Upload completed work
Start with labeled text, a spreadsheet of picture links, or photos sorted into category folders.
BUSINESS-SPECIFIC AI
Build your Business-Specific AI with StayCharted AI Model Trainer (AMT). Turn your team’s text, images, and decisions into private models—without writing model-training code.
Your decisions → consistent, structured results
FROM EXAMPLES TO A WORKFLOW
Start with labeled text, a spreadsheet of picture links, or photos sorted into category folders.
Review inconsistent labels, gaps, and detected sensitive values in text before training. For images, check duplicates, category mismatches, and unreadable links.
Build a private model and measure its results against examples it has not seen before.
Use your model through an API, batch files, or connections to your existing business tools.
Correct mistakes and add new examples as your business changes. Train an improved version when you’re ready.
Customer request → The right team
Explore solutionM8 stainless bolt → BOLT-M8-30-SS
Explore solutionDifferent descriptions → One format
Explore solutionQuote needed by Friday → High priority
Explore solutionSource codes → Your internal categories
Explore solution18V cordless drill → Power tools
Explore solutionVISION · IMAGE MODELS
Teach an AI Image Classifier Model from pictures you’ve already sorted. Categorize new product, damage, or inspection photos, with uncertain results flagged for review. Location and camera metadata are removed from the copies used by your model; your original uploaded ZIP is retained unchanged until you delete the model.
01 · ADD EXAMPLES
Upload a ZIP with one folder per category, or a spreadsheet with picture links and their category labels.
02 · CHECK AND TRAIN
Review category mismatches, conflicting labels, near-duplicate pictures, and links that could not be read.
03 · USE YOUR MODEL
Submit new pictures in a ZIP or sheet of links and download their categories. Or use your model from your own apps.
SENSITIVE DATA CHECKS · EVERY PLAN
Check your text examples for personal information and secrets before training. You decide what your model gets to learn from.
AMT flags recognizable email addresses, phone and payment card numbers, IBANs, US Social Security numbers, IP addresses, passwords, API keys, and credentials in links. Findings are shown with partially hidden values.
Mask detected values with labels such as [MASKED-EMAIL], exclude affected rows, or keep them. Your choice is recorded with who made it and when.
Models trained on masked text apply the same masking before reading new text through files, the app, and API calls. Your own files keep their original text.
Included on every plan, including Free, for models that read text. Names, street addresses, and free-text details such as medical notes are not detected yet; remove those yourself before training.
How we built sensitive-data checks ↗A SIMPLE WAY TO GET STARTED
Choose a model for your task, with plans that grow alongside your business.
Start with a Free workspace with Classifier Models and file downloads. No card needed.
Invite your team members. Paid plans are priced per workspace, not per person or model.
FIND YOUR STARTING POINT
Start with a recurring decision where your team’s experience defines what a good result looks like.
StayCharted AMT checks text before training so you can mask detected values, exclude affected rows, or keep them. Models trained on masked text also mask new inputs. The check does not detect everything; names, street addresses, and free-text medical details still need manual removal.
Yes. The Vision add-on enables AI Image Classifier Models on Essentials and Business. Train from categorized photos, then categorize new images through files or your own apps. Business with Vision also supports Dedicated AI Image Models, which train the AI itself on your examples. Vision recognizes what a picture shows; it is not OCR for reading text inside receipts or forms.
AI Model Trainer (AMT) is StayCharted’s product for building Business-Specific AI from your own examples. Train private AI models to match records, route requests, score and prioritize work, map between systems, standardize information, and categorize data. Add Vision to learn categories from images. Start with a recurring task where your team already has examples of the right decisions.
Start with a spreadsheet or business-system export containing examples and their correct outcomes, such as tickets paired with categories or supplier records paired with approved matches. For images, use a ZIP with one folder per category or a spreadsheet of public picture links and category labels.
You do not need to write training code or have AI expertise: provide examples, train a model, and review its results. Connecting the Prediction API to your application may require a developer.
Start with the kind of examples you have. For clearly worded text categories, try a Classifier Model. When wording varies, consider an AI Classifier Model. For pictures, start with an AI Image Classifier Model through Vision. If your task needs finer distinctions, compare a Dedicated AI Model using separate test examples. Choose based on the errors that matter in your workflow.
Yes. Models you build are private to your workspace. The shared, ready-made AI behind AI Classifier Models and AI Image Classifier Models does not learn from your uploaded data. Dedicated AI Models are trained on your examples for your workspace.
Yes. Start with a lasting Free workspace with Classifier Models and file downloads, with no card needed. Add a paid workspace for AI Classifier Models, Dedicated AI Models, API access, or more capacity.
STAYCHARTED AI MODEL TRAINER
Build your Business-Specific AI with AMT. Start with examples you already have, test your model’s results, and put it into your workflow.
Try AI Model Trainer