Coaching Session Recap & Accountability

What it does

Turns session notes into a client recap with commitments, adds it to their Notion page after you approve, then sends a check-in and a prep prompt.

• Starts from each session's notes or transcript posted by your session form.
• AI writes the client's recap — insights, commitments with dates, homework and one question for next time — plus a check-in and a prep prompt, using only what was said.
• Health topics are kept out of everything the client receives and flagged privately for you.
• You approve (and can edit) it all; the recap is added to the client's Notion page and emailed.
• 3 days later, sends the accountability check-in quoting their commitments (unless the next session is under 3 days away).
• At 09:00 the day before the next session (when it's 2–30 days away), sends the prep prompt.
• Dates are worked out in code, never by the AI: days until or since each date, the window and business days are computed in your workflow's time zone, and records outside the window are skipped before the AI sees them.

What it needs

• A paid plan (agents run live on paid plans).
• An AI provider key (Settings → AI Providers).
• Notion, connected in Settings → Integrations, with a page per client shared with Fluxo Flow.
• A session form (or your own tool) that can post JSON to a webhook.

What it doesn't do

• It drafts and organises recaps for you to approve; it makes no medical, legal or eligibility decision and is not therapy or clinical care. Health topics are kept out of the recap and flagged for you.
• It never adds advice or commitments the client didn't make.
• Sessions more than 30 days apart get no prep prompt (a Wait step pauses for at most 30 days). Waits need migration 0062 in your workspace.
• It works from text only (not recordings) and isn't Meeting Notes Agent (internal team notes).

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: Notion.
• A form, app or system that can send each new item to a webhook URL (the agent starts from a webhook).
• About 15 minutes.

• Bring your own AI key
• 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 Notion

Connect Notion and share your clients' pages (or their parent page) with the Fluxo Flow integration (Settings → Integrations → Notion).

• Connecting Notion

3. Add your coaching details

Open “Write the recap” and replace the placeholder with your practice, tone and sign-off. Set the prep-prompt hour and your time zone in “Prep-prompt timing”.

4. Pick your Notion account

Open “Add it to the client's Notion page” and pick the account.

5. Add your reply-to address

Open each email step and enter the address clients' replies should go to.

6. 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

7. Switch the trigger on

Open the trigger, switch the webhook on and copy its URL and secret into your session form.

How it works

The agent is a normal workflow with 18 steps (1 AI step, with a person approving in Reviews). You can open, edit and monitor it like any other workflow.

• Session notes — Starts when your form or app sends data to the agent's webhook URL. Starts when your session form (or note-taking tool via your own form) posts here: client, email, session date, notes or transcript, the next session date and the client's Notion page.
• Write the recap — AI step (runs on your AI provider key). AI writes the recap (insights, commitments with dates, homework, one question for next time), plus the check-in for 3 days later and the prep prompt for the day before the next session. Health topics are kept out.
• Coach approves the recap — A person approves or rejects it in Reviews (the run waits). The coach reads the recap, the check-in and the prep prompt in Reviews (and any health note), edits them and approves. Reject to send nothing.
• Add it to the client's Notion page — Notion: Add content to a page. Branch: Approved. Appends the approved recap to the client's page in Notion.
• Email the recap — Sends an email from your workspace's sender. Emails the approved recap to the client, with replies to you.
• Wait 3 days — Waits 3 days. Pauses for 3 days before the accountability check-in.
• Check-in timing — Step. In code, not AI (after the wait): the check-in goes only when the next session is at least 3 days away or not set. Change the 3 here (within.min).
• Prep-prompt timing — Step. In code, not AI: the prep prompt goes only when the next session is 2 to 30 days away (a run can wait at most 30 days), at 09:00 the day before it. Change the hour (add.time) or set your time zone (timezone, e.g. Europe/London; UTC otherwise) here.
• Send the check-in? — Step. In code: there is an approved check-in text (no commitments = no check-in), no placeholders are left, and the timing check passed.
• Send the prep prompt? — Step. In code: there is an approved prep text with no placeholders left, and the next session is 2–30 days away.
• Which follow-ups? — Decision: picks the branch to follow. Sends the check-in and/or schedules the prep prompt, from the checks in code.
• No follow-ups — Kept in the run history. Branch: Neither. No check-in text (or the next session is under 3 days away) and no next session 2–30 days away.
• Send the check-in — Sends an email from your workspace's sender. Branch: Check-in only. Sends the approved accountability check-in (no prep prompt: the next session is too far off or not set).
• Check-in sent — Kept in the run history. The run history keeps the recap and the check-in.
• Send the check-in — Sends an email from your workspace's sender. Branch: Both. Sends the approved accountability check-in quoting the client's commitments.
• Until the day before the next session — Waits until a date taken from the data (at most 30 days). Branch: Prep only. Waits until 09:00 the day before the next session (computed in code in “Prep-prompt timing”).
• Send the prep prompt — Sends an email from your workspace's sender. Sends the approved prep prompt the day before the next session.
• Follow-ups sent — Kept in the run history. The run history keeps the recap, the check-in and the prep prompt.

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. Edit the sample to match the fields your own form or app sends.

Sample data fields

client_name, client_email, coach_name, session_date, next_session_date, client_notion_page, notes.

• 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.
• Wait steps don't wait: they report how long they would wait and the run goes on.

Go live

• Open the trigger, switch the webhook on and copy its URL and secret into your session form.
• The webhook is protected by a secret: send it in the header shown in the Activation panel (requests without it are refused with 403). Each request starts one run.
• 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.

• Webhook triggers
• Switching a trigger on (Activation)

Questions

What should the session form send?

A JSON POST with client_name, client_email, coach_name, session_date, next_session_date, notes (your notes or a transcript) and client_notion_page (the link of the client's page in Notion, shared with Fluxo Flow).

What happens to health topics?

They're kept out of the recap, check-in, prep prompt and Notion page, and you get a private note in Reviews. If anything suggests someone may be at risk, the note says so first so you can follow your own safety procedure.

What if the next session is weeks away?

A Wait step can pause for at most 30 days, so sessions more than 30 days apart get the recap and the check-in but no prep prompt.

How are the follow-up dates worked out?

In code, not by the AI: after the 3-day wait, the check-in goes when the next session is at least 3 days away (or not set), and the prep prompt is scheduled for 09:00 the day before a session 2–30 days away. Change the hour and time zone in “Prep-prompt timing”.

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.
• Nothing happens when your form sends data: check the webhook is switched on and the request carries the secret header (403 means it's missing or wrong).
• A run shows as paused: it's waiting for someone in Reviews to approve or reject it.
• A run shows “Waiting until …” in History: that's a Wait step; it continues on its own (it can be cancelled through the API).
• 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