Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
27 contributions to AI Agency Plus +
Let your AI agent draft, but make it ask before it sends
Something I keep coming back to with client builds: the scary part of an AI agent isn't the reply it writes, it's the tool it calls. Sending the email, booking the slot, giving the refund. n8n has a human in the loop option for agent tools now. You mark a tool as needing review, and when the agent decides to use it the workflow pauses and sends an approval request to Slack, Telegram, Gmail, Outlook etc. Approve and it runs, deny and the agent gets told no. Where I'd use it for local businesses: Refunds or discounts for a shop. Agent drafts the reason and amount, owner taps approve on their phone. Booking changes for a salon or clinic. Agent finds the new slot, staff confirms before the client gets a text. Anything that messages a customer in the first few weeks after handoff. Once the owner trusts it, turn review off for the low risk tools only. One thing the docs flag that's easy to miss: tell the agent in its system prompt that some tools need approval, otherwise it gets confused when a call is denied. Docs: https://docs.n8n.io/advanced-ai/human-in-the-loop-tools Walkthrough example: https://docs.n8n.io/build/integrate-ai/ai-examples/human-in-the-loop-for-tools Which tool would you never let an agent call without a human checking first?
1 like • 15d
@Emma Shaw a Limit node is such an easy add, approval plus a cap feels way safer than either one alone (thanks Andrew). haven't run the timeout test yet, I'll drop what happens here when I do
1 like • 14d
@Suman Inavati the approve on autopilot thing is so real. mine just says the tool name right now, gonna add the name, amount and the agent's reason so she can decide from the lock screen
Free: Claude Duet vs ChatGPT Dots one-page decision sheet
As I said in the video, here is the one-page sheet. It tells you which one to pick in 30 seconds, for you or for your client. What's inside: - Who should pick Duet and who should pick Dots - The full 3 to 3 scoreboard from the video - What to check first, because neither one is available everywhere - How to sell the setup to a business The PDF is attached. Any doubt, just comment here and I'll help you. https://www.youtube.com/watch?v=LRjgDohn0bU
1 like • 14d
the "check first, neither is available everywhere" bit is useful, i would've picked one for a client and then found out it doesn't work in their country lol. saving the sheet for the salon owner
Before you change the prompt on a client's AI workflow, run it against the same 10 messages first
Something I keep running into while building a reply bot for my friend's cleaning biz: I tweak the prompt, test it on 2 messages, looks fine, ship it. Then I have no idea what it does now on the questions I didn't try. Turns out n8n has a built in fix for this called Evaluations. The light version is pretty simple. You put a handful of real example inputs in a data table (or a Google Sheet), add an Evaluation Trigger, and it runs your workflow once per row and writes the output back next to each input. So every time you change the prompt or swap the model, you rerun the same set and compare instead of eyeballing one test. What I'm putting in my test set: the normal everyday questions, the weird ones that tripped it up before, and a couple where the right answer is basically "someone will get back to you". Pulling real ones from past executions is way easier than making them up. There's also a metric based version that scores each run (like correctness, or whether it called the right tool) if you want actual numbers. I haven't gone that far yet. Docs if you want to try it: Overview: https://docs.n8n.io/advanced-ai/evaluations/overview Light evaluations: https://docs.n8n.io/advanced-ai/evaluations/light-evaluations Metric based: https://docs.n8n.io/advanced-ai/evaluations/metric-based-evaluations/ Do you test your AI workflows against a fixed set before changing them, or just run a couple and ship?
1 like • 15d
@Emma Shaw only when the prompt or model changes. rerunning on every tiny tweak would drive me mad lol, and it's only 10 rows so it takes like two minutes when it matters
1 like • 14d
@Hardik Tanwar honestly never thought about it, her customers are pretty much all local. one random spanish message wouldn't hurt though, at least i'd see if it answers in spanish or just ignores it
Building chatbots for anyone with EU customers? the AI Act disclosure rule has been live since August
worth a look if you build chat or voice bots for clients who sell into the EU. Article 50 of the EU AI Act has applied since 2 Aug 2026. the short version as i read it: if an AI system talks directly to people, they have to be told it's an AI, unless that's already obvious from context. there's also a rule about machine readable marking on AI generated content. the Commission's FAQ mentions a grace period to 2 Dec 2026 for systems already on the market, but only for that marking part (and it's tied to their omnibus proposal), not the chatbot disclosure. the bit that caught my eye: a bunch of write ups say a small business running a support bot on its site is in scope too, not just big companies. so a one line "you're chatting with an AI assistant" at the start seems like a cheap thing to bake into every build. not a lawyer and the guidance is still settling, so read the source yourself: Article 50 text: https://artificialintelligenceact.eu/article/50/ Commission FAQ: https://digital-strategy.ec.europa.eu/en/faqs/transparency-obligations-under-article-50-ai-act anyone already adding an AI disclosure by default, even for non EU clients? and where do you put it, first message or the widget header?
1 like • 15d
first message makes sense. the part I'm unsure about is the other direction, when the owner jumps into the chat halfway through. should the bot drop a line like you're now chatting with a person? feels weird if the customer thinks they're still talking to the bot
Stop burning API calls every time you test an n8n workflow (pin data)
small thing that saves a lot of time + credits when building client workflows. when you're testing step 6 of a workflow you usually end up re-running steps 1-5 every single time. that means hitting the CRM again, calling the AI model again, sometimes even sending a test email again lol. n8n lets you pin data on a node. you run it once, pin the output, and from then on the workflow just uses that saved output instead of calling the API again. you can also edit the pinned data by hand to fake edge cases, like an empty field or a weird phone format, without waiting for a real one to show up. couple things to know: pinned data only works for manual test runs, production executions ignore it. you can't pin on nodes that output binary data. and unpin before handing the workflow over so nobody gets confused by it. docs: https://docs.n8n.io/data/data-pinning/ editing pinned data: https://docs.n8n.io/data/data-editing/ do you guys pin data while building or just re-run the whole thing each time?
2 likes • 15d
pin data saved me so many fake test leads lol. only thing that confused me at first is it only applies to manual test runs, so the live workflow still pulls real data. which is what you want, but I didn't get why my test and live results looked different for a while
1-10 of 27
Amanda Brown
4
75 points to level up
@amanda-brown-6207
Solve problems using AI

Active 2d ago
Joined Oct 9, 2026