Vendor Release Watch setup guide

What it does

Summarises each new vendor release and flags breaking changes that touch your stack in Slack.

Checks a vendor's JSON releases endpoint (e.g. GitHub's releases API for a repository) on your plan's schedule interval and starts a run for each new release.
AI summarises the release notes and lists breaking changes, deprecations and security fixes, as written.
Flags which parts of the stack you describe they touch, and who owns them.
Posts the summary to your engineering channel in Slack (drafts, and pre-releases if you choose, are skipped).

What it needs

A paid plan (agents run live on paid plans).
An AI provider key (Settings → AI Providers).
An HTTP / Custom API connection for the vendor's API, and Slack, connected in Settings → Integrations.
An endpoint that returns the releases as a JSON list.

What it doesn't do

It only reads the public releases feed: it never touches your code, dependencies or repositories.
One vendor per setup (one HTTP connection has one base URL).
It doesn't read HTML changelog pages or RSS feeds, only JSON.
It reports what the notes say: it doesn't test upgrades or open tickets.

Availability and plans

Available

Its workflow is built and tested, and every app it needs is live. You can get it and set it up now.

Included free on the Enterprise plan; on other paid plans it's a one-time purchase per workspace (the price is on the Agents page). The Agents page in the app always shows its current status.

Before you start

A paid plan: agents run live, and the Free plan only runs Dry Runs.
An AI provider key (OpenAI, Anthropic, Google and more) in Settings → AI Providers. AI usage is billed by your provider.
These apps, connected in Settings → Integrations: HTTP / Custom API and Slack.
The app it watches, connected in Settings → Integrations (the agent starts from an app event).
About 10 minutes.

Set it up step by step

Get the agent first (buy it, or it's already yours when your plan includes it), then in Agents → My agents press “Set up this agent”. That creates the agent's workflow in your workspace (it counts towards your plan's workflow limit) and opens the canvas with a setup checklist above it. Each item links to the exact place to go and ticks itself off when it's done.

1. Connect your AI provider

The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.

Connect your AI provider

2. Connect the vendor's API (HTTP / Custom API)

Add an HTTP / Custom API connection with the vendor's API base URL (Settings → Integrations → HTTP / Custom API), e.g. https://api.github.com with an optional read-only token.

Connecting HTTP / Custom API

3. Connect Slack

Connect the Slack workspace your engineers use (Settings → Integrations → Slack).

Connecting Slack

4. Point the trigger at the releases

Open the trigger, pick the vendor connection and enter the releases path.

Setting	What to enter	In step
Vendor connection (HTTP / Custom API)	An HTTP / Custom API connection whose base URL is the vendor's API, e.g. https://api.github.com (a GitHub token is optional for public repositories but raises the rate limit). Pick your connected HTTP / Custom API account.	“New release at the endpoint”
Releases path	The path that returns the list of releases, e.g. /repos/<owner>/<repo>/releases for GitHub. For another JSON feed, also check “Where the list is” and “Item id field” on the trigger.	“New release at the endpoint”

5. Describe your stack

Open “Summarise and flag what matters” and replace the placeholder with your stack.

Setting	What to enter	In step
Your stack	Replace the placeholder with the vendor's products, SDKs, API versions and features you use, which team owns each, and whether to skip pre-releases. It starts as “[LIST YOUR STACK HERE: THE VENDOR'S PRODUCTS, SDKs, API VERSIONS, PLUGINS AND FEATURES YOU USE, AND WHICH TEAM OWNS EACH]” until you replace it.	“Summarise and flag what matters”

6. Pick the Slack account and channel

Open “Post to Slack” and pick your account and channel.

Setting	What to enter	In step
Slack account	The Slack workspace release summaries are posted to. Pick your connected Slack account.	“Post to Slack”
Engineering channel	The channel your engineers watch, e.g. #eng-updates.	“Post to Slack”

7. Test it with Dry Run

Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.

Dry Run vs Run

8. Switch the trigger on

Open the trigger and click “Activate app trigger”: the endpoint is checked on your plan's schedule interval. Releases published before activation aren't posted.

How it works

The agent is a normal workflow with 6 steps (1 AI step). You can open, edit and monitor it like any other workflow.

New release at the endpoint — Starts on “New item at an endpoint” in HTTP / Custom API (an app event). Checks the vendor's JSON releases endpoint on your plan's schedule interval and starts a run for each new release (e.g. GitHub's releases API).
Summarise and flag what matters — AI step (runs on your AI provider key). AI summarises the release, flags breaking changes, deprecations and security fixes, and says which parts of your stack they touch.
Post it? — Decision: picks the branch to follow. Drafts (and pre-releases, when your stack note says to skip them) are kept in the run history only.
Not posted — Kept in the run history. Branch: Skip. The run history keeps the summary.
Post to Slack — Slack: Post a message. Branch: Post. Posts the summary, breaking changes and what they touch in your stack to your engineering channel.
Posted — Kept in the run history. The run history keeps the release summary.

Test it with Dry Run

Press Dry Run in the canvas. The agent runs on the sample data stored on its trigger (the “Sample data for Dry Run” box), so you can check every step's output before anything is live. The sample has the same shape as a real event from the app.

Sample data fields

name, id, tag_name, published_at, prerelease, draft, html_url, body.

Nothing is sent or written: app actions, emails and Slack posts are simulated, and AI steps don't call your AI provider.

Go live

Open the trigger and click “Activate app trigger”: the endpoint is checked on your plan's schedule interval. Releases published before activation aren't posted.
Activating the app trigger needs the trigger's connected account. The first check only remembers what's already there, so older items don't start runs; the same item never starts two runs.
The setup checklist adds a “paid plan” item before activation: live runs need a paid plan (the Free plan only runs Dry Runs).
When every checklist item is done and the trigger is on, the checklist says “Live — this agent is running”. Follow its runs in the workflow's History tab and in Analytics → Agents.

Questions

Can it watch several vendors?

One vendor per setup: each HTTP connection has one base URL. Set the agent up again for another vendor or repository.

Can it read an HTML changelog or RSS feed?

No. It needs an endpoint that returns JSON with a list of releases (GitHub releases API, or a vendor's JSON changelog).

Troubleshooting

“No AI provider connected” or a rejected key: connect or fix the key in Settings → AI Providers, then press Test there.
A checklist item stays unticked: the setting is still empty or still contains its placeholder text. Open the step from the checklist and fill it in.
An app step fails with “Needs reconnect”: the account's access was revoked or expired. Reconnect it in Settings → Integrations.
Slack says the app isn't in the channel: in Slack, type /invite @Fluxo Flow in that channel (always needed for private channels).
No runs start: activate the app trigger with a connected account. Only items created after activation start runs.
A step failed: open the run in History and check that step in the Trace tab for the error and what it received.

Generated from the agent's own workflow, so it always matches what the agent does. Last updated October 12, 2026.