Use cases by system22 use cases
AI agents in Slack, built as your own internal app
In most builds in this library Slack is not the product. It is where the human step happens: the invoice that needs approval, the lead worth a call, the Monday brief, the draft reply a person checks before it goes out. That is why so many use cases here touch it, from weekly KPI briefs to a company knowledge assistant and plain-English questions over your database.
Two platform decisions shape how to build for Slack. The official Slack MCP server is generally available, with search, messages, canvases, lists, users and file uploads, but only Marketplace-published or internal apps may use it. And since 29 May 2025, commercially distributed apps that are not on the Marketplace can call conversations.history and conversations.replies once a minute, 15 messages at a time, while internal customer-built apps keep 50 or more requests a minute and 1,000 objects.
The consequence is structural: an app built for your workspace and installed only there has more access than an unlisted third-party bot. So I build Slack agents as internal apps in the client's own workspace, owned by the client, with a private AI gateway behind them where model access needs central control.
What to build around Slack
A company assistant that answers from SharePoint and Drive, and respects who may see what
Answers staff questions in Teams and Slack from SharePoint, Drive and Confluence, cites every source, and only searches what the person asking may open.
SharePoint and Teams / Google Drive / Slack / Confluence or Notion / Microsoft Entra ID or Google groups
A Monday KPI brief that explains last week's numbers instead of just charting them
Computes last week's KPIs in SQL, checks the data is complete, finds what moved and why, and posts a short written brief to Slack at 07:00 every Monday.
Shopify / BigQuery or Google Sheets / GA4 and the ad platform APIs / HubSpot / Accounting and payments
A second-line support agent that checks the logs before an engineer gets pulled in
Investigates escalated tickets the way an engineer would, from account settings to error logs to known issues, and returns a checked answer or a ready bug report.
Zendesk or Intercom / Jira or Linear / Sentry and Datadog / Admin API or read replica / Slack
A support agent that answers 'where is my order?' from live Shopify and carrier data
Answers order questions on every channel from live Shopify and carrier data, verifies the customer first, and hands refunds and angry customers to a person.
Shopify / Gorgias or Zendesk / WhatsApp Business Platform / Carrier tracking API / Returns app (Loop, ReturnGO)
An agent for the shared inbox: every email sorted, answered or filed into the right system
Reads every email in your shared mailboxes, sends orders and invoices into the right system, drafts replies for approval, and flags fake bank-detail changes.
Microsoft 365 shared mailboxes / Gmail and Google Workspace / The ERP (Business Central in this example) / Teams or Slack / The AP flow and accounting system
An agent that chases suppliers for delivery dates and updates the ERP when they change
Emails suppliers about open POs in their language, reads confirmations and date changes, writes agreed dates to the ERP and flags the late parts that will hurt.
Outlook and Microsoft 365 / SAP Business One / NetSuite / Shopify / Microsoft Teams or Slack
An AI bill growing faster than your users: a cost audit, model routing and budgets
Traces model spend to each feature and customer, fixes caching, batching and prompt bloat, routes simple calls to small models, and proves quality holds with evals.
OpenAI and Anthropic APIs / Langfuse or Helicone / AI gateway / Data warehouse / Slack
Every inbound lead researched, scored and routed before a rep opens it
Researches and scores every inbound lead against your rubric, catches existing customers, routes by territory and capacity, and replies with a booking link.
HubSpot / Salesforce / Enrichment provider (Clay or Apollo) / Cal.com or Calendly / Slack
Fixing n8n, Zapier and Make automations that report success and did nothing
Audits inherited n8n, Zapier and Make automations, then adds a run ledger, idempotency keys and a daily reconciliation so a green run means the work was done.
n8n / Zapier / Make / Postgres / Slack
Freight quote requests in four languages, answered in minutes and priced by your own rules
Reads freight quote requests in your customers' languages, asks for what is missing, prices the lane with your margin rules, and sends or drafts the quote.
Outlook and Microsoft 365 / TMS (Soloplan CarLo, Transporeon, CargoWise or similar) / Freight exchange data (Timocom, Trans.eu; DAT in the US) / HubSpot or the TMS customer record / Truck routing API (PTV or HERE)
One support team answering customers in twelve languages without hiring for each one
Lets a small team work in its own language while customers get replies in theirs, with product names protected, formality per market and legal wording pre-approved.
Zendesk / Intercom or Gorgias / DeepL API / Glossary and market profiles / Zendesk Guide
Supplier invoices from inbox to ledger, with the checks a good controller would do
Reads supplier invoices from the AP inbox, matches them to purchase orders and goods receipts, and holds any invoice whose bank details changed until someone calls.
Outlook (Microsoft 365) / Xero / QuickBooks Online / DATEV / NetSuite
Turning a 40-tab dispatch spreadsheet into an internal tool with rules, roles and history
Moves daily planning off a 40-tab spreadsheet into a web tool with validated forms, roles and a full edit history, while people keep Excel for analysis.
Excel and Google Sheets / Postgres / Microsoft 365 single sign-on / The ERP or TMS / Slack
A private ChatGPT for every employee, behind single sign-on, with redaction and team budgets
A company chat app behind single sign-on that strips client data and secrets, routes to approved EU or self-hosted models, logs use, and gives each team a budget.
Microsoft Entra ID or Google Workspace / Slack or Teams / OpenAI, Anthropic and Mistral / Open models on EU infrastructure / Open WebUI, LibreChat or a custom interface
Agency client reports with commentary drafted from the data and approved by the account lead
Loads every client's ad and analytics data, measures it against their own targets, names only causes it can prove, and drafts commentary in the client's language.
Google Ads, Meta Ads and GA4 / Supermetrics or Funnel / BigQuery or Google Sheets / Looker Studio / HubSpot
Candidate screening that quotes the CV behind every score, built for the EU AI Act
Scores each application against a rubric the recruiter wrote, quotes the CV line behind every score, catches hidden instructions, and never rejects anyone on its own.
ATS (Greenhouse, Personio or Bullhorn) / Gmail / Slack / The language model / Audit store (Postgres)
Every support conversation scored against your own rubric, not a two percent sample
Scores every conversation against your rubric with quoted evidence, calibrated against your QA lead, and built for coaching rather than discipline.
Zendesk / Intercom / Language model / Billing system and CRM / Slack
Onboarding that provisions accounts only after approval, and answers new starters' questions
Turns a signed contract into an approved access plan, creates the accounts through APIs, answers new starters from the handbook, and reverses it all on the last day.
HRIS (Personio, HiBob or BambooHR) / Google Workspace / Microsoft 365 / Okta or Microsoft Entra ID / Slack
Plain-English questions over your own database, with the SQL shown and checked
Answers plain-English questions from a read-only copy of your database, shows the SQL and definitions behind each answer, and asks when a question is ambiguous.
Postgres or BigQuery / dbt or plain SQL views / Metabase / Slack / Excel export
Sales calls and emails that update the CRM on their own, after the rep approves
Reads customer calls and email threads, proposes stage, next step and close date changes with evidence, and writes them to the CRM after one click from the rep.
HubSpot / Salesforce / Gmail or Outlook / Zoom, Google Meet or Microsoft Teams / Slack
What your returns are telling you: return reasons turned into product and size-guide fixes
Reads return comments, reviews and tickets in every language, ties them to SKU, variant and batch, and sends product a weekly list of issues with counts and quotes.
Shopify / Loop or AfterShip Returns / Gorgias or Zendesk / Reviews (Okendo, Yotpo, Trustpilot) / ERP or PIM
Replies to every review at every location, and the recurring problems they point to
Collects every location's reviews, drafts replies a manager approves, sends hygiene and safety complaints to a person the same day, and builds a weekly issue list.
Google Business Profile API / Tripadvisor / Slack / Google Sheets / Reservation system or hotel PMS
Building in Slack: events, buttons and threads
Acknowledge within three seconds
Slack expects events and button clicks to be acknowledged within three seconds, and it retries events that are not. The app answers at once, queues the work, and posts the result when the lookups and the model are done.
Socket Mode behind a firewall
The Events API needs a public HTTPS endpoint. Socket Mode opens an outbound connection instead, which suits an internal app running next to the ERP rather than on the open internet.
Buttons that act once
Approve, edit and reject are Block Kit buttons whose payload carries the ID of a pending action. A second click, or a retried request, finds the action already done and changes nothing.
Permissions follow the person
An assistant answering from Slack, Drive or SharePoint should see only what the person asking may see. The build resolves the user's identity and filters sources before retrieval, not after the answer is written.
What to switch on before building a Slack app
Slack's own AI for catching up
Slack's built-in AI features summarize channels and answer questions from workspace history. If catching up on conversations is the problem, try those first.
The MCP server for assistant users
If people already work in Claude or ChatGPT, connecting the official Slack MCP server through an internal app gives the assistant search and posting without a build.
Custom when Slack fronts other systems
Approving a refund in Stripe, a bill in Xero or a discount in HubSpot from a Slack button needs an app that holds those credentials, applies limits in code and logs every decision.
Slack is not the audit log
Approvals are recorded in the system of record with who approved and when. Retention settings change, and a decision that exists only as a Slack message is hard to prove a year later.
The same design in Teams
Microsoft shops get the same pattern with Adaptive Cards in Teams, covered in the Outlook and Microsoft 365 hub.
Frequently asked questions
Can I build an AI agent for Slack?
Yes. It is a Slack app, installed as an internal app in your workspace, that listens for mentions, messages or button clicks, calls your systems and a model, and replies in the thread. Built internally, it keeps Slack's higher API limits and can use the official MCP server. It should be owned by your workspace, not by the developer who built it.
Does Slack have an official MCP server?
Yes. Slack's MCP server is generally available and covers search, messages, canvases, lists, users and file uploads. Access is limited to apps published on the Slack Marketplace and internal apps built for a workspace, so an unlisted third-party tool cannot use it. For a company, an internal app is the straightforward route.
Why do third-party Slack bots hit rate limits?
Since 29 May 2025, commercially distributed apps that are not on the Slack Marketplace can read channel and thread history only once a minute, 15 messages per call. Internal apps built by or for the customer keep 50 or more requests a minute and 1,000 objects per call. A bot that reads conversations works far better as your own internal app.
Should approvals happen in Slack or in the system itself?
Both, with a clear split. Slack is where the person sees the request and clicks, because that is where they already are. The decision is executed and recorded in the system of record, with who approved and when, and the button checks that the request is still valid before anything happens.
Also browse: Internal tools and knowledge · SaaS · n8n · Outlook and Microsoft 365 · all use cases