by TradeCRM (LX AI)
Open TradeCRM, provide the required inputs, run Demo to preview the workflow, then switch off Demo when a live key is configured.
A CRM built for one trade
Decision-support only — confirm before you publish or act.
When you first open the app you see a blank form asking for three inputs: your trade name, the typical job size you handle, and the usual follow‑up interval you prefer. Fill those fields with short text entries. The trade name can be anything like “electrician”, “plumber”, or “HVAC tech”. Job size is a number that reflects the average dollar value of a project you take on. Follow‑up interval is the number of days you usually wait before checking back with a lead.
After you submit the form the app creates a default pipeline with four columns: New Lead, Quote Sent, Job Scheduled, and Completed. Each column gets a colour label that you can change later if you want a different visual cue. The demo mode is automatically turned on, which means the AI backend is not called and you see placeholder data that shows how the workflow would look.
To see a live preview click the “Run Demo” button. The app will populate each column with sample cards that contain a lead name, a short description, and a suggested next action. You can drag a card between columns to simulate moving a lead forward. Use this preview to verify that the column names and the flow match the way you work.
When you have a real API key from your AI provider, go to the settings page, paste the key into the field labelled “Live AI Key”, and toggle the demo switch off. The app will then start sending real requests to the model and you will see actual suggestions based on the inputs you gave.
TradeCRM lets you rename columns, add new stages, or remove ones you do not need. To edit a column title, click the pencil icon that appears when you hover over the column header. Type the new name and press Enter. For example, a plumber might change “Quote Sent” to “Estimate Sent” and add a column called “Parts Ordered” between Quote Sent and Job Scheduled.
You can also set a default next‑action hint for each column. Open the column settings menu and choose “Edit hints”. Type a short phrase that reminds you what to do when a lead sits in that stage, such as “Call client to confirm details” or “Check inventory for required parts”. The hint appears on every card in that column as a small tooltip.
If you work with sub‑trades or special services you can create extra columns that are only visible when you tag a lead with a specific label. To add a label, open a card, click the “Labels” field, and type a keyword like “emergency” or “maintenance”. Then go to the column visibility settings and choose to show a column only when the label matches. This keeps the board clean for routine jobs while still giving you space for special cases.
Below is a table that shows a typical configuration for an electrician who does both installations and repair work.
| Column | Typical hint | Optional label |
|---|---|---|
| New Lead | Collect address and scope | none |
| Quote Sent | Follow up if no reply in 2 days | estimate |
| Parts Ordered | Verify delivery date | installation |
| Job Scheduled | Confirm time with client | none |
| In Progress | Log hours daily | repair |
| Awaiting Inspection | Schedule third‑party check | installation |
| Completed | Request review and referral | none |
Start by clicking the “Run Demo” button on the main board. The app will generate five sample leads, each with a random name and a short description that matches the trade you entered. Observe how the cards appear in the New Lead column.
Pick the first lead and open its detail pane by clicking the card. You will see fields for contact phone, email, and a free‑text notes area. Fill in any real information you have; the demo will not save it permanently, but it lets you test the UI.
In the detail pane you will also see a section titled “AI suggestion”. In demo mode this section contains a static example such as “Send a quick SMS to confirm availability”. When you switch to live mode the same area will show a suggestion generated by the model based on the lead’s description and your trade inputs.
To move the lead forward, drag the card to the Quote Sent column. As you do this, a small toast appears confirming the move. Repeat the process for the remaining leads, trying different paths: some leads can go straight to Job Scheduled if you already have a quote, others may need a follow‑up first.
While you drag cards, notice the column hints that appear at the bottom of the pane. They are the short phrases you set earlier. Use them as a quick checklist before you decide to move a card.
When you have moved all leads through the board, click the “Reset Demo” button to clear the sample data and start again. This is useful if you want to test a different column layout or a new set of hints.
Each card in a column shows three pieces of information: the lead title, a short description, and the next‑action hint. The hint is derived from the trade‑specific rules you entered when you set up the column. For example, if you told the app that you usually call a lead within 24 hours after receiving a quote, the hint in the Quote Sent column will read “Call lead to confirm details”.
The hint is not a command; it is a reminder. You should still verify that the action makes sense for the specific situation. If a lead has indicated they prefer email, you might choose to send a message instead of a call, even though the hint says to call.
When you switch to live mode the hint is generated by the model. The model looks at the lead description, the trade name, and the typical workflow you defined. It then produces a phrase that fits the pattern you gave in the hints editor. Because the model is a language model, the output can vary slightly each time you refresh the card.
To see the raw model output, open the developer console in your browser and look for the network request labelled “/suggest”. The response includes a field called “suggestion_text”. You can copy that text and compare it to the hint shown on the card. This helps you understand how the model is interpreting your inputs.
If you notice that the hint often misses a step you consider important, go back to the column hints editor and add a more precise phrase. For instance, if the model frequently suggests “Send email” but you want to include a deadline, edit the hint to “Send email and note the response deadline”. The model will then try to incorporate that wording in future suggestions.
TradeCRM does not promise that every suggestion will lead to a closed job. The output is decision‑support only; you must review each hint before you act on it. There is no guarantee of a 100 % success rate, and the app never claims to replace your professional judgment.
The tool does not include built‑in accounting, invoicing, or tax features. If you need those functions you will have to use a separate service or manually export data. TradeCRM focuses solely on the pipeline and the next‑action cues that help you move a lead forward.
It does not provide real‑time synchronization with external calendars or messaging platforms unless those integrations are explicitly added in this build. Do not assume that a Google Calendar sync or a Slack notification exists just because you saw it mentioned elsewhere.
The demo mode is intentionally ephemeral. Data entered while the demo switch is on is stored only in the browser’s local storage and is cleared when you reload the page or clear the cache. Treat any information you type in demo mode as temporary and not suitable for record‑keeping.
Finally, TradeCRM does not claim to be a comprehensive risk‑management system. For guidance on responsible AI use you can consult public frameworks such as the OWASP LLM Top 10 (https://owasp.org/www-project-top-10-for-large-language-model-applications) and the NIST AI Risk Management Framework (https://www.nist.gov/itl/ai-risk-management-framework). These references are provided for informational purposes only and do not imply endorsement or certification.
When the demo switch is off and a live key is present, TradeCRM sends requests to the model endpoint you configured. The request payload includes the trade name, the lead description, and the column hints you set. The response is a short text suggestion that the app displays in the card’s detail pane.
All user‑entered data — trade name, job size, follow‑up interval, column titles, hints, and label definitions — is saved to the browser’s IndexedDB under a key that is unique to your installation. This means that if you close the tab and reopen it later your pipeline will appear exactly as you left it.
Lead cards themselves are not stored permanently in demo mode. In live mode each card’s description and any notes you add are also saved to IndexedDB, but the AI‑generated suggestion is not persisted; it is regenerated each time you open the card. This design keeps the app lightweight while still giving you a record of the information you entered.
If you want to export your pipeline for backup or to move it to another device, open the settings menu and choose “Export data”. The app will download a JSON file containing all of your configuration and the current state of each lead. To import, select “Import data” and pick a previously exported file. The app will overwrite the current state with the contents of the file.
Because the app runs entirely in the browser, no data leaves your machine unless you explicitly send it to the model endpoint. The model provider’s privacy policy governs what happens to the data you send in the request. Review that policy before you enable live mode if you have confidentiality concerns.
A CRM built for one trade
Operators and builders who need a fast first draft or checklist from TradeCRM.
Yes in explicit Demo mode. Live AI requires a configured key.
No. Outputs are decision-support; you still review before publishing or acting.
Only if those features are implemented in this product build — do not assume them from marketing copy.
Runs may be stored locally under the product's .data/ boundary; treat demos as ephemeral.