Social Reply Assistant

What it does

Reply drafts in your brand voice for every Mastodon mention, from your Notion FAQ; complaints, refunds, legal and angry posts always go to a person.

• Starts for each new mention of your Mastodon account, including replies to your posts (checked every few minutes).
• Reads your Notion voice and FAQ page and drafts a short public reply in your voice that answers only with facts from that page.
• Flags sensitive posts (complaints, refunds, legal, angry, anything personal) and sends them to a high-priority review with a note on why: it never promises refunds or outcomes in public.
• Routine replies wait for your approval too, unless you switch auto-posting on; spam is left alone.
• Code checks the reply (not blank, no leftover placeholders, 500 characters) before it's posted under their post, with the same visibility as theirs.

What it needs

• A paid plan (agents run live on paid plans).
• An AI provider key (Settings → AI Providers).
• Mastodon and Notion, connected in Settings → Integrations.
• A Notion page with your voice, FAQ answers and support contact, shared with Fluxo Flow.

What it doesn't do

• Mastodon only: Bluesky mentions aren't answered by this agent.
• It answers only from your FAQ page; it can't look up orders or accounts.
• It doesn't like, boost, block or delete anything.
• Not instant: mentions are checked every few minutes. Text only.

Availability and plans

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: Mastodon and Notion.
• The app it watches, connected in Settings → Integrations (the agent starts from an app event).
• About 15 minutes.

• Bring your own AI key
• Mastodon (live)
• Notion (live)

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 Mastodon

Connect Mastodon with your server and an access token with read and write scopes (Settings → Integrations → Mastodon).

• Connecting Mastodon

3. Connect Notion

Connect the Notion workspace with your voice and FAQ page (Settings → Integrations → Notion).

• Connecting Notion

4. Pick your Mastodon account

Open the trigger and pick the Mastodon account to watch.

5. Pick your voice and FAQ page

Open “Read your voice and FAQ page” and pick the account and page.

6. Describe your reply rules

Open “Draft the reply” and replace the placeholder with your rules.

7. Pick the account that replies

Open “Post the reply” and pick the same Mastodon account.

8. 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

9. Switch the trigger on

Open the trigger and click “Activate app trigger”: new mentions are checked every few minutes.

How it works

The agent is a normal workflow with 12 steps (1 AI step, with a person approving in Reviews). You can open, edit and monitor it like any other workflow.

• New Mastodon mention or reply — Starts on “New mention” in Mastodon (an app event). Starts a run for each new mention of your Mastodon account, including replies to your posts (checked every few minutes).
• Read your voice and FAQ page — Notion: Read a page's text. Reads your Notion page with your brand voice, FAQ answers and links you may share.
• Draft the reply — AI step (runs on your AI provider key). AI sorts the post, flags anything sensitive (complaint, refund, legal, angry, private details) and drafts a short public reply in your voice from your FAQ page only.
• Who decides? — Decision: picks the branch to follow. Spam and no-reply posts are left alone. Sensitive posts go to a high-priority review. Routine replies are reviewed too, unless you switched auto-posting on.
• No reply — Kept in the run history. Branch: No reply. Spam or nothing to answer: the run history keeps the classification.
• Sensitive: approve the reply — A person approves or rejects it in Reviews (the run waits). Branch: Sensitive. Complaints, refunds, legal, angry and personal posts wait here with high priority. Edit the reply (or reject and answer yourself), then approve to post it.
• Approve the reply — A person approves or rejects it in Reviews (the run waits). Branch: Review. Routine replies wait here: edit, approve to post, or reject.
• Check before replying — Step. Branch: Auto-post / Approved. In code: the reply is there, has no leftover placeholders and fits 500 characters.
• Passed the checks? — Decision: picks the branch to follow. Passed: the reply is posted. Otherwise nothing is posted.
• Held: nothing posted — Kept in the run history. Branch: Held. The reply was blank, too long or still had a placeholder; answer by hand if needed.
• Post the reply — Mastodon: Reply to a post. Branch: Reply. Replies under their post, with the same visibility as their post (a private mention stays private).
• Replied — Kept in the run history. The run history keeps the post, the draft and the reply link.

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

account_acct, account_name, status_content, id, type, created_at, account_id, status_id, status_url, status_visibility, notification.

• Nothing is sent or written: app actions, emails and Slack posts are simulated, and AI steps don't call your AI provider.
• Approval steps use the Dry Run decision you pick in the step's settings (approved, rejected or timeout), so you can try each branch.

Go live

• Open the trigger and click “Activate app trigger”: new mentions are checked every few minutes.
• 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.

• App event triggers
• Switching a trigger on (Activation)

Questions

Does it post without me?

Not by default: every reply waits for approval. You can let routine replies (questions your FAQ answers, thanks) post on their own by writing AUTO-POST ROUTINE REPLIES: yes in your rules; sensitive ones always wait.

What counts as sensitive?

Complaints, refund requests, legal-sounding posts, angry posts, anything about someone's order, account, health or money, threats and press. These go to a high-priority review with a note on why.

Why only Mastodon?

Mastodon tells us about mentions and replies to your posts in one trigger. Bluesky mentions can be alerted with the Mention & Reply Alerts agent.

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.
• No runs start: activate the app trigger with a connected account. Only items created after activation start runs.
• A run shows as paused: it's waiting for someone in Reviews to approve or reject it.
• A step failed: open the run in History and check that step in the Trace tab for the error and what it received.

• Debugging failed runs
• Error messages
• Get help