Chat page

The Chat page is where you ask questions about your connected data, or general questions. Each thread is attached to one workspace and one connection.

What the Chat page is for

Chat lets you ask business or operational questions in natural language. For a question about your data, STYD translates it into a controlled database query, validates it, executes it safely, and returns a structured answer. A general question, a request for advice or a draft is answered from general knowledge and labelled General knowledge.

A chat thread uses one connection. This keeps the database context clear: STYD never mixes two connections in one answer. The workspace's uploaded documents can be joined into the answer, each part under its own label.

Chat layout

Left panel
Create, select, and switch between chat threads.
Right panel
Ask questions and review answers.
Connection badge
Shows which database connection the active thread is using.
Input area
Type your question and send it to STYD.

Create a chat thread

Open the Chat page
Click New Chat
Select the database connection for the thread
Create the thread
Ask your first question
Create a new thread when you want to ask questions about a different connection. A single thread should not mix multiple databases.

Connection badge

At the top-right of the chat area, STYD shows the connection name used by the current thread.

Connection name
Confirms which database the thread is attached to.
Warning icon
Appears when AI Guide is still running or when schema analysis may be incomplete.
Always check the connection badge before asking important questions.

While an answer is being written

While we work, a line under your question shows progress, and the answer replaces it when it is ready. If an earlier answer in the thread is still running, it says “Waiting for current answer to finish”.

If it fails, you see “This answer could not be finished. Try asking again.”

Result tags under an answer

Some answers include small tags below the assistant response. These tags help you understand where the answer came from and how confident the system is.

Source: Database
The answer was generated from database results.
Source: Model
The answer may rely on model reasoning instead of direct database output.
Source: General knowledge
The answer was written from general knowledge, not from your data.
Confidence
Indicates how confident STYD is in the generated answer.
Verification
Shows whether answer claims were supported by available evidence.

How we found this

When available, STYD shows a link called How we found this under the AI response. This opens a trust panel that explains, in plain language, how the answer was produced from your data. For an answer from general knowledge, it says: “Written from general knowledge and your business context, not from your data.”

What the panel includes

  • Simple explanation, a short summary of what STYD did.
  • Business logic used, the calculation or selection logic behind the answer.
  • Filters applied, the conditions used, such as company, invoice type, payment status, date range, or customer filters.
  • Data used, the business objects or tables used to answer the question.
  • Assumptions, important interpretation notes, such as when no date range was requested.
  • Technical details, on a database, the SQL query and technical trace; on Odoo, the Odoo records and filters read. Collapsed by default for non-technical users.

Example

If you ask for draft invoices, STYD may explain that it searched customer invoices, kept only invoices with draft status, applied your accessible Odoo company scope, and returned the matching records.

This panel is designed to help business users trust the answer without needing to read SQL. On PostgreSQL and MySQL, the SQL remains available under technical details for advanced users, debugging, or audits.

Feedback buttons

Each assistant answer can be reviewed with thumbs up or thumbs down feedback.

Thumbs up
Mark the answer as helpful. This can help similar answers rank better later.
Thumbs down
Open a feedback form to explain what went wrong.

Thumbs down feedback

When you mark an answer “Not helpful”, a short form asks what went wrong. You pick the closest reason. There is no field for SQL or notes.

The reasons
Wrong number, wrong period, wrong customer, product or filter, missing data, STYD did not understand my question, wrong language, too slow, or other. On a database connection there is also “wrong data source”. Answers taken from your uploaded files have reasons of their own, such as wrong document or wrong citation.
Reasons for general answers
An answer from general knowledge offers “Wrong or unhelpful advice”, “Too generic”, “Should have used my data” and “Out of date”, plus misunderstood question, wrong language, too slow and other. An answer from your data that ends with a General knowledge part also offers “Wrong or unhelpful advice”.
What did you expect?
One optional field where you can describe the answer you expected.

Parallel prompts and sequential answers

You can send multiple prompts one after another. STYD keeps the thread context and returns answers in order so the conversation remains consistent.

For complex analysis, it is still better to ask one clear question at a time.

Best practice

Start with a clear question, review the result, then refine with follow-up questions instead of starting over.

Good prompts produce better answers. Clear filters, time ranges, and business terms help STYD generate more accurate queries.

Need help? Contact support