Table of Contents
Overview
Trovata AI Agents extend the capabilities of Trovata AI Chat by turning one-time questions into automated, recurring workflows.
Each agent operates like a dedicated analyst. It follows user-defined instructions, retrieving live data from your Trovata workspace using the same tools available in Trovata AI Chat, and delivers formatted results to an activity feed you can check at any time. Teams can build a fleet of agents, each focused on a specific task: summarizing your daily cash position, monitoring large payments, tracking idle cash, scanning for FX exposure, etc.
Agents use the same secure infrastructure as Trovata AI Chat (AWS Bedrock AgentCore, powered by Claude Sonnet 4.6). Your data is never used for model training, never leaves your Trovata instance, and is never accessible to anyone but you.
Trovata AI Security
Summary: You get the analytical power of a state-of-the-art AI model with enterprise-grade data isolation and security. Your financial data is processed securely, never used for training, and never accessible to anyone but you.
The entire system runs on AWS Bedrock AgentCore, a secure, isolated environment purpose-built for enterprise AI. When you ask a question, the AI retrieves your data through Trovata's own verified API layer, analyzes it, and presents the answer, all within that secure infrastructure. Here's what that means for you:
Your data is never used to train the AI. Not your balances, not your transactions, not your questions. AWS Bedrock guarantees that your inputs and outputs are completely isolated from model training. Your data goes in, your answer comes out, and nothing is retained or learned from.
Anthropic never has access to your data. Claude Sonnet 4.6 powers the intelligence, but Anthropic as a company has no access to anything processed in your Trovata sessions. That's a core guarantee of the AWS Bedrock architecture.
Nothing is stored beyond your session. Your financial data isn't persisted, cached, or logged outside of your Trovata instance. When your session is over, it's over.
Your conversations are private. Other users in your organization cannot see your chat history. Your sessions belong to you.
Errors are transparent. If a tool call fails or data isn't available, the AI tells you what happened. It never silently fills in the blanks with made-up numbers.
Getting Started
Check Your Access
To use Trovata AI Agents, two things need to be in place:
Feature Enabled: Trovata AI Agents must be turned on for your organization.
Permission Assigned: Your user role needs the Read Trovata AI Agents permission in the User & Entitlements section of Trovata. The video below displays a walkthrough on how to create an AI user group for your organization.
You'll find Trovata AI in the left sidebar navigation (or go directly to /trovata-ai). Log in with your standard Trovata credentials. No separate account needed. If you can't see Trovata AI Agents in your sidebar, contact your organization's Trovata administrator and/or Trovata support (via chat or email at support@trovata.io) to verify that the feature is enabled and your role has the right permissions.
Find Agents in Trovata
Navigate to Trovata AI in the left sidebar, then click Agents. The Agents page opens with two tabs:
Activity is the default view, showing a timeline of all agent execution results grouped by date (Today, Yesterday, and specific past dates).
Listing shows all agents you've created, with their name, status, and last run time.
A New Agent button is visible in the top right corner of both tabs.
Creating Agents & Starter Templates
If you're not sure where to start, the Agent Builder offers five starter templates below the chat greeting:
Daily Cash Position Summary summarizes your cash position across all accounts.
Weekly Cash Flow Report provides a weekly breakdown of credits, debits, and net flow.
Account Reconciliation Monitor checks reconciliation status across your accounts.
90-Day Cash Forecast generates a forward-looking cash forecast.
Large Transaction Alert flags transactions at a threshold you define.
Click any template to send its instructions into the chat. The Configuration tab auto-populates with the template's default instructions and a suggested schedule. You can customize both before saving.
Click New Agent to open the Agent Builder. The builder is a full-screen dialog with two panels:
Left Panel: A chat interface where users can describe what they want the agent to do in plain English. Five starter templates are also available, serving as examples to get going quickly.
Right Panel: Two tabs.
Configuration (left tab) is where users set the agent's instructions and schedule.
Preview (right tab) is where users test the agent's output before saving.
Describe Your Agent (Left Panel)
Type a description of what the agent should do in the chat input. For example:
"Provide a comprehensive overview of all credit transactions from yesterday, including transaction amounts, account details, counterparties, and any relevant descriptive information."
The AI responds conversationally to help you refine the instructions. Your description is automatically populated into the Instructions field on the Configuration tab. You can continue the conversation to iterate, or edit the instructions field directly.
General Tips
The quality of an agent's output depends on the instructions you give it. A few principles that make a difference:
Be specific about scope. "Monitor all accounts" is broad. "Monitor my USD accounts at Chase and Bank of America" gives the agent a clear target.
Define the timeframe. "Check yesterday's transactions" or "analyze the last 7 days" is precise. "Check recent activity" is ambiguous.
Set thresholds when relevant. "Flag any single transaction over $100,000" gives the agent a clear rule. "Flag large transactions" leaves too much interpretation.
Describe the output format. "Provide a summary table with columns for amount, account, counterparty, and description" tells the agent exactly how to structure the result.
Iterate using chat. The Agent Builder's chat interface is there to help you refine. Start with a rough idea, review the AI's response, and tighten the instructions based on what you see.
Configuring a Schedule (Right Panel)
Switch to the Configuration tab on the right panel. Below the Instructions field, you'll see the Trigger section. Click the Trigger dropdown and select Schedule. Three cadence options are available:
Hourly: Select Hourly and choose the 5-minute increment of each hour for when the agent should run (for example, :00, :05, :15, :30, :45, etc.).
Daily: Select Daily and configure:
Time: Choose the hour and toggle AM/PM.
Timezone: Select from a full list of IANA timezones (e.g., America/New_York, America/Los_Angeles, Europe/London).
Multiple Times: Click + Add another time to have the agent run more than once per day. Remove additional entries with the X button.
Weekly: Select Weekly and configure:
Days: Use the multi-select dropdown to choose which days of the week the agent should run (Sunday through Saturday).
Time and Timezone: Same as daily, with support for multiple time entries.
Email Delivery
Agents can be shared via email delivery. Specified recipients do not have to be provisioned as Trovata users to receive agentic reports.
Preview and Save (Right Panel)
Before saving, switch to the Preview tab on the right panel. The agent runs a live preview using your current instructions and streams the result in real time. The output may include formatted text, tables, highlighted values, or recommended actions, previewing what the agent would produce on its scheduled execution run.
If you update the instructions and switch back to Preview, a new preview generates automatically with the updated instructions. When iterating on agents, users will frequently toggle back and forth to fine-tune the instruction set.
Save the Agent (Right Panel)
Click the agent name in the top bar (defaults to "Untitled agent") to give it a descriptive name, something like "Daily Credit Transaction Report" or "Weekly Cash Activity Monitor."
When you're ready, click Save. You'll see two options:
Save as draft saves the agent without activating a schedule. The agent appears in your Listing tab with a Draft status badge. It does not run automatically.
Save and activate saves the agent and starts the schedule immediately. The agent appears with an Active status badge and runs automatically at the times you configured.
A confirmation banner ("Agent saved and activated") appears at the bottom of the screen, and the agent is now visible in your Listing tab.
Managing Agents
View Agent Details
Click any agent in the Listing tab to open the detail panel on the right side. The panel shows:
Status: Draft, Active, or other lifecycle states.
Last run: When the agent last executed, or "Never" if it hasn't run yet.
Last modified and Created on dates.
Configuration: The full instructions text and trigger summary (e.g., "Scheduled: Daily").
Execution History: A list of past runs, each with a timestamp, status badge, and a brief summary of results.
Edit an Agent
Open the context menu (three-dot icon) on any agent in the Listing tab and click Edit, or click the Edit button in the detail panel. The Agent Builder opens in edit mode with the existing chat history and configuration loaded. Make your changes and click Save.
Duplicate an Agent
Click Duplicate from the context menu. A copy of the agent is created with the same instructions and trigger settings. The copy is independent, so editing it does not affect the original.
Delete an Agent
Click Delete from the context menu. A confirmation dialog appears. Confirm to permanently remove the agent and its execution history.
Run an Agent Manually
For any active agent, click Execute from the context menu or the play button in the detail panel header. The agent runs immediately regardless of its schedule, and the result appears in the Activity feed within seconds to a minute.
Monitoring Agent Activity
The Activity tab is your dashboard for all agent executions. Results are grouped by date, with the most recent at the top.
Each entry shows the agent name, a brief summary of the result, a timestamp, and a color-coded status badge:
Success (green) indicates the agent found actionable results.
No Action (gray) indicates the agent ran but had nothing to report.
Warning (yellow) indicates a condition worth your attention.
Alert (red) indicates a critical condition was detected.
Error (red) indicates the execution failed.
Click any entry to open the full output in a detail panel. Results may include formatted text, data tables, highlighted values, and recommended actions.
Use the search bar on either tab to filter agents or activity entries by keyword.
Available Data Sources
Agents have access to various data retrieval tools. Each connects to a specific part of your Trovata workspace:
Account balances provide current and historical balances, grouped by institution, entity, currency, or account type. Supports daily, weekly, monthly, and quarterly cadences.
Account details return individual account records with balances, connection info, and account metadata.
Transactions return individual transaction records with full details. Filter by date, amount, type (credit/debit), account, tag, keyword search, and more.
Transaction summaries provide aggregated transaction totals and counts, useful for high-level reporting without individual transaction detail.
Transaction analysis shows transaction trends over time, segmented by tag, institution, currency, entity, or other dimensions.
Account summaries deliver a high-level cash position overview across accounts, grouped by any account attribute.
Payments return payment records filtered by status (open, submitted, approved, failed, completed, and others) and type (ACH, Wire, RTP, Transfer).
All tools accept optional filters. If no filters are provided, sensible defaults are applied (e.g., date range defaults to the last 90 days, currency defaults to USD).
AI Agent Workflows
Trovata AI Agents work with the data in your instance. Here's a list of recommend agents. We encourage users to leverage these agents as a frame of reference, and iterate off of them to establish the best agents for your organizational needs.
Category | Description | Example Instructions/Prompt |
General | Executive summary of key cash areas | Generate a monthly executive summary: 1). Opening and closing total balance for the month 2). Monthly cash flow summary 3). Balance trend chart data by week 4). Forecast for next 90 days 5). Any reconciliation issues. Have the summary speak in treasury terms tailored to presenting to a CFO who wants to be able to tell the story or impact of the details in the report. |
General | Reporting package w/ email delivery | Display the following 5 reports, with a line inserted between them, in the following order: "Report 1", "Report 2", "Report 3", "Report 4", and "Report 5". |
General | Custom reporting calendars (i.e. sharing a 4-4-5 schedule directly in the instructions) | Using my custom 4-4-5 calendar instructions below, recreate a report with the custom calendar dates, using "XYZ Report Name" as a reference. |
Tags | Tagging assistance | Identify my untagged transactions on a daily basis and make suggestions as to what tags I should apply them to. Also, suggest what TQL query I would need to add them to the respective suggested tags. |
Balances | FDIC balance limit threshold (250k) | Display a list of all of my accounts and the respective balances, with an indication on which ones are above the FDIC limit. Show the date and when the balance was last shared from the bank (as of column). |
Balances | Balance limit w/ visual indicator | Display a balance report in bar chart format showing the last 5 business days that draws a horizontal line through the chart at the $1,000,000 mark to give me a visual representation of how close my account balances are to that limit. |
Balances | Weekly balance trends | Show week over week balance trends grouped by entity for current and prior week. Highlight any entity where the balance increased or decreased by more than 10%. |
Balances | Cash concentration reporting with designated thresholds | On a quarterly basis I'm providing our board of directors with our cash concentration reporting. Can you provide me with the global % allocation of cash per bank (display the full bank name) as of 6/30/2026. No individual bank should have more than 30% allocation, so flag those if they do. |
Balances & Transactions | Custom daily cash position report | Create a prior day daily cash report that displays the following lines items in this order and rounds to the nearest Million with one decimal place in dollars. Title it "Total Liquidity Summary — Insert Prior Day's Date"
Borrowing Base (Use the balance from Account *1255) Letters of Credit (Sum All Manual Debt Account Types) Revolving Loan (Use the Virtual Account *1448) --- "Net Available - US Only" will be the subtotal of the above
"Cash Balance - US Only" will be the Sum of all of the Operating Account Types ---
"Excess Availability - US Only" will be the sum of all of the above
"Mexico Region 1 Cash Balance" will be 0.3 Million "Mexico Region 2 Cash Balance" will be 0.1 Million --- "Available Cash - Mexico Only" will be the Sum of the above
--- "Total Liquidity" will be the sum of all of the above
Also, below this report, display the top five largest collections from customers by displaying the customer name and amount (exclude ZBAs or anything that looks like intercompany) and also display the top five largest disbursements by displaying the vendor name and amount (exclude ZBAs, payroll, or anything that looks like intercompany). |
Transactions | Rolling top 10 collections | Show me the top 10 collections into accounts *0810, *1885, and *2550 in the past week, and remove all ZBA or sweep transactions. |
Transactions | Rolling top 5 disbursements | Show me the top 5 disbursements out of accounts *1595, and *9050 in the past week, and remove all ZBA or sweep transactions. |
Transactions | Disbursement summary | Display a list of all wire payments made to "XYZ beneficiary" on a monthly basis. Group the output by Entity Division, then Account Name. |
Transactions | Entity cash flow health check | Show me weekly cash flows by entity and trigger a warning sign for entities that are bleeding cash. |
Transactions | Unusual transactions detection | Identify any transactions in the past 30 days that appear unusual — amounts significantly larger than average, unfamiliar counterparties, etc. |
FAQs
What's the difference between Trovata AI Chat and Agents? Trovata AI Chat is mainly used for interactive, one-time questions or resource creation (i.e. tag building) where you ask and get answers in real time. Agents automate those same kinds of questions on a schedule. Think of Chat as asking a question and Agents as assigning a recurring task.
Can I have multiple agents running at the same time? Yes. You can create as many agents as you need, each with its own instructions and schedule. The Activity tab gives you a unified timeline across all of them.
Do agents share context with each other or with Trovata AI Chat? No. Each agent operates as an independent session. Agents do not share context with each other or with your Trovata AI Chat conversations.
Are agents subject to the same security protections as Trovata AI Chat? Yes. Agents run on the same AWS Bedrock AgentCore infrastructure. Your data is never used for model training, never stored beyond execution, and never accessible to Anthropic or anyone outside your Trovata instance.
Who can see my agents? Only you. Agents are private to your user account. No one else in your organization has visibility. If you want to share an agent with a team member, simply share the agent instruction prompt with them.
Do I need to write code or know an API to create an agent? No. You describe what the agent should do in plain English using the chat interface. The AI helps you refine the instructions. No coding, query language, or API knowledge required.
Can I edit an agent after saving it? Yes. Open the agent from the Listing tab, click Edit, and modify the instructions or schedule. Click Save to apply your changes.
What happens if I save without configuring a schedule? The agent is saved as a Draft. It appears in your Listing tab but does not run automatically. You can add a schedule later by editing the agent.
How long does an agent take to run? Most agents complete within seconds to a minute, depending on the complexity of the instructions and the volume of data being retrieved.
What happens if an agent fails? The execution shows an Error status badge in the Activity feed. You can review the error, adjust your instructions if needed, and re-run the agent manually. If errors persist, contact Trovata support.
Can I run an agent manually outside its schedule? Yes. Use the Execute option from the agent's context menu or detail panel to trigger an immediate run at any time.
I can't see Agents in my sidebar. Two things need to be in place: Trovata AI must be enabled for your organization, and your user role needs the Read Agents permission under the Trovata AI section in User & Entitlements. Check with your Trovata administrator. Also, if you're an Admin, see the video above to enable other users for AI in your instance.
My agent's output doesn't match what I expected. Review the instructions on the Configuration tab. Vague or broad instructions produce general results. Add specificity: name accounts, set date ranges, define thresholds, and describe your preferred output format. Use the Preview tab to test changes before saving.
I've used Trovata's AI features before... Is Trovata AI 2.0 included in my subscription? The AI experience you used previously was Trovata AI 1.0. With the launch of Trovata AI 2.0, AI Insights, AI Chat, and AI Agents are now paid premium features. All existing customers can try Trovata AI 2.0 for free during the trial period — no action needed to get started. After the trial ends, reach out to your Customer Success Manager if you want to add AI 2.0 to your plan.
How much does Trovata AI Agents cost? Consult your CSM to see if it's included in your subscription.