Bruin CLI Step 5 of 7

Build an AI Finance Agent for QuickBooks

Guide overview
  1. Set Up Your Environment6 min
  2. Load and Model QuickBooks Data5 min
  3. Map Your Chart of Accounts5 min
  4. Build the Context Layer5 min
  5. 5Ask, Report, and Dashboard6 min
  6. 6Take Actions in QuickBooks8 min
  7. 7Schedule and Share4 min
PreviousBuild the Context LayerNextTake Actions in QuickBooks

1) Ask quick questions

Start a session in the project root and ask in plain language. The agent picks the report table, shows the SQL, runs it with bruin query, and answers with the month and caveats:

AI Prompt

Who owes us money, and how overdue is it? Group by customer, largest open balance first.

AI Prompt

What's our runway? Show the inputs and tell me how confident I should be in the number.

AI Prompt

What did we spend on software last quarter, and which tools are new in the last 90 days?

AI Prompt

Which customers churned or contracted last month, and how much MRR did we lose?

Watch the first few answers closely. If the agent queries the wrong table or skips a caveat, fix the rule in AGENTS.md once instead of correcting it in every chat.

Sign up to our newsletter

Practical updates on open-source data pipelines, AI analysts, governance, and what we are shipping at Bruin.

The signup form is hosted by Brevo. Allow marketing cookies to load it.