SerpApi.Org
The way to use a chatbot is given in the name. They are designed to be used by having two-way conversations with the LLM using natural language. You type something into the chatbot, and it replies. In some cases, continually typing stuff into a chatbot isn't the most efficient way to do things, so I set up a system that does it for me.
Talking to a chatbot can soon get repetitive
Even scheduled tasks aren't always ideal
When you have something new to ask your chatbot, typing directly into the chat window (or talking to it using a voice conversation) is the most obvious thing to do. You type in your prompt and get your response in the same window, and you can carry on a back-and-forth conversation.
Things start to get more tedious when you're constantly asking the same things over and over. If you've hooked up your chatbot to your email, you might start each day asking what tasks and events you have coming up. After several days of asking the same thing each morning, it can soon get tiresome.
Scheduled tasks can help. You can set up tasks to run at specific times with instructions telling the chatbot what to do instead of having to enter the prompt each time. You could create a scheduled task that runs at the same time each morning and asks the chatbot to summarize your calendar events.
The problem is that scheduled tasks are most useful when the trigger and overall instructions remain broadly the same each time. If you're providing new information each day, they're not ideal.
I took talking to AI out of my hands
An LLM is the brain, but n8n is the glue
Thankfully, there are ways to save yourself from having to talk to your chatbots over and over. You can set up automations that will do the talking for you. That's exactly what I've done using n8n.
n8n is automation software that lets you build visual workflows to perform sets of actions automatically. You can run it in the cloud, but you can also run it on your own server, which is exactly what I do. This means that my automations run locally on my own hardware.
The workflows can run at set times or can be triggered by webhooks or other actions. The key part is that n8n can send prompts to LLMs. The workflow can generate the prompt for you, so you don't need to write anything yourself each time, and the prompt can be completely different from day to day.
You can get n8n to pass the prompts to cloud-based AI services, or you can point it at a local LLM running on your own hardware. My computers aren't powerful enough to run large LLMs, so I use a mix of both: local LLMs running on a mini PC for simpler jobs and cloud-based services for the more complex tasks.
You can use APIs from services such as Anthropic, Google, and OpenAI, but you may have to pay API fees to use them. I use Groq, which is a cloud-based AI service that lets me use their super-fast hardware to run free AI models, with multiple models to choose from.
The best part is that limited use is free; Groq’s free tier currently allows up to 1,000 requests per day on several models, which is more than enough for my needs.
How I use my system on a daily basis
From trigger to output, no chat window required
I have multiple workflows set up in n8n that I use on a daily basis. They run without me touching anything, and I never need to enter any prompts into a chatbot.
One of my favorites generates a morning briefing that is spoken aloud on a smart speaker the first time we enter the kitchen in the morning. The automation pulls information including the day's calendar events, the weather forecast, and information on what my kids have for lunch at school, all of which is provided by Home Assistant.
The automation then passes this mess of information to a local LLM running through Ollama on my mini PC. The prompt asks the model to turn the mess of information into a written morning briefing with a dash of personality. This written briefing is then converted into audio using a local text-to-speech (TTS) model and played through the smart speaker as a spoken announcement.
Another automation pulls stories from several RSS feeds that contain news on my favorite topics or from my favorite sources. These stories are then passed to the local LLM, which converts them into a written digest. The digest is shared to my Kindle so that I can read a custom news briefing each morning.
An automated system isn't perfect for everything
I still talk to my chatbot all the time
Running these prompts on my local hardware isn't fast. I could use Groq to do it in next to no time, but the morning briefing contains personal information that I'd rather not send to third-party servers, so using the local LLM is a better option.
The slow speed of the responses isn't an issue, however. I can get the automation to run on schedule using n8n, so I have it generate the morning briefing at 5 am each day, and it's completed long before we get up. The announcement then plays instantly when we enter the kitchen.
Using automation isn't ideal for every job, of course. I still enter hundreds of words a day into chatbots for off-the-cuff questions or when working on specific projects. Having a workflow enter your prompts for you is best for cases where you do the same things every single day, since it can take that job completely off your hands.
You don't need to chat with a chatbot
The first experience of AI for many of us was using a chatbot such as ChatGPT. AI has progressed far beyond that now, to the point where the recent UI updates to the ChatGPT app have relegated the chat window to a second-class citizen. You can do so much with AI without using the chat window at all.
