attest_tag
Sign inTry it now
Menu
Comparisons

Comparisontheir pages read 22 Sep 2026

Relevance AI vs attest_tag

Relevance AI is where a team builds its workforce of specialist agents, any of which can wait for approval before acting; the difference is what attest_tag prints, holds and lets you run: model and cost under every reply, every write held for a Confirm by default, a grant routed to an approver who is never the requester, an audit log in the free plan, and one MIT binary you can host 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

  • A credential is given to the service, never the model: sealed with AES-256-GCM under a MASTER_KEY you hold on a self-host, injected by an in-process proxy one hop before the request leaves, and scrubbed out of every response before it reaches the model or Slack.
  • Any method other than GET, HEAD or OPTIONS is held in the Slack thread for a card with Confirm, Cancel and “Something else…”; a pending write expires after five minutes, and admins can pre-approve expected writes with plain-sentence allow rules, checked strictly.
  • 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, rather than reporting having crossed it.
  • “Fix this and raise a PR” hands the change to a separate worker container that clones the branch, runs the tests, makes the change, runs them again, and opens a draft pull request; it pushes one branch and never merges.
  • A flat monthly fee by plan size, never per seat, from $49 for up to 10 users to $599 for up to 250, and a free plan that does not expire with every feature in it — approval tiers, audit export, budgets, two-factor sign-in, MCP servers, fix jobs.
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.

Relevance AItheir hero, verbatim

“Specialist agents for every task”

A platform for building and running “specialist agents for every task”, which its site calls “The home of the AI Workforce”, with agents that answer an @mention in Slack.

What their pages do not say

  • Whether it runs on your own infrastructure
  • A licence, or source you can read
  • Whether the audit log can be exported, and on which tier below Enterprise
  • Which roles may approve outside Enterprise RBAC, and whether a requester may approve their own action
  • Who inside a workspace can view a stored key or OAuth token

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 Relevance 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

Relevance AI

“Route to any model provider and optimize cost per agent, per task” (Enterprise page). The homepage lists Claude Opus, Sonnet and Haiku, GPT-5.5, GPT-5.4 Mini, Gemini 3.1 Pro, Gemini 3 Flash, Kimi K2.6 and GLM-5.2; “Bring Your Own API Keys (BYOK)” is a bullet on every paid plan from Pro up.
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

Relevance AI

Per task: their Enterprise page lists “Cost visibility” and “See what every task really cost”, and a homepage illustration shows “Avg cost / task: $0.09”. Usage is metered in Actions — “counted when an Agent runs a Tool” — and Vendor Credits “at wholesale, with no markup”.
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

Relevance AI

Not stated on their site.
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

Relevance AI

“API keys: Fully self-managed. Relevance will store certs, service accounts, API keys etc securely and encrypted”, with “TLS 1.2+ for data in transit and AES 256 for data at rest”. The Slack doc says the builder integration “Uses a workspace-level bot token through the Relevance AI Slack app”, with “Per-user OAuth” as the alternative; who can view a stored key or token is not stated.
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

Relevance AI

Three modes: Auto Run, Approval Required and Let Agent Decide. Approval Required “forces the agent to seek explicit approval before executing an action” and drafts its intended action first. On their Enterprise page: “High-stakes actions pause for human sign-off. You set the thresholds.” A January 2026 changelog adds “You can now approve or reject agent tool requests without leaving Slack”, switched on per Slack trigger under “Tool approval from Slack”.
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

Relevance AI

“The agent will now draft its intended action and wait for human approval before proceeding.” Their security page says “Fine-grained RBAC and escalation features for sensitive actions is available for Enterprise customers”; which roles may approve, and whether a requester may approve their own action, their pages do not state.
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

Relevance AI

“SSO, RBAC & Audit Logs” is a bullet on the Enterprise (Custom-priced) plan card on their pricing page. “Audit logs” also appears under Access & Controls on the homepage and the Enterprise page, without a tier stated there.
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

Relevance 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

Relevance AI

Priced per workspace, not per seat: Pro at $19 a month billed annually or $29 billed monthly (2 Build Users, 1 Project, 2,500 Actions and $20 Vendor Credits a month); Team at $234 a month billed annually or $349 billed monthly (5 Build Users, 45 End Users); Enterprise custom. Extra Actions $80 per 1,000. Their docs say “The Free plan is retired and closed to new signups.”
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

Relevance AI

Slack — “Mention @Relevance in any channel and summon the right agent for the job”, “Set up agents to watch specific channels”, replies in threads and a Slack DM as a trigger — with the web app as the build and monitoring surface.

“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: Specialist AI Agents for Every Task | Relevance AIPricing - Relevance AIAgents in SlackEnterprise AI Agents | Relevance AISecurity overview - Relevance AI DocumentationSlack - Relevance AI DocumentationPricing - Relevance AI DocumentationApprovals and Escalations - Relevance AI DocumentationSlack tool approvals: Approve or reject agent tools in one click

Questions

What people ask about Relevance AI and attest_tag.

Is attest_tag an open-source alternative to Relevance AI?
attest_tag is MIT-licensed: one Go binary with the admin console embedded, one database, and a public repository on GitHub; the hosted service runs the same code. Relevance AI’s pages do not state a licence or whether its source is available. Both answer an @mention in a Slack channel; Relevance AI is a platform for building a workforce of specialist agents, attest_tag one teammate that joins the channels you invite it to.
Can I run attest_tag on my own servers?
Yes, and self-hosting costs nothing: Docker on a laptop or VM, Google Cloud Run, AWS Fargate, Azure Container Apps, or Kubernetes with Helm, with every feature in the binary and the MASTER_KEY that seals credentials held by you. Relevance AI’s pages do not state a self-hosted or customer-hosted deployment; the nearest is region choice, with data stored in Australia, the US, or the EU/UK “based on your selection at signup”.
Which model does each run on?
attest_tag runs on any OpenAI-compatible endpoint — OpenRouter, a vendor API, or a model you host — shipping on google/gemini-flash, with a default set per workspace and channel in the console, a per-thread override with !model, and a heavy model routed to automatically for code and long threads. Relevance AI says “Route to any model provider and optimize cost per agent, per task”; its homepage lists Claude, GPT, Gemini, Kimi K2.6 and GLM-5.2, and bring-your-own API keys is a bullet on every paid plan from Pro up.
What does a turn cost?
In attest_tag, every completion’s tokens and cost are measured and printed under the reply in the thread, with !usage for the month by channel against the budget; a typical question on the default model costs about $0.002 and a fix job about $0.18. Relevance AI meters Actions — “counted when an Agent runs a Tool” — and Vendor Credits, and its enterprise page says “See what every task really cost”; a homepage illustration shows “Avg cost / task: $0.09”.
Does Relevance AI hold a write for a human before it runs?
It can. Its approvals doc lists three modes — Auto Run, Approval Required and Let Agent Decide — and says Approval Required “forces the agent to seek explicit approval before executing an action”; the enterprise page adds “High-stakes actions pause for human sign-off. You set the thresholds.”, and a January 2026 changelog says you can “approve or reject agent tool requests without leaving Slack”. In attest_tag the hold is the default: any method other than GET, HEAD or OPTIONS waits in the thread for Confirm, Cancel or “Something else…”, and 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, and a request routes to the least powerful tier that covers every call in it. Relevance AI’s pages say the agent will “wait for human approval before proceeding”, and its security page says “Fine-grained RBAC and escalation features for sensitive actions is available for Enterprise customers”; which roles may approve, and whether a requester may approve their own action, its pages do not state.

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.