Case Study Drafter setup guide

What it does

Turns end-of-project feedback into a case-study draft in Notion and asks the client to approve the quote.

Starts when your end-of-project feedback form posts a response to the webhook.
AI writes a case-study draft (challenge, solution, results) and picks a pull quote copied word for word from the client's feedback.
Lists what to confirm with the client (numbers, title, permission) instead of guessing.
Saves the draft as a page in your Notion case studies database.
Drafts an email asking the client to approve the quote and attribution; marketing approves it in Reviews before it's sent.

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 case studies database.
A feedback form or site that can post to a webhook.

What it doesn't do

It never invents metrics, results or quotes: it uses only what the client wrote.
It never publishes the case study: publishing stays with you.
It doesn't track the client's approval: their reply comes to your inbox.
No email is sent when the client asked not to be contacted or left no email; the draft is still saved.

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: Notion.
A form, app or system that can send each new item to a webhook URL (the agent starts from a webhook).
About 12 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 Notion

Connect Notion and share your case studies database with Fluxo Flow (Settings → Integrations → Notion).

Connecting Notion

3. Describe your style

Open “Draft the case study” and replace the placeholder with your company and case study style.

Setting	What to enter	In step
Your company and case study style	Replace the placeholder with what your company does, your case study style and length, and who signs the permission email. It starts as “[DESCRIBE YOUR COMPANY, WHAT YOU DELIVER, YOUR CASE STUDY STYLE AND LENGTH, AND WHO SIGNS THE PERMISSION EMAIL HERE]” until you replace it.	“Draft the case study”

4. Pick the Notion database

Open “Save the draft in Notion” and pick your account and database.

Setting	What to enter	In step
Notion account	The Notion workspace with your case studies database. Pick your connected Notion account.	“Save the draft in Notion”
Case studies database	The database each draft becomes a page in (title property “Name”). Share it with Fluxo Flow first: ••• → Connections.	“Save the draft in Notion”

5. Add your marketing inbox

Open “Email the permission request” and enter the address the client's reply should go to.

Setting	What to enter	In step
Marketing inbox (Reply-to)	The client's reply (approval or changes) comes back to this address.	“Email the permission request”

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, copy the webhook URL and secret into your feedback form or site, and switch it on. Fields: company, contact_name, contact_title, contact_email, project, permission, challenge, solution, results, comments.

How it works

The agent is a normal workflow with 9 steps (1 AI step, with a person approving in Reviews). You can open, edit and monitor it like any other workflow.

End-of-project feedback — Starts when your form or app sends data to the agent's webhook URL. Your end-of-project feedback form (or your site) posts each response to this webhook.
Draft the case study — AI step (runs on your AI provider key). AI turns the client's feedback into a case-study draft (challenge, solution, results, pull quote) using only what they wrote, and drafts the permission email.
Save the draft in Notion — Notion: Create a page in a database. Creates a page in your case studies database with the full draft and the questions for the client.
Draft saved — Kept in the run history. The run history keeps the Notion page link.
OK to contact the client? — Decision: picks the branch to follow. Clients without an email or who asked not to be contacted get no email; the draft stays in Notion.
Draft saved only — Kept in the run history. Branch: Don't contact. The draft is in Notion; no email is sent.
Marketing approves the draft and email — A person approves or rejects it in Reviews (the run waits). Branch: Ask permission. Marketing reads the draft in Notion and the permission email in Reviews, edits the email if needed and approves it to send.
Email the permission request — Sends an email from your workspace's sender. Branch: Approved. Emails the client the quote and the questions, asking for approval. Replies go to your marketing inbox.
Permission requested — Kept in the run history. The run history keeps the draft link and the email sent.

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

company, contact_name, contact_title, contact_email, project, permission, challenge, solution, results, comments.

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, copy the webhook URL and secret into your feedback form or site, and switch it on. Fields: company, contact_name, contact_title, contact_email, project, permission, challenge, solution, results, comments.
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.

Questions

Will it make up results?

No. It only uses what the client wrote. Missing numbers become questions for the client, and the pull quote is copied word for word from the feedback.

Does it publish the case study?

No. The draft stays in Notion for your team; publishing is yours, after the client approves.

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 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.