--- title: "Chat agent that asks a human on Slack when it is stuck" kind: "Kit" category: "Business" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/ae22f309-58a1-4538-908d-0bf66f852fbf" updated: "2026-11-12" --- # Chat agent that asks a human on Slack when it is stuck > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow with a chat. An AI agent answers what it can. When it has no answer, it asks for the visitor’s email address, then posts the question to a Slack channel so a person can reply. Chat agent that asks a human on Slack when it is stuck is an n8n workflow in the Business category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow is a chat agent that hands a question to a person when it cannot answer. A visitor types in the chat. The agent, GPT-5.6 Sol in Mindket’s copy, answers if it can and remembers the last five exchanges. When it has no answer or is unsure, it calls a tool named `dont_know_tool`. That tool runs a second workflow inside the same file. The second workflow looks for an email address in the visitor’s message. With one, it posts the message to a Slack channel, and the agent tells the visitor a human has been messaged. Without one, it asks the visitor to send the question again with an address. Ten nodes do the work, beside seven sticky notes. ### Who it suits Small teams that put a chat on a help page and want a person to catch what the bot cannot answer, with an address to write back to. Skip it if you need the human to join the chat itself. The agent only posts to Slack, and the reply has to leave Slack by email. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Support leads | Put the agent on a help page and send the odd billing or account question to a Slack channel | A SaaS team’s agent answers feature questions and passes a refund dispute to the support channel. | | Ecommerce | Store owners | Let the agent handle sizing and shipping and pass the rest to the owner | A shop owner gets a Slack message when a visitor asks about a bulk order. | | Agencies | Freelancers who build bots for clients | Hand a client a chat with a human fallback already wired | A freelancer sets up the Slack step for a client’s own workspace. | | Education | Course teams | Answer common questions and route the rest to an instructor | A course team sees each unanswered question in one channel. | You need a little n8n: import a file, add two credentials and pick a Slack channel. The workflow’s own sticky notes give no setup time. ### Where to use it Any n8n that can reach OpenAI and Slack will run it. The chat opens inside n8n until you make the trigger public. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - A help page: switch \`Chat Trigger\` to public to get a chat address you can embed or share - Another channel: swap the Slack node for Gmail, Teams or a ticket tool ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Two accounts cover every step. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | OpenAI | An API key that can use \`gpt-5.6-sol\` | | Slack | A workspace, an app that can post messages and a channel for the questions | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. Add an OpenAI credential and select it in `OpenAI Chat Model`. 3. Save the workflow. The tool calls this same workflow by its id, so it works only once the workflow is saved. 4. Add a Slack credential. In `Message Slack for help`, choose the channel by name. The file leaves it empty. 5. Open the chat with the Chat button at the bottom of the canvas. Ask a question and tell the agent to answer as if it does not know. It should ask for your email address. 6. Send the question again with an address in the same message. Slack gets it, and the agent confirms that a human was messaged. ### How to use it Open the chat and type a question. The agent answers from what the model knows. When it cannot, the visitor sees a request for an email address and then a thank-you. Your team sees the question in Slack with the address typed in the message. Memory covers the last five exchanges for each chat session. What to change for a different result | To change | Where | | --- | --- | | The agent’s rules | The system message in \`AI Agent\` | | When it asks for help | The description of \`Not sure?\` | | The two replies | The texts in the two Code nodes | | The Slack message | The text in \`Message Slack for help\` | | How much it remembers | \`Context Window Length\` in \`Window Buffer Memory\` | ### Example A visitor asks whether a plan includes a feature the agent has no source for. The agent calls its tool. The first message carries no address, so the visitor sees a request to send the question again with one. The visitor sends it again with an address in the same message. Slack gets the question and the address in one post, and the visitor reads that a human has been messaged. Nobody on your side has to watch the chat. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This one is two workflows in one file. The top runs the chat, and the lower one only runs when the agent calls its tool. Start with the chat test from step 5. Then open the run to see the tool call. **For experts.** The tool calls the same workflow it sits in, through its id. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`AI Agent\` | Version 1.2 with the model, the memory and \`Not sure?\` | No agent type is set, so n8n reads it as a Conversational Agent | | \`Not sure?\` | A Tool Workflow node that calls \`$workflow.id\` | It sends \`chatInput\` from \`Chat Trigger\`, the visitor’s latest message | | \`Check if user has provided email\` | An IF node with a regular expression | It tests only the latest message and does not confirm the address exists | | \`Message Slack for help\` | Posts the message to a channel chosen by name | Nothing is chosen in the file | ### Good to know The model was swapped, and the agent node is an older version. - Model: OpenAI’s deprecations page, read on 12 November 2026, gives 23 October 2026 as the shutdown of \`gpt-4\`, with \`gpt-5.6-sol\` as the replacement. Mindket’s copy calls it and drops the temperature of 0.2, since the model’s page lists none - Agent type: version 1.2 runs as a Conversational Agent, which n8n’s code marks deprecated and says it removes in n8n v3. If your n8n shows that notice, swap in a current AI Agent node and reconnect the model, memory and tool - The address: the check reads the latest message only, so the visitor must put the address in the message with the question - Memory: it sits on the n8n instance and is not shared between workers in queue mode - Billing: each visitor message costs one or more OpenAI calls - Public chat: once the trigger is public, anyone with its address can spend your key - Your data: messages go to OpenAI, and a question that asks for a person goes to Slack with its address - Credentials: the JSON holds none ## README ```markdown # Chat agent that asks a human on Slack when it is stuck An n8n workflow with a chat. An AI agent answers what it can and remembers the last five exchanges. When it has no answer or is unsure, it calls a tool that runs a second workflow inside the same file. That one looks for an email address in the visitor's message. With one, it posts the message to a Slack channel so a person can reply. Without one, it asks the visitor to send the question again with an address. ## What is inside - `workflow.json`: the workflow as n8n exports it, ten nodes and seven sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - The chat model was called `gpt-4`, which OpenAI shut down on 23 October 2026. The node is now named `OpenAI Chat Model` and calls `gpt-5.6-sol`, the replacement on OpenAI's deprecations page, read on 12 November 2026. - The model node asked for a temperature of 0.2. The page for `gpt-5.6-sol` lists no temperature setting, so the copy leaves it out. Add it back in the node's options if your model takes it. - The Chat Trigger lost its webhook id, and the Slack and OpenAI nodes lost their credential links. Select your own. - Nothing else. The file has two small Code nodes, and neither needed repair. ## Before you start - An n8n instance, on n8n Cloud or your own server. - An OpenAI API key that can use `gpt-5.6-sol`. - A Slack workspace, an app that can post messages, and a channel for the questions. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Add an OpenAI credential and select it in `OpenAI Chat Model`. 3. Save the workflow. The tool `Not sure?` calls this same workflow by its own id, so it works only once the workflow is saved. 4. Add a Slack credential. In `Message Slack for help`, choose the channel by name. The file leaves it empty. 5. Open the chat with the Chat button at the bottom of the canvas. Ask the agent a question and tell it to answer as if it does not know. It should ask for your email address. 6. Send the question again with an address in the same message. Slack gets the message, and the agent confirms that a human was messaged. 7. To let visitors use the chat outside n8n, set `Chat Trigger` to public and read the notes below first. ## How the tool and its sub-workflow connect `Not sure?` is a Tool Workflow node. Its workflow is `{{ $workflow.id }}`, this workflow, and it starts at `Execute Workflow Trigger`. It sends `query`, the text the agent hands to a tool, and one field of its own, `chatInput`, set from the Chat Trigger's `chatInput`: the visitor's latest message. Only `chatInput` is used downstream. The tool's description tells the agent to use it when it does not know or is not confident. The sub-workflow ends in one of two Code nodes. Each returns a `response` text, and the agent's system message tells it to answer with that text. ## How a run goes 1. `Chat Trigger` takes the visitor's message. 2. `AI Agent` (version 1.2) reads it with `Window Buffer Memory`, whose context window is the node's default of five past interactions, and answers with `OpenAI Chat Model`. 3. If the agent cannot answer, it calls `Not sure?`. `Check if user has provided email` tests the message with a regular expression for something shaped like an address. 4. With a match, `Message Slack for help` posts the message and `Confirm that we've messaged a human` returns the thank-you. Without one, `Prompt the user to provide an email` returns the request to send the question again with an address. ## Change the look - The agent's rules: the system message in `AI Agent`. - The tool's trigger: the description in `Not sure?`. - The two replies: the texts in the Code nodes `Confirm that we've messaged a human` and `Prompt the user to provide an email`. - The Slack message: the text in `Message Slack for help`. - How much it remembers: `Context Window Length` in `Window Buffer Memory`. - The model: `OpenAI Chat Model`. ## Good to know - `AI Agent` is version 1.2 with no agent type set, which n8n reads as a Conversational Agent. n8n's code marks that mode deprecated and says it goes in n8n v3. If your n8n shows that notice, replace the node with a current AI Agent and reconnect the model, the memory and the tool. - The email check looks only at the latest message, not at the memory, so the visitor must put the address in the message that carries the question. It checks the shape of an address and does not confirm it exists. - `Window Buffer Memory` keeps messages on the n8n instance. They are not shared between workers in queue mode. - Each visitor message costs one or more OpenAI calls. Slack posts cost nothing extra. - A public chat lets anyone with its address spend your OpenAI key, so add limits before you share it. - The visitor's messages go to OpenAI, and one that asks for a person goes to your Slack channel with its email address. ``` ## What is in it 3 files, 15 KB, downloaded as a zip. ```text NOTICE.md 607 B README.md 5 KB workflow.json 9 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 7 steps, starting when another workflow calls it or on a chat message - AI: 1 step calls an AI model: AI Agent - Sign-ins: Signs in to: Slack and OpenAI - API keys: No API key is left in the file - Step types: Mindket’s checker reads all 6 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/ae22f309-58a1-4538-908d-0bf66f852fbf) - [Its page on Mindket](https://mindket.com/p/ae22f309-58a1-4538-908d-0bf66f852fbf)