attest_tag
Sign inTry it now
Menu
Comparisons

Comparisontheir pages read 22 Sep 2026

Slack AI vs attest_tag

Slack AI is already in the workspace — summaries, search and recaps on every paid plan, and a Slackbot that takes actions on Business+ and Enterprise+ — so the difference is what its pages leave unsaid: attest_tag lets you choose the model and prints each reply’s cost under it, routes access grants to an approver who is never the asker, seals each credential under a key you can hold, and ships as one MIT binary you can run yourself.

Try it nowDeploy it yourselfSkip to the table
The short versionTheir page, oursSide by sideQuestionsTry both

Which model answers

Any endpoint, per thread

What a turn costs, and who sees it

Model and cost under every reply

Where it runs

Hosted, or one binary of yours

Who holds the credentials

The proxy. Never the model

Who may approve

Never your own request

What you can audit

Every call, exportable

Pick attest_tag when

  • Any method other than GET, HEAD or OPTIONS is held: the bot posts what it intends to do with Confirm, Cancel and “Something else…”, the pending write expires after five minutes, and admins can pre-approve expected writes with plain-sentence allow rules checked strictly.
  • A credential is given to the service, never to the model: an in-process proxy injects it one hop before the request leaves, the model only ever emits a URL and a method, and responses are scrubbed of secret-shaped values before they reach the model or Slack.
  • Budgets that stop rather than report: a monthly budget for the workspace, another per channel, and a per-user hourly rate limit — the bot pauses at the ceiling and says so.
  • Runs hosted by us on Cloud Run, or on your own infrastructure — Docker, Cloud Run, Fargate, Azure Container Apps, Kubernetes with Helm — at no fee and with no limits set by us, from the same code the hosted service runs.
  • A free plan that does not expire, then a flat monthly fee by plan size rather than per seat — up to 10 users for $49, up to 250 for $599 — with every feature in the free plan and the open-source binary, so what a paid plan adds is scale and paperwork.
The ten questions, side by side

Their page, ours

What the hero says, and what the rest of the site does not.

A hero line is a promise about the product. The questions an engineer asks before rolling one out are usually answered somewhere else on the site — or not answered. These are the ones we looked for.

Slack AItheir hero, verbatim

“AI in Slack works where you do.”

Slack’s built-in AI features and agents, sold with paid Slack plans and working inside Slack: “a powerfully simple way to be more productive, built with knowledge from your company.”

What their pages do not say

  • Which model answers
  • What a turn cost
  • Where the credentials for connected tools live
  • Who may approve an agentic action, and whether anyone may approve their own
  • A self-hosted option — the pricing FAQ puts the models in Slack’s own AWS virtual private cloud, and Enterprise+ lists an EKM add-on for your own keys, not your own servers
  • The licence, or any source to read

On the public pages listed under the table, as of 22 Sep 2026. An absence is a fact about a page, not about the product; if one of these has since been answered, we will change it.

attest_tagthe same questions, in writing

Side by side

Ten questions worth asking either way.

Our column is the same on every comparison, and each cell ends where the mechanism is shown. Theirs is Slack AI’s own pages, quoted or closely paraphrased, as read 22 Sep 2026.

01Which model answers

attest_tag

Any OpenAI-compatible endpoint — OpenRouter, a vendor API, or a model you host. Ships on google/gemini-flash, with a heavy model routed to automatically for code and long threads, and a per-thread override.
Models and cost

Slack AI

Not stated on their site.
02What a turn costs, and who sees it

attest_tag

Metered per completion and printed under the reply beside the model that answered, with !usage for the month by channel. A monthly budget for the workspace, another per channel, and a per-user hourly rate limit — the bot pauses at the ceiling rather than reporting having crossed it.
Audit and budgets

Slack AI

Not stated on their site.
03Where it runs

attest_tag

Hosted by us, or one MIT-licensed Go binary with the console embedded on your own infrastructure — Docker, Cloud Run, Fargate, Container Apps or Kubernetes. The same code either way. Where HIPAA applies, run it yourself so nothing leaves your network, and we sign a business associate agreement with you.
Self-hosted

Slack AI

Slack’s cloud: “Our large language models are hosted directly within Slack’s AWS virtual private cloud, ensuring your data remains in-house.” A self-hosted option is not stated on their site; Enterprise+ lists an EKM add-on for your own encryption keys.
04Who holds the credentials

attest_tag

The service, never the model. Sealed with AES-256-GCM at rest — under a key you hold, on a self-host — injected by a proxy at the network edge, and scrubbed back out of every response before it reaches the model or the thread.
Credentials, in the guardrails

Slack AI

Not stated on their site.
05Before it changes something

attest_tag

Any method other than GET, HEAD or OPTIONS is held for a card in the thread — Confirm, Cancel, or say what you actually wanted. Pending writes expire after five minutes. A fix job opens a draft pull request and never merges.
Human-in-the-loop writes

Slack AI

On the Slackbot page (Business+ and Enterprise+): “Every agentic action gets a full audit trail and human-in-the-loop approval, so nothing runs without your say.” The Agentforce page says agents “suggest and automate actions on your behalf”; a confirm step is not stated there.
06Who may approve

attest_tag

Writes that grant access leave the thread and go to an approver’s DM. Nobody approves their own request — enforced three times over, once in SQL — and a request routes to the least powerful tier that covers every call in it.
Access requests and tiers

Slack AI

“Human-in-the-loop approval” on the Slackbot page. Who the approver is, approver tiers, and whether a person may approve their own request are not stated on their site.
07What you can audit

attest_tag

Every turn, tool call, proxied request and completion — with tokens and cost — in a console you run, exportable as CSV. Self-hosted, it is a table in your own database.
The audit trail

Slack AI

“Audit logs track changes and usage. View in Slack, export CSV, or use the Audit Logs API” — listed under Business+ and Enterprise+ on the pricing page. The help article says “Available on Enterprise plans”, with Slackbot actions tagged acting_agent: Slackbot.
08Source and licence

attest_tag

MIT. The repository is the product: the hosted service runs the same binary you can clone, read and build.
The same binary, inside your network

Slack AI

Not stated on their site.
09What it costs

attest_tag

A free plan that does not expire — $5 of model spend a month — then a flat monthly fee by plan size, $49 for up to 10 users to $599 for up to 250 users, with AI credit included. Never per seat, and every feature in every plan.
Pricing

Slack AI

Free: $0 USD, “free forever”. Pro: $8.75 USD per user a month, or $7.25 paid annually. Business+: $18, or $15 annually. Enterprise+: contact sales. AI features are on all paid plans; Slackbot is on Business+ and Enterprise+, unlimited on Enterprise+.
10Where it lives

attest_tag

Slack and Microsoft Teams, from one console: channels, threads and DMs in Slack; channel reply chains, group chats and one-to-one chats in Teams. It joins the channels you invite it to, and there is no second place for the team to go.
Threads and streaming

Slack AI

Slack: “AI in Slack works where you do.” Enterprise search reads data from connected apps and answers inside Slack; the Agentforce page frames it as “Agentic productivity for every employee in Slack.” No other surface is stated on their site.

“Not stated on their site.” means we read the pages below on 22 Sep 2026 and did not find it — not that the product lacks it. Ask them; a vendor that answers all ten in writing is a good sign about the vendor. If we have something wrong, tell us and we will fix the page.

Pages read: Slack AI featuresSlackbot, personal AI agentPricingAI agents with AgentforceSecurity for AI features in Slack (help)Audit logs in Slack (help)Work with AI agents in Slack (help)Guide to AI features in Slack (help)

Questions

What people ask about Slack AI and attest_tag.

Is attest_tag an open-source alternative to Slack AI?
attest_tag is open source under the MIT licence: one Go binary with the admin console embedded, one database, the same code the hosted service runs, public on GitHub. Slack AI’s pages do not mention a licence or source; they describe “third-party large language models (LLMs) hosted within our secure cloud infrastructure”. Both live in Slack, and attest_tag in Microsoft Teams as well, so an alternative here means a bot you invite to channels rather than features built into paid plans.
Can I run attest_tag on my own servers?
Yes, at no fee and with no limits set by us: Docker on a laptop or VM, Google Cloud Run, AWS Fargate, Azure Container Apps, or Kubernetes with Helm, with the MASTER_KEY that seals credentials held by you. Slack AI’s pages do not state a self-hosted option; the pricing FAQ says its models are “hosted directly within Slack’s AWS virtual private cloud”, and Enterprise+ lists an EKM add-on for your own encryption keys.
Which model does each run on?
Slack’s pages name no model or vendor and do not state a bring-your-own key; the security article says Slack “uses third-party large language models (LLMs) hosted within our secure cloud infrastructure”. attest_tag talks to any OpenAI-compatible endpoint — OpenRouter, a vendor API or a model you host — ships on google/gemini-flash, sets the model per workspace, per channel and, with !model, per thread, and routes to a heavier model automatically for code, long threads and turns that have made eight tool calls.
What does a turn cost, and who sees it?
In attest_tag every completion’s tokens and cost are measured and printed under the reply; !usage shows the month’s spend by channel against the budget. A typical question on the default model costs about $0.002, a fix job about $0.18. Slack AI’s pages show no per-turn figure: Slackbot has “a weekly message limit” on Business+, the pricing page says “Plan limits apply”, and Business+ customers on invoice plans can buy Flex Credits for higher limits, at a price the pages do not give.
Does Slack AI hold a write for a human before it runs?
For Slackbot, its page says so: “Every agentic action gets a full audit trail and human-in-the-loop approval, so nothing runs without your say.” Who approves, and whether the asker may, is not stated; the Agentforce page does not state a confirm step. In attest_tag any method other than GET, HEAD or OPTIONS is held: the bot posts what it intends to do with Confirm, Cancel and “Something else…”, and the pending write expires after five minutes.
Can someone approve their own request?
Not in attest_tag. A write that grants access leaves the thread and goes to an approver as a DM with Approve and Deny; nobody approves their own request, enforced three times over, once in SQL. Approvers hold a tier naming the bundle they may grant from. Slack’s pages state “human-in-the-loop approval” for Slackbot and do not say who the approver is or whether a person may approve their own request.

More comparisons

The same ten questions, asked of the others.

All comparisons

Try both

Run both in the same channel for a week.

We mean it. attest_tag answers in threads, so it will not collide with whatever else is in the channel, and a week of your own questions settles this faster than any table.

Try it nowDeploy it yourself

Half an hour to set up, one channel to start, and the free plan needs no card. See what it costs.