KYC & AML Screening Assistant

What it does

Pre-reviews every onboarding file against your KYC policy and queues it for a compliance officer.

• Receives each onboarding file (applicant data, document data and optionally your screening provider's results) from your onboarding form or core system through a webhook.
• AI pre-reviews it against the KYC / AML policy you paste in: missing items, inconsistencies, red flags with quoted evidence, and a summary of any sanctions, PEP or adverse-media hits you sent.
• Document expiry and age (e.g. proof of address older than your policy allows) are worked out in code from the document dates, never by the AI.
• It suggests a risk rating and due-diligence level, neutral questions for the applicant and a checklist for the officer.
• High-risk files, reported matches and enhanced-due-diligence cases are posted to your compliance channel in Slack and go to a priority review queue.
• Every file waits in Reviews for a compliance officer; reviewed files are logged in your Google Sheets KYC review log as an audit trail.

What it needs

• A paid plan (agents run live on paid plans).
• An AI provider key (Settings → AI Providers).
• Slack and Google Sheets, connected in Settings → Integrations.
• An onboarding form or core system that can send each file to a webhook URL, and your own sanctions / PEP screening provider for list checks.

What it doesn't do

• It never approves, rejects, onboards or exits a customer: a compliance officer decides, in your own systems. Its rating is a suggestion.
• It doesn't screen against OFAC, UN, EU or PEP lists itself (there's no list connection): it only reports the screening results you send, and says when screening is missing.
• It can't see ID documents or tell whether they're genuine; it checks the data you send for consistency.
• It doesn't re-screen existing customers, file reports or replace your compliance program; it never uses protected characteristics.

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: Slack and Google Sheets.
• A form, app or system that can send each new item to a webhook URL (the agent starts from a webhook).
• About 30 minutes.

• Bring your own AI key
• Slack (live)
• Google Sheets (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 Slack

Connect the Slack workspace your compliance team uses (Settings → Integrations → Slack).

• Connecting Slack

3. Connect Google Sheets

Connect the Google account that can edit your KYC review log (Settings → Integrations → Google Sheets).

• Connecting Google Sheets

4. Paste your KYC / AML policy

Open “Pre-review the KYC file” and replace the placeholder with your policy. The pre-review is only as good as these rules.

5. Pick the Slack account and compliance channel

Open “Alert compliance in Slack” and pick your account and a private channel. Invite the app to private channels first (/invite @Fluxo Flow).

6. Pick your KYC review log

Open both log steps and pick your account, spreadsheet and tab (usually the same in both). Header row: Date, Application, Applicant, Type, Completeness, Screening, Suggested risk, Due diligence, Summary, Red flags, Missing items, Queue, Status.

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, switch the webhook on and have your onboarding form or core system send each file to its URL.

How it works

The agent is a normal workflow with 10 steps (1 AI step, with a person approving in Reviews). You can open, edit and monitor it like any other workflow.

• New onboarding file — Starts when your form or app sends data to the agent's webhook URL. Your onboarding form or core system posts each applicant's details, document data and (optionally) your screening provider's results to the webhook URL.
• Work out the document dates — Step. In code, not AI: for each document in the file, whether it has expired (days until its expiry date) and how old it is (days since its issue or statement date), in the trigger's time zone. No document is dropped.
• Pre-review the KYC file — AI step (runs on your AI provider key). AI checks the file against your KYC policy for missing items, inconsistencies and red flags, summarizes any screening results you sent and suggests a risk rating for the officer.
• Priority review? — Decision: picks the branch to follow. High suggested risk, a reported screening match or enhanced due diligence goes to the priority queue with a Slack alert; everything else to the standard queue. Both need an officer.
• Alert compliance in Slack — Slack: Post a message. Branch: Priority. Posts the applicant, suggested rating, screening status and red flags to your compliance channel (no documents or ID numbers).
• Compliance alerted — Kept in the run history. The run history keeps the alert that was posted.
• Officer reviews (priority) — A person approves or rejects it in Reviews (the run waits). Branch: Priority. A compliance officer reviews the file and the AI pre-review, does the checks on the checklist and records the outcome; approving only logs the reviewed file.
• Log the reviewed file (priority) — Google Sheets: Add a row. Branch: Reviewed. Appends the reviewed file to your KYC review log for your audit trail.
• Officer reviews (standard) — A person approves or rejects it in Reviews (the run waits). Branch: Standard. A compliance officer confirms the file and the AI pre-review; approving only logs the reviewed file.
• Log the reviewed file (standard) — Google Sheets: Add a row. Branch: Reviewed. Appends the reviewed file to your KYC review log for your audit trail.

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

application_id, customer_type, full_name, email, date_of_birth, country_of_residence, address, occupation, source_of_funds, expected_monthly_volume, expected_activity, documents (a list), screening_results.provider, screening_results.sanctions_matches, screening_results.pep_matches, screening_results.adverse_media.

• 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, switch the webhook on and have your onboarding form or core system send each file to its URL.
• 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

Does it screen against OFAC, UN or EU lists?

Not by itself: Fluxo Flow has no sanctions or PEP list connection. Run screening with your provider and include its results in the file you send; the agent summarizes them and flags matches. If none are sent, it tells the officer screening is still needed.

Does it approve or reject applicants?

No. It prepares a pre-review. A compliance officer decides, in your own systems, and approving in Reviews only logs the reviewed file.

Can it read passport images?

No. Send the document data (type, number, expiry, name and date of birth as captured by your ID-verification tool). It checks consistency, not authenticity.

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).
• 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.

• Debugging failed runs
• Error messages
• Get help