# Guardian for n8n: 8 Approval Gate Mistakes to Avoid > The mistakes that break a Guardian approval gate in n8n, from wiring all three outputs to the send to a rule field typo, and how to fix each one. Source: https://learn.ynteractive.com/content/blog/guardian-n8n-approval-mistakes · Updated 2026-10-20 · Free from Stepthrough (https://learn.ynteractive.com) Quick answer A Guardian approval gate in n8n usually fails in one of three ways: the policy never fires because its field name doesn't match the [payload](https://learn.ynteractive.com/content/glossary/request-body), the workflow sends anyway because more than the **Allowed** output is wired to the send, or an approved email goes out twice because two workflows listen for the same action type. All eight mistakes below are named in the free [Guardian approval gate lesson](https://learn.ynteractive.com/content/guardian-n8n-ai-agent-approval-before-sending-email), where you build the policy in the real Guardian app for a made-up firm, Harbor Line Bookkeeping, whose agent drafts about 60 [invoice](https://learn.ynteractive.com/content/glossary/invoice) reminders a month. Last updated October 20, 2026 [Take the free module →](https://learn.ynteractive.com/courses/n8n-jump-start/18)Module 18 of the free [n8n Jump Start](https://learn.ynteractive.com/courses/n8n-jump-start) course, about 14 minutes. No account needed. By [Robert Breen](https://learn.ynteractive.com/content/about) · Published October 20, 2026 · Updated October 20, 2026 · 5 min read Guardian · n8n · AI agents · Troubleshooting The goal of the setup is simple: team emails go out alone, client emails wait for a person, and deletes never run. That is [human in the loop](https://learn.ynteractive.com/content/glossary/human-in-the-loop) placed only where it matters. ## What are the most common Guardian mistakes? | # | Mistake | What happens | Fix | | --- | --- | --- | --- | | 1 | All three outputs wired to the send | Denied and held emails still go out | Connect **Allowed** only | | 2 | Rule field name differs from the payload | The rule silently never fires | Test with the real payload | | 3 | No project ticked | The policy won't save | Tick **Default** under **Apply to Projects** | | 4 | An allow policy for deletes | Deletes can run | Rely on **Deny unmatched actions** | | 5 | First test against a live send | A real email goes out mid-test | Disable the send or use **Listen Mode** | | 6 | Two workflows listening for one action type | An approved email is sent twice | One active listener per action type | | 7 | Action type typed differently in n8n | The node's request doesn't match the policy | Use the same `email.send` in both | | 8 | [API key](https://learn.ynteractive.com/content/glossary/api-key) pasted into a chat or shared workflow | Anyone can act as your workflow | Keep it in the Guardian API credential | ## Why does the email still send when it needs approval? **1. Wiring every output to the send.** The Guardian node has three outputs: **Allowed**, **Denied** and **Needs Approval**. Only **Allowed** connects to Send an Email. Denied and Needs Approval should each end in a note or a response. If all three feed the send, Guardian's answer makes no difference. An approved email doesn't come back through that first node. It is sent by a separate approval path: a **Guardian Approval Trigger**, then a Guardian node set to **Enforce**, then the send, reading the approved payload. ## Why does my Guardian rule never fire? **2. A field name typo.** A rule checks a field by name. If the rule checks `recipent` and the workflow sends `recipient`, the rule is silently dead. The lesson's knowledge check asks exactly this. The fix is testing: **Test This Policy** before you save, and the flask icon on the saved policy afterwards. Run one payload that should pass (a team address returns **ALLOW**) and one that should not (a client address returns **REQUIRE APPROVAL**). Both are [sandbox](https://learn.ynteractive.com/content/glossary/sandbox-environment) tests, so nothing is created or logged. **7. A different action type in n8n.** The policy applies to one action type in lowercase dot notation, `email.send`. The Guardian node's **Action Type** must be the same string, and its payload must use the same field names as the rule: `recipient`, `subject` and `body`. ## Why won't my policy save? **3. No project.** Under **Apply to Projects**, tick **Default**. Guardian won't save a policy without a project. While you're on that form: the **Manual** option builds rules from scratch, and the AI Wizard isn't available yet, so use Manual and build the rules by hand. ## Try it free, step by step **Guardian: Make Your n8n AI Agent Ask Before It Emails a Customer**. A business case for a small firm whose n8n agent drafts client emails: turn "team emails go out alone, client emails wait for a person, deletes never happen" into a Guardian policy, test it, and see… You do every step yourself in a practice copy of Guardian, it checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/guardian-n8n-approval-gate) [Or read the full step-by-step guide](https://learn.ynteractive.com/content/guardian-n8n-ai-agent-approval-before-sending-email) ## How do I stop an agent from deleting records? **4. Writing an allow policy for deletes.** You don't need a "never delete" rule at all. Under **Settings > Organization**, **Default Policy Behavior** has **Deny unmatched actions** selected and marked Recommended: any action type without an explicit policy is blocked. If the agent ever asks for `record.delete`, Guardian answers Denied. The only way to break that is to write an allow policy for it, so don't. (**Allow unmatched actions** is the wrong default for this job anyway.) This is how a [policy engine](https://learn.ynteractive.com/content/glossary/policy-engine) limits [agent permissions](https://learn.ynteractive.com/content/glossary/agent-permissions): the safe answer is the default one. ## How do I test without sending a real email? **5. Testing against a live send step.** For the first real run, disable the send node (select it and press D), or turn on **Listen Mode** under the Organization tab. Listen Mode records every request and what Guardian would have decided, without blocking anything. Read those decisions, then switch it off. ## Why did an approved email go out twice? **6. Two listeners.** If two active workflows listen for the same action type, both can act on one approval. Keep exactly one active workflow listening for `email.send`. If you copy a workflow to experiment, deactivate the copy. ## Where should the Guardian API key go? **8. Anywhere but the credential.** Create the key under **Settings > API Keys** (Guardian asks you to verify your email first) and add it, with the signing secret and the base URL, to the Guardian API credential in n8n. Don't paste it into a chat, a screenshot or a shared workflow. ## What does a working setup look like? A client reminder arrives in the **Approval Inbox** marked "Blocked, awaiting human approval" with the reason and an expiry time. **Edit Payload & Approve** shows the original payload next to the one that will run, so you can fix a wrong amount first. The original stays in the [audit trail](https://learn.ynteractive.com/content/glossary/audit-trail), and the edited version is checked against the policy again. For all settings on one page, use the [Guardian cheat sheet](https://learn.ynteractive.com/content/cheat-sheets); for the tool listing, see [Guardian in the AI tools directory](https://learn.ynteractive.com/content/ai-tools/automation-workflows#tool-guardian). ## Key takeaways - Wire only **Allowed** to the send; approvals use their own trigger path. - Test every policy with the real payload, before and after saving. - Leave **Deny unmatched actions** on and never allow deletes. - Use Listen Mode or a disabled send for the first run. - One active listener per action type, and the key stays in the credential. ## Frequently asked questions **Does Guardian send the email for me?** No. Guardian only answers Allowed, Needs approval or Denied and records the decision. n8n does the sending. **What does Guardian return for an email to my own team?** With the lesson's rule, **ALLOW**, because the address is on the list. Everything else gets **REQUIRE APPROVAL**. **Can I change a draft before approving it?** Yes, with **Edit Payload & Approve**. The edited version is checked against the policy again. **How many approvals does one email need?** The lesson leaves **Approvals Required** at 1. **Where can I read more answers?** See the [Guardian for n8n FAQ](https://learn.ynteractive.com/content/blog/guardian-n8n-approval-faq) and [Guardian use cases by role](https://learn.ynteractive.com/content/blog/guardian-ai-approval-use-cases). ## Free lessons in this post - [Guardian: Make Your n8n AI Agent Ask Before It Emails a Customer](https://learn.ynteractive.com/content/guardian-n8n-ai-agent-approval-before-sending-email): A business case for a small firm whose n8n agent drafts client emails: turn "team emails go out alone, client emails wait for a person, deletes never happen" into a… ## Watch it in a free lesson: Find and Use n8n Templates ### Find and Use n8n Templates: video walkthrough Full walkthrough · 3:32 · with captions Skip the blank canvas. Find a ready-made workflow in the n8n template gallery, import it into your workspace, connect Google Sheets and Gmail, test it with a real form entry and publish it. The whole lesson narrated step by step, recorded in Stepthrough’s simulated practice environment. [Watch it with chapters and the full transcript](https://learn.ynteractive.com/content/find-and-use-n8n-templates#watch) From the free lesson [Find and Use n8n Templates](https://learn.ynteractive.com/content/find-and-use-n8n-templates) ## Related terms Plain-English definitions, each with an example from a free lesson. [Request body (payload)](https://learn.ynteractive.com/content/glossary/request-body) · [Invoice](https://learn.ynteractive.com/content/glossary/invoice) · [API key](https://learn.ynteractive.com/content/glossary/api-key) · [AI agent permissions](https://learn.ynteractive.com/content/glossary/agent-permissions) · [Policy engine](https://learn.ynteractive.com/content/glossary/policy-engine) · [Wait node](https://learn.ynteractive.com/content/glossary/wait-node) · [Agent orchestration](https://learn.ynteractive.com/content/glossary/agent-orchestration) · [Agentic AI](https://learn.ynteractive.com/content/glossary/agentic-ai) [The full AI glossary](https://learn.ynteractive.com/content/glossary) ## Keep reading - [Guardian AI Approval Gates: Use Cases by Office Role](https://learn.ynteractive.com/content/blog/guardian-ai-approval-use-cases): Where an office puts a Guardian approval gate in an n8n workflow, role by role: bookkeepers, account managers, ops, HR, sales and executive assistants. - [Guardian for n8n FAQ: Policies, Approvals and Cost](https://learn.ynteractive.com/content/blog/guardian-n8n-approval-faq): Plain answers about Guardian for n8n: what a policy is, how Allowed, Needs approval and Denied work, testing, the Approval Inbox and what's free. - [n8n Showing Feedback Agent: 9 Mistakes to Avoid](https://learn.ynteractive.com/content/blog/n8n-showing-feedback-agent-mistakes): Mistakes that hurt an n8n showing feedback agent for listing agents, from price advice and buyers' names to mismatched columns and missing memory. [All blog posts](https://learn.ynteractive.com/content/blog) · [All free tutorials](https://learn.ynteractive.com/content)