How to build an AI language tutor for your business with Bolt (no coding required)

Rule of thumb: if you want to learn a language yourself, do not build this. Any row above teaches you more for less than the weeks below cost, and a curriculum written by people beats a generated deck for a beginner. If you teach, run a school, train staff or want a product of your own, the seat is the bill, and a tutor on your own key turns a price per learner into cents per lesson. The honest middle case is a tutor for beginners in a language you do not speak yourself, and there the right answer is to build it and have a native speaker check what the model generates before learners see it.

* On this template the free-tier line to watch is the pause rather than storage. Nothing large is stored, because conversations are not saved and no files are kept, so a learner is a few rows of text. What bites is that a free project sleeps after a week without activity, and a tutor people open when they have ten spare minutes is exactly the sort that goes quiet. Pro, from $25/mo, ends the pause and keeps a daily backup for 7 days.

Prices and rates from supabase.com, developex.com and bolt.new, checked September 2026.

The GitHub step comes before Bolt exists for you at all. Everything after it happens inside the browser tab Bolt opens, with no install.

1. 01

   Create the project online, import it, then connect the database

   Bolt has no upload button, so the project has to exist as an online repository first. The tutor cannot answer without a server-side function, so the database comes next.

   PromptSet up and connect the databaseCopy

   This project is an AI language tutor. Set it up as React 18 + Vite + TypeScript with Tailwind, and keep this vocabulary throughout: learners, target language, activities, streaks. Two standing rules for the whole build: every call to the AI provider goes through a server-side function with the key in its secrets and a per-learner limit checked first, and the browser never holds the key or decides the limit. Now connect a database and build the tables: a profile per learner with their native and target languages, activity completions with a type and the learner’s local day, streaks per activity with the current and longest run, a calls log for every model call with tokens and a cost estimate, and a settings table holding the daily limit per learner.

   Keep the repository private. Bolt commits to it automatically as you build.

2. 02

   Clear the context, then get the tutor answering with the ceiling

   One function, one corrected reply, and the log and the limit in the same prompt. Test it in the preview with a sentence that has a real mistake in it.

   PromptBuild the tutor function and the ceilingCopy

   Add a server-side function on the database side called chat-assistant that calls my AI provider with the key held in its secrets. It takes the learner’s message, their target and native languages and the last ten turns, and asks the model to reply in the target language at the learner’s level and then, in the native language, to point out up to three mistakes and how to fix them without rewriting the whole message. Before contacting the provider it writes a row to the calls log and checks the learner’s calls today against the limit in settings, returning a friendly limit message when it is hit. Build a simple chat screen that shows the conversation and renders the reply as formatted text, with a placeholder learner id for now.

   The function runs on the database side rather than in Bolt’s preview, which is where the key has to live anyway. Bolt may ask for the provider key when it scans the code. Leave that blank and put the key in the function’s secrets.

3. 03

   Point one prompt at the database layer and lock it down

   Name the layer rather than letting the prompt range over the whole project. The rule is simple here, which leaves no excuse for getting it wrong.

   PromptAdd auth and access rulesCopy

   Working on auth and the database layer only. Add email-and-password sign-up, login, logout, a persisted session and a profile row per learner created on sign-up, with signed-out visitors sent to the login screen. Then row-level security on every table: a learner reaches only their own rows, and every insert and update carries an explicit check that the row is not being filed under someone else. Make every function, including the ones that only record activity, refuse a caller who is not signed in, and switch the tutor function to the real learner id. Show me how to verify a second learner comes back empty for the first learner’s rows.

   Naming the layer keeps the prompt narrow, which Bolt charges you less for and which makes the result easier to check.

4. 04

   Talk the dashboard through in Plan Mode before it is written

   This is the largest and most expensive-to-redo screen in the build. Agreeing the layout and the shared ceiling before Bolt writes a line is exactly what Plan Mode is for.

   PromptBuild the dashboard, the drills and the dictionaryCopy

   Use Plan Mode for this one. I need the learning dashboard as one page with a language picker and four tabs. Chat Practice uses the function from step 02. Flashcards calls a get-flashcards function that generates vocabulary cards for the target language and a chosen difficulty, flips to reveal the meaning and reads the word aloud with the browser’s own speech. Quick Exercises calls a generate-exercise-sentence function for fill-in-the-blank sentences checked as the learner types. Dictionary calls get-word-meaning and translate-text with one tap to swap the two languages. Every function goes through the same key, the same sign-in check and the same per-learner ceiling as the chat. Talk me through the component structure and how the ceiling is shared first, then build it with my name and colours on it.

   Plan Mode costs a message and can save a rebuild. Four functions with four separate limits is the rebuild it saves.

5. 05

   Add streaks and the history page, and check them in the live preview

   The feature that brings learners back tomorrow, and the one that makes them angry when it miscounts. The preview is the running app, so complete an activity and watch the counter move.

   PromptAdd streaks and historyCopy

   Add an activity-completed function that records a completed activity for the signed-in learner and updates that activity’s streak: consecutive days extend it, a missed day resets it, and the longest run is kept, using the learner’s local day sent from the browser and checked on the server. Add a get-streaks function, show the four streaks as counters on the dashboard, and build a streak history page with a week view and charts of completions per day and per activity. Tell me exactly when a streak breaks so I can write it into the help text.

6. 06
   Destination

   Add settings and demo mode, then ship it

   The pieces around the lesson come last. Click the whole thing through as a stranger, then publish, to Bolt’s own hosting by default, or to Netlify if you would rather keep the domain there.

   PromptAdd settings, demo, and publishCopy

   Add a settings page for the learner’s languages and a password change, plus a usage panel showing their calls and estimated cost this period. Add a demo mode: a visitor who continues without an account sees the dashboard shell with sample content and clear prompts to sign up, and none of the functions accept a call from them. Then walk me through the full flow in the preview: open the demo signed out and confirm nothing calls the provider, sign up, hold a ten-turn conversation with mistakes in it, drill cards and an exercise, look a word up, check the streaks moved, hit the daily limit on purpose and read what the app says, and once it holds up, publish it.

Review the access rules (row-level security policies) on every table. For each one, tell me in simple terms who can view, add, edit, and delete records, confirm that people can only reach their own data while the right roles can reach more, and flag anything left open that shouldn’t be.

One rule outranks everything above it: your database service key and your AI provider key belong on the server only, never in the app a learner downloads and never in a repository. If either escapes, treat it as compromised, check your provider’s usage page for what was spent with it, and replace it the same day.

Choose on two things, neither of them speed. First, whether the plan permits commercial use, because Vercel’s Hobby tier does not and a tutor with paying learners is a business. Second, whether a bookmarked link to the streak page opens the app for a learner arriving cold, because their own progress is the page they bookmark. The tutor itself never touches the host: every reply comes from your database’s functions, and the host serves one small static folder.

Add a calls table that records every model call (which learner, which activity, which model, how many tokens went in and came back, whether it succeeded, and a cost estimate) and write to it from every function that calls the provider, successful or not. Then add a ceiling: a limit per learner per day and a total across the whole app, both settings I can change without a deploy, checked inside the function before it contacts the provider and returning a friendly "you have reached today’s practice limit" rather than an error. Do not let the client send the limit or the cost, because both are read on the server. Then add a small usage panel in settings showing calls and estimated spend for the current period.

Add a microphone button to the chat and the exercises that uses the browser’s speech recognition to turn what the learner says in the target language into text, shows the transcript for them to correct before it is sent, and falls back to the text box in browsers that do not support recognition for that language. Then extend the tutor prompt so that when a message arrived by voice, the reply also comments briefly on any word the transcript suggests was mispronounced, without turning the lesson into a pronunciation drill.

Add a five-exchange placement conversation for a new learner in their target language, send the transcript to the ai function and ask for a level on a simple scale with a one-line reason, store it on the profile, and use it as the default difficulty for flashcards and exercises. Re-evaluate every twenty completed activities and tell the learner when their level changes, letting them override it.

Save every generated flashcard and exercise to the learner’s account with whether they got it right, then add a "Review" tab that schedules cards with spaced repetition: the ones they missed come back tomorrow, the ones they knew come back in a week, then a month. Ask the ai function to generate a fresh example sentence for each card on its review day so the same word is met in a new context, and show the learner how many cards are due today on the dashboard.

Pick a lighter model for the high-volume prompts above and save a stronger one for wherever the reasoning actually matters. That is the same token-budget logic as the rest of this page, applied to the app’s own AI calls instead of the build itself. When Bolt flags a missing secret, add the key through its secrets settings instead of pasting it into the chat, and keep every AI feature behind one server-side function so there’s only one key to manage.