New

Release Announcement: Bold BI 17.2.16 has arrived! Explore the latest features

AI Agent for Data Analysis: Ask Your Dashboard, Get an Answer

Bold BI's AI Agent is a read-only chat in the Dashboard Viewer. Ask a question about the dashboard you are viewing, with no SQL, and it answers with a chart or a written explanation. It works on existing dashboards, considers your last 4 conversations and enforces row-level security.

  • Ask in plain English — no SQL, no filters, no report request
  • Get a chart or a written answer, depending on the question
  • Keep asking — the Agent builds on your last 4 conversations
Start Your Free Trial

30 days. No credit card required.

Request Demo
Bold BI AI Agent answering a plain-English question with a chart inside a live dashboard
  • Syscon
  • Networcx
  • A4B
  • DigiQuip
  • CarNow
  • Revver
  • Smartway2
  • GeniusVets
  • Talentegy

How does Bold BI AI Agent keep answers secure and governed?

Permissions apply to every answer

Row-level security is enforced before anything is retrieved. OAuth and SAML sessions carry over in Cloud and On-Premises.

SOC 2 Type 2 and HIPAA

Bold BI holds a SOC 2 Type 2 report. Its products are considered a Business Associate under HIPAA and independently audited for HIPAA compliance.

Your data does not train the models

Customer data is not used to train or fine-tune Bold BI's AI models.

Read the SOC 2 overview and the HIPAA overview.

How does Bold BI AI Agent replace the report request?

Bold BI's AI Agent skips the ticket: ask inside the dashboard you are already viewing, with no SQL or query language. "Which segments contributed most to the churn increase in March?" shouldn't wait for a report.

Before — file a request

  • File a request with the BI team
  • Wait for the report to be built
  • Ask a follow-up and start again

After — ask in the dashboard

  • Skip the request queue entirely
  • No dependency on the BI team
  • Ask a follow-up at once; the Agent considers your last 4 conversations

How does Bold BI AI Agent turn a question into an answer?

Bold BI's AI Agent works in the same 3 steps behind every question, whether it is a quick count or a written explanation.

  1. Ask

    "Show me top 5 products by margin this quarter." Plain English, the way you'd ask a coworker.

    Understands business terms, not only field names
  2. Check

    The Agent maps your words to your data using schema context and enforces row-level security before it retrieves anything. SQL runs only inside the secure Bold BI environment.

    Role-based access and row-level security on every request
  3. Answer

    A chart or a written answer. Written answers need "Enable Widget Insights and Dashboard Summary" switched on.

    Multi-turn: considers your last 4 conversations

Read-only analysis

What can you ask Bold BI AI Agent?

Bold BI's AI Agent covers 4 areas of read-only analysis and never edits widgets or the layout. On-premises users on v10.1 or later switch it on with the global "Enable AI Agent" option.

Ask about your data

Trends, comparisons, counts and likely contributors.

Business terminology

Clear table and column names and exact column references improve accuracy.

Plain-English explanations

Where Widget Insights and Dashboard Summary are enabled, answers can include a written summary.

Keep the thread going

Refine and drill with follow-ups instead of starting over.

Need to build or change the dashboard itself?

The Agent only reads. Use AI Copilot to build visuals, or Prompt to Dashboard to generate a dashboard from one prompt.

AI-generated output should be reviewed before it's used for business decisions.

How is Bold BI AI Agent different from AI Copilot and AI Assistant?

Bold BI has 3 AI surfaces on one AI engine and security model: AI Copilot, AI Agent and the AI Assistant hub, which embeds from v14.1.

AttributeAI CopilotAI AgentAI Assistant
Where it lives
Dashboard Designer
Dashboard Viewer
Standalone hub
What it does
Builds and refines visuals
Answers questions about the viewed dashboard
Combines AI Copilot and AI Agent
Edits dashboards
Yes, creates and customizes widgets
No, read-only
No
Saved conversations
Session ends after 2 hours idle
Not saved as a named conversation
Saved; resume, rename and delete

What does a Bold BI AI Agent question look like?

A Bold BI AI Agent session needs no SQL and runs in 3 stages on a sample Sales Analysis dashboard: the question, the chart and a follow-up that refines the answer.

Bold BI AI Agent chat panel on a Sales Analysis dashboard offering suggested questions such as how many customers per city
Bold BI AI Agent answering "What is the total sales amount per month?" with a monthly total sales column chart
Bold BI AI Agent chat panel on a Sales Analysis dashboard showing a request being processed

Embedding

Can you embed Bold BI AI Agent in your own application?

Yes. The in-dashboard AI Agent embeds with the Dashboard Viewer, and the standalone AI Assistant embeds with the JavaScript SDK from v14.1. The embed token is generated on your server.

  1. Bring Your Own Key

    OpenAI, Azure OpenAI and Anthropic (Claude); Anthropic needs v16.1.90 or later. On-premises only.

  2. White-labeled

    An embedded AI Assistant carries no third-party AI branding.

  3. Security inherited

    Row-level security carries into embedded sessions, and so does SSO in Cloud and On-Premises.

  4. AI usage

    Admins review AI credit use by user, site and time period.

Who is Bold BI AI Agent for?

Bold BI positions the AI Agent for 4 audiences: executives, BI and data teams, SaaS product teams, and IT and security.

Executives

Ask a question, read the explanation, skip the analyst meeting.

BI / data teams

Every question the Agent answers is one less ticket in your queue.

SaaS product teams

Embed it, white-label it, ship conversational analytics as your feature.

IT / security

Roll it out on role-based access, row-level security and OAuth and SAML sessions.

What are the limits of Bold BI AI Agent, and when is it not the right fit?

Bold BI's AI Agent is not the right fit for building or editing dashboards, or for calculations such as median and variance.

  1. It is read-only: it never edits widgets or the layout.

  2. Written answers need "Enable Widget Insights and Dashboard Summary" switched on, and its chat is not saved as a named conversation.

  3. The AI Assistant features, including the AI Agent, support 6 aggregations (COUNT, COUNTD, SUM, MIN, MAX, AVG), not MEDIAN or VARIANCE.

  4. A tenant can send up to 100 messages per minute, and accuracy varies by language.

  5. Your own AI provider is on-premises only.

How do reviewers rate Bold BI?

Bold BI is rated 4.4 out of 5 on G2 and 4.9 out of 5 on Capterra (as of October 2026).

G2

G2: 4.4 out of 5 (as of October 2026)

Capterra

Capterra: 4.9 out of 5 (as of October 2026)

Questions

Bold BI AI Agent frequently asked questions

What is Bold BI's AI Agent?

A read-only chat in the Dashboard Viewer that answers questions about the dashboard you are viewing. It never edits dashboards. Use AI Copilot to build visuals or Prompt to Dashboard to generate a dashboard. See the AI Agent documentation.

How is the AI Agent different from the AI Assistant?

The AI Agent lives in the Dashboard Viewer and its chat is not saved. The AI Assistant is a standalone hub combining AI Copilot and AI Agent, with saved conversations you can resume, rename and delete.

Does every answer include a written explanation?

No. It answers with a chart or a written explanation, depending on the question. Written answers need "Enable Widget Insights and Dashboard Summary" switched on.

Is my data safe with the AI Agent?

Row-level security is enforced before anything is retrieved, and customer data is not used to train or fine-tune Bold BI's AI models. Written answers send the schema, your question and some processed data to the model.

Can I use my own AI provider?

Yes, on-premises only: OpenAI, Azure OpenAI and Anthropic (Claude), with Anthropic needing v16.1.90 or later. The built-in Bold AI Service needs no credentials.

Try Bold BI AI Agent free for 30 days