AI Twin

Your Blog's AI Twin | A Blog AI Chatbot Trained on Your Posts

Your blog's AI Twin knows you better than you do. It remembers every article you have written and speaks in your voice; when visitors ask where an old post is, ask about a certain view, or ask what you have been thinking about lately, it picks up the thread in your tone. It is not an agent that writes the blog for you; it is another talking you that your blog gains, your AI rep.

At the edge of a valley at dawn, a mechanical knight built on human anatomy pauses alone on a cliffside path, an open book in its hands, a winding river and ridge upon ridge fading into golden haze before it; beside it a wooden chest brims with books and loose scrolls. This knight, da Vinci's first robot modelled on the human body, is where humanity's wish to recreate itself began. The road from that biomimicry to today's neural networks reaches all the way here, to the blog's AI persona speaking in your voice.

Cultivate an AI Twin of yourself on your blog

Your blog has been written over years, post by post: the recipe you wrote carefully back then, the note jotted after seeing an exhibition, the reflections from a season you wanted to keep are all held inside. But hidden in all this are two losses you cannot see. A reader who truly takes it in, who wants to know more about the person who has been writing for years, will not flip that far back on their own, and a few posts on the home page hardly let them really know you; and you yourself may not remember every post clearly, sometimes wanting to converse with your past self or recover a lost view, only to flip back a few pages and not remember which post it was in.

Its voice is defined by you; the road it has walked is in the blog you built up

This AI persona's voice is defined by you. The plugin has a settings area called SOUL, a self-introduction you write for the persona, telling it your tone, your views, and how you see things; it need not be long, a few sentences are enough: who you are, what you care about, and how you tend to respond.

It has been to the same places you have, seen the same scenery, eaten the same food, and remembers the things you went through, all of it drawn from your blog itself. The views accumulated over years of writing, the subtle shifts in your tone, and the thread of each inner journey are the you that readers most need to know, and that even you cannot fully remember. An AI persona will certainly remember this more completely than you do: its memory is your blog itself, and it can feel every mood you have written.

A visitor asks, and your AI Twin answers for you

Someone who scrolled into your latest post asks, "Have you written anything on a similar topic before?" In your voice, it picks out three old posts and attaches the links. Someone who finished a post comes back and asks, "Your 2022 travel post, where did you go?" It can answer the place and lists the later posts in that series for them too.

Someone browsing recent content asks, "Your taste lately seems a bit different from a few years ago?" It says yes, after a certain year you began writing more in a certain direction, and points out the post where it turned. Someone wanting to go further asks, "Do you take collaborations or commissions? How do I get in touch?" It knows which page you put your contact on and takes them straight there.

By the time a visitor sees these few exchanges, your blog has quietly risen to another level. Posts once merely archived can now be called back to speak by your persona at any time; a reader who thought the most but never asked, who would quietly close the page, can now ask the questions on their mind one by one; and where a visitor once saw only the latest few posts on the home page, now they can walk, through your voice, into every story you have written.

Can you afford this character?

AI token cost can start from $0. Cloud AI providers commonly offer free tiers, and those tiers are counted per model: each model comes with its own separate quota. RAG Chatbot reserves one routing slot each for retrieval, response, and vision, and you can assign a different model to each slot, so multiple quotas work for you in parallel. Some providers offer only text models; in that case vision is handed to another provider that has an image model. Multi-model routing is the headroom this architecture builds in for you.

Cerebras's free tier gives a single text model 1M tokens a day; with one model applied to both retrieval and response, that is roughly 45 questions answered per day. For a small site, this quota lands right on the sweet spot of long-term sustainability.

Even if traffic one day grows beyond the free tier, switching to an entry-level paid API costs about the price of a soda each month. The model we used while developing the plugin is Llama-3.2-3B-Instruct, a step smaller than Llama-3-8B-Instruct, the cheapest paid model commonly offered by cloud API providers, so any paid AI model on the market only puts you on firmer ground.

RAG Chatbot itself adds no markup on any token.

Model

Llama 3 8B Instruct

Provider
OpenRouter / Groq
Input Price
$0.05 / 1M tokens
Output Price
$0.08 / 1M tokens
Tokens per Q&A
≈ 20k input + 2k output
Per Answer
≈ $0.0012
Monthly cost at 1,000 questions
≈ $1.2