material.

Frequently asked questions

Which AI agents work in Microsoft Teams, not just Slack?

Moveworks, Runbear and Viktor all run natively in Microsoft Teams as well as Slack. Moveworks adds Webex, Google Chat and email, and Runbear adds Discord. Glean lists Teams among its integrations alongside Slack. Grok Bot accepts Teams messages as a trigger but does not live there. Claude Tag is Slack only, with no Teams version as of September 2026, and Slack AI is Slack by definition. Dust reaches Teams content as an indexed data source rather than as a chat surface.

Can a shared AI agent respect each person's individual permissions?

Four of the eight do this, in different ways. Glean runs an agent under the invoking user's identity by default, and in a shared Slack channel restricts it further to documents every member can see. Moveworks restricts enterprise search results to the asking employee's access level. Slack AI only uses Slack data the member already has access to. Runbear offers per-user authentication on a shared agent from the Business plan up. Claude Tag, Dust and Viktor connect tools at the workspace level, so a shared agent sees the same data regardless of who asks. Grok Bot is personal, so it uses your own connections and nobody else's. This matters most for CRM, HR and finance systems where row-level access differs by role.

What does an AI agent for Slack cost?

Four pricing shapes exist in this category. Per seat: Claude Tag comes with Claude Team or Enterprise seats, Slack AI comes with a Slack plan upgrade at $15 per user per month for Business+, and Glean is reported around $40 to $50 per user per month with roughly 100-seat minimums. Per seat plus credits: Dust. Usage credits with no seat charge: Runbear from $99 per month and Viktor from $50 per month. Quote-only on headcount: Moveworks, commonly six figures a year. Grok Bot is bundled into SuperGrok and Cursor subscription tiers. Seat pricing is predictable but charges for people who rarely use the tool; credit pricing tracks real usage but takes a billing cycle or two to forecast.

Should I just use Slack's built-in AI?

Start there if your questions are mostly answerable from Slack history. Slack AI summarizes threads, recaps channels and searches messages using only data you already have access to, with no setup and no new vendor. The limit is knowledge: Slack AI knows Slack. The moment the answer lives in Notion, Google Drive, a CRM or a ticketing system, you need either Agentforce layered on top at a reported $125 per user per month, or one of the other seven tools here. A useful test is to look at the last twenty questions your team asked in a channel and count how many could be answered from Slack messages alone.

Do I need Claude Enterprise to use Claude Tag?

Claude Tag requires a Claude Team or Claude Enterprise plan. It is not available on individual Pro or Max plans, which use the older Claude Code in Slack setup path instead. Claude Tag replaced the previous Claude app in Slack on August 3, 2026.

Is one shared agent better than several scoped agents?

Neither is better in general, and the trade is predictable. One shared agent is faster to start and needs almost no configuration, but it carries a single set of instructions and one tool scope for the whole company. Several scoped agents let an HR agent and an engineering agent hold different knowledge and different permissions, at the cost of someone owning their setup. Small teams usually get more from one agent working well. Companies past roughly 100 people tend to hit the limits of a single shared identity.

How this comparison was put together

Every capability and price in this piece was taken from vendor documentation, vendor pricing pages, product docs and launch announcements, checked on September 3, 2026. The eight landing page screenshots were captured the same day at a single 1440 by 900 viewport, so they can be compared like for like.

Matter, "50 Best Slack Apps & Integrations in 2026." Used as an external reference for how the productivity and AI categories are framed across the market.

Correction. This piece was first published with five tools and expanded to eight on September 3, 2026. The earlier version said Runbear was the only tool in its set offering per-user authentication on a shared agent. Adding Glean, Moveworks and Slack AI showed that claim was too narrow: Glean runs agents under the invoking user's identity by default, Moveworks scopes search to the asking employee, and Slack AI never exceeds what the member can already see. The table and the FAQ above reflect the correction.

Three other things surfaced during the check and are worth stating plainly. xAI publishes no standalone Grok Bot landing page: x.ai/grok-bot returns a 404, which is why the Grok Bot screenshot shows grok.com, the consumer chat app, instead. Dust's pricing page is client-rendered and returns no content to a plain fetch, and public listings disagree on its 2026 credit migration, so this piece describes the shape of Dust's pricing and leaves the numbers to Dust. Glean and Moveworks publish no pricing at all, so their figures come from analyst and buyer reports rather than the vendors, and should be treated as directional.

This is desk research, not a hands-on bake-off. Nobody here ran the same task through all eight products. Treat the capability claims as vendor-stated and verified against primary sources, not as measured performance. The category also moves fast: Claude Tag was two months old at the time of writing, Grok Bot three weeks, and Slack retired its own Channel Expert agent in May. Check current pages before deciding.

Runbear publishes this blog and appears as one of the eight, with the same pros-and-cons treatment applied to it as to the others.