Skip to main content
Apragya AIFree quotation builderQuotation builderQuote builderno signup
AI agents

Run AI Agents on Your Own Data: Records, Documents and Systems, Without Copying Them Around

For operations and IT heads who want AI that knows their customers, stock and policies, without staff pasting data into a chat tool.

A credit head and a small robot opening a ledger in a warehouse office

To run AI agents on your own data, the agent must be able to reach that data safely: the order it is checking, the policy it must follow, the system that holds the stock. A general model knows none of these.

The common workaround is copy and paste. Staff paste customer details into a chat tool, get an answer, and paste it back. Data leaks out, and nothing is recorded.

This page covers what that costs, an illustrative example, and the three ways Apragya agents reach your data.

An example: a Nagpur agri-inputs distributor

Take an illustrative distributor of seeds and fertiliser selling to dealers on credit. The credit team wanted an agent to suggest a credit limit for each new dealer order, using the dealer's history and the company's credit policy.

What the agent used for one dealer

  • Dealer recordOrders, payments and overdue invoices.Checked
  • Credit policySearched from the policy document.Checked
  • Season calendarKharif demand, from a reference sheet.Checked
  • Overdue invoicesTwo past the agreed period.Overdue
  • Suggested limitLower than asked, with the reason.Ready
  • Credit head reviewApproves or changes the limit.Pending
Every input came from the company's own records and documents.

The credit head approved most suggestions as they were and changed a few. Each dealer record now shows the suggested limit, the reasons, and who approved it, and no dealer data went into a chat tool.

A dealer file beside a small balance and an approval stamp
A suggested limit, weighed against the dealer's history, waiting for the credit head's stamp.

How AI agents on company data work

Step 1 of 5

Bound to records

An agent runs on a record event and reads that record and its links.

  1. Bound to records: An agent runs on a record event and reads that record and its links.
  2. Knowledge: Upload policies, price lists and manuals; the agent searches them.
  3. Connectors: Reach databases, SharePoint, S3, FTP or SAP through connectors.
  4. Tenant Runner: Reach systems inside your network over an outbound connection.
  5. Output and review: Results are saved on the record, with human review where set.

Before and after agents on your own data

Agents on your data

  • The agent reads the record it is bound to
  • Output is saved on the record
  • Each run is logged
  • Policy documents are searched as knowledge

Private data AI agents: what to check

An agent is only as safe as its access. It should read only what the task needs, run under role controls, have personal data checks on its output, and log every run. Model calls can use your own provider keys.

Chat tools against Apragya agents

FeatureGeneral chat toolApragya agents
Data sourcePasted by staffRecords, knowledge and connectors
OutputPasted backSaved on the record
Personal dataUncheckedGuardrails and PII masking
Record of useNoneEach run logged
Model accountThe tool'sYours, where you add keys

Checked against public information on 16 September 2026.

What sets Apragya apart when you connect AI to ERP data

Already on your records

Sales, stock, finance and HR records are in the same platform.

Built without code

Describe the agent and bind it to a record.

Guardrails

Checks on input and output, with block, warn or log.

Your keys

Model calls can use your organisation's provider keys.

Metered

Every run is counted in AI Credits.

Inspectable

Runs keep their steps and output.

See agents for credit limit recommendation and collections prioritisation, or bring your own LLM key.

Getting started

  1. Pick one decision that uses records you already keep.
  2. Collect the policy documents that decision follows.
  3. Build the agent and add those documents as knowledge.
  4. Bind it to the record event and keep review on.
  5. Check the first fifty suggestions against what people decided.

The policy documents usually need a tidy-up first; agents follow what is written, not what is meant.

What it costs to start

INR 7,999
Pro, a month
Up to 25 users, with the no-code agent builder and every enterprise app
5,000
AI Credits a month
Included on Pro
Free
Up to 3 users
CRM and HR, to try the platform first

AI agents on your own data questions

Does our data train the model?
Agents send the data a task needs to the model you use. Check your provider's terms; your own keys keep that relationship yours.
Can agents reach our on-premise systems?
Yes, through connectors, and through the Tenant Runner for systems inside your network.
Can agents change records?
Output is saved on the record, and human review can be required before anything goes ahead.
Which systems have connectors?
Examples include PostgreSQL, SharePoint, S3, FTP, SAP OData and SAP RFC. A custom adapter covers others with an API.
What does it cost to start?
The no-code agent builder comes with the Pro plan, INR 7,999 a month for up to 25 users, which includes every enterprise app, 5,000 AI Credits a month, single sign-on and audit logs. The free plan covers up to 3 users with CRM, HR and Vendor Onboarding if you want to try the platform first.

Let one agent read your own records

Pick one decision, add its policy, and keep review on for the first month.