Integrations

Connected to where the work already lives.

Complex apps come with complex context — spread across GitHub, Slack, tickets, and docs. Gentlybot connects to those systems so threads start grounded and results land where your team already looks.

Gently in Slack

Support needs an explanation. Sales needs to check a promise. Product needs to understand a flow. Ask Gently where your team already works, with answers grounded in your connected code and tools.

  • Mention Gentlybot or send a DM. Describe the question and attach a screenshot when it helps.
  • Keep the conversation in Slack. Read the answer, ask a follow-up, and answer Gently’s questions in the same thread.
  • Open the work in Gently. Follow the thread’s link when you want to explore previews, wireframes, or code changes.
How to ask from Slack

Example Slack exchanges · Crosstown, a fictional delivery app

# customer-support
M
Maya10:42 AM

@gentlybot In Crosstown, what happens when a courier cannot finish a delivery?

GentlybotAPP10:43 AM

The courier marks the stop “Could not deliver” and chooses a reason. If the customer has an email address, Crosstown tells them the delivery failed and the order is returning to the shop. The shop arranges another delivery.

In a channel, mention Gentlybot again in your thread reply to ask a follow-up. The conversation continues in the same Gently thread.

Connect Slack →

The deepest integration — installed as a GitHub App you control.

  • Open pull requests with context, checks, and evidence attached
  • Read failing CI, reproduce in a sandbox, and push a fix to the same branch
  • Address line-anchored review comments as follow-ups in the thread
  • Create and link issues written from the real scope of a thread
  • Autonomous capabilities (auto-fix CI, review comments, security alerts) are individual opt-in toggles, each with its own scoped permission

CI failed and a reviewer left two comments — both came back into the thread. Gently fixed the test, addressed the comments, and pushed.

Add rate limiting to the login route#438
open
18/18 passed · 2 review threads resolved

Ask product questions. Get answers in Slack.

  • Mention Gentlybot in a channel or send a DM to ask about your product
  • Read answers in Slack and mention Gentlybot again for follow-ups in the same thread
  • Attach screenshots and answer Gently’s clarifying questions directly in Slack
  • Open the linked Gently thread for previews, wireframes, and code changes
  • Trigger saved automations from messages in the channels you choose
Event triggers in early access

Tickets written from the code, not from memory.

  • Connect with OAuth in a couple of clicks
  • Turn a thread into well-scoped Jira issues, with the PR and evidence linked
  • Pull issue context into threads so plans reflect what was actually reported
Product request triage
Jira trigger Issue created in PRODREQ
Check the request against the product, dedupe against existing issues, and comment back with what exists today
Early access

Product context beyond the repo.

  • Connect your workspace with OAuth
  • Work from the specs and docs your team already maintains
  • Start automations when selected pages or databases change
S
SamImplement

Draft the help-center article for the new export flow — the spec is in Notion.

Worked for 21s · 8 tools

Drafted from the spec and the shipped behavior — flagged one place where they disagree:

References

notion · Export v2 spec
docs/help/exports.md

Issue work connected directly to the product.

  • Search and read issues with their descriptions, state, team, and comments
  • Create, update, transition, and comment on issues from a thread
  • Start automations from issue and comment events, scoped by team or keyword
Customer-impact first response
Linear trigger Issue created with label “customer-impact”
Check the report against the product and add likely causes plus the next diagnostic step

If it speaks Model Context Protocol, Gently can use it as a tool.

  • Add any remote MCP server — bearer token or OAuth
  • Presets for common tools like Confluence, Linear, Sentry, and Datadog
  • Live health status so you can see when a connection degrades
  • Credentials encrypted at rest and scoped to your workspace
R
RaviAsk

Pull yesterday’s Sentry errors for checkout and group them by likely cause.

Worked for 12s · 6 tools

3 distinct causes across 41 events — one is ours:

  • Ours — null cart on re-entry from the confirmation email (28 events)
  • Not ours — two payment-provider timeouts, already recovered

Model-agnostic by design.

  • Capable models included out of the box — no keys required to start
  • Works across Anthropic, OpenAI, and open-source model families
  • Admins configure model pools: exactly which models each kind of work may use
  • Enterprise: bring your own model accounts or private deployments

Anything with an MCP server can become a Gently tool today. Request access and tell us what your workflow needs — integrations are prioritized by what design partners actually use.

Request access
Read the setup guide