Back
Control example

Boundaries in the workflow

An operating boundary determines what may reach the AI model and on what terms. We show one recorded run: the user asks for a reply to a complaint, and before sending, AiTrust shows which data will be replaced with tags and which version the model will receive.

The points of the flow this example concernsSee the whole flow
  1. Intent
  2. Input control (applies)
  3. Authorization (applies)
  4. AI
  5. Result validation
  6. Human
  7. Evidence

Highlighted: the points of the flow that this description refers to. Orange marker: a human decision at this point.

Explanation

What a boundary in the workflow means

Queries in configured paths go through AiTrust. The model receives the context after sanitization of designated data categories. The organization decides which categories are designated and what happens to them.

Check before sending
A check of the query content before it reaches the AI model. The user sees the result of the check and the version that will be sent.
Sanitization
Replacing detected data with tags, e.g. an e-mail address with the [EMAIL] tag. It limits data exposure, but on its own it is not irreversible anonymization.
Zone
A risk class marked with a letter and assigned according to the organization’s rules. The rest of the workflow depends on the zone, as described in more detail in the Operation risk assessment example.
Configured path
The route of a query from the user to the model, set up in AiTrust, e.g. a conversation with a selected AI digital worker. Data sent from private accounts, browsers or other applications requires controls on the organization’s devices and network.
Control flow

The full flow from input to record

A technical version of the diagram from the home page: the same stages with the mechanisms expanded, without rules or configuration parameters.

An explanatory diagram, not a live feed from a production system.

  1. 01 · IntentInstruction and context
    Stage 1 of 7 · Intent

    Instruction and context

    The user's message enters the run together with the context of the project, the task and the related documents.

    • Task and project context
    • This user's conversation history
    • Project documents
    • AI digital worker assigned to the project
  2. 02 · Input controlAccess, document status and content
    Stage 2 of 7 · Input control

    Access, document status and content

    The system checks permissions to the conversation, documents and models, whether a document is ready for use, and the content of the instruction.

    • Permissions and access level
    • Quarantine and document status
    • Cleaned version of the document
    • Protection against prompt injection
    • Data sanitization
    Before controlPrepare a reply to a customer complaint. Contact details from the report: e-mail jan.kowalski@example.invalid, phone +48 600 000 000.
    Version sent to AIPrepare a reply to a customer complaint. Contact details from the report: e-mail [EMAIL], phone [PHONE].

    An example on synthetic data. Detected identifiers are replaced with tags; the scope of detection depends on the configuration.

  3. 03 · AuthorizationZone and decision
    Stage 3 of 7 · Authorization

    Zone and decision

    The H.A.D.A. zone and the organization's policy determine the next step. It can be execution, limiting the content, a request for approval or a stop. In the panel before sending, the user decides whether to send a restricted version. Operations of designated classes wait before execution for the decision of an authorized person, who does not approve their own request. The approval covers the operation before it is executed.

    • H.A.D.A. zone (A to D)
    • Organization policy
    • Access to models by role
    • Tool permissions
    • Control panel before sending
    • Approval requests
    Execute (scope permitted for the task)
    Approve operation (consent of an authorized person before execution)
    Stop (the operation is not executed)

    The H.A.D.A. zone and the organization's policy determine the next step. The policy can also limit the content by sending a masked version.

  4. 04 · AIExecution within the permitted scope
    Stage 4 of 7 · AI

    Execution within the permitted scope

    The model and tools work within the scope permitted for the role, the project and the zone; tool use leaves a confirmation.

    • Local model
    • Approved external model
    • Project tools
    • Tool execution confirmation
    Local model
    Approved external model

    The model receives the context after the specified data categories have been sanitized. The choice of model follows from the configuration.

  5. 05 · Result validationResponse check
    Stage 5 of 7 · Result validation

    Response check

    The response is checked before display, and restricted content is not disclosed to people without the required access.

    • Response check
    • Content restriction by access level
    • Verification against sources, if enabled
    • Check of content returned by tools
    • Response check before display
    • Verification against sources, if enabled

    Limit of the assessment: The assessment does not determine whether the result is correct in substance; a person assesses it.

  6. 06 · HumanAcceptance of the result
    Stage 6 of 7 · Human

    Acceptance of the result

    After result validation, a person accepts the result or sends it back for correction. The acceptance covers the prepared result, while consent to the operation is given earlier, at authorization.

    • Accept result
    • Send back for correction
    • Accept result
    • Send back for correction

    Decisions in the run diagram. The acceptance covers the prepared result after its validation, before it is used further in the process. Consent to the operation itself is given earlier, at authorization.

  7. 07 · EvidenceA record of successive stages
    Stage 7 of 7 · Evidence

    A record of successive stages

    Successive stages leave a record, and the send report with the zone, decision and redactions is shown with the response.

    • Event record at successive stages
    • Send report with the response
    • Log view with filters and export

The scope and order of the mechanisms depend on the specific deployment and process; some controls apply conditionally, according to the configuration.

Diagram

Conditions, transitions and decisions

Diagram of the controlled run

  1. Step 1: InstructionThe user types a task in a conversation held in a configured path.
  2. Step 2: CheckBefore sending, the content is checked for the data categories designated by the organization.
  3. Step 3: Policy decisionIf designated data is detected, the policy determines the next step. In this example: restricting the content (Redact).
  4. Step 4: User’s choiceThe user sees the version to be sent and can cancel, edit the instruction, check again or send the restricted version.
  5. Step 5: Sending and reportThe model receives the sanitized version. The send report is shown with the response.
Illustrative diagram: conditions and decisions in the controlled path, not a view of a running system. The order of steps and the rules are set by the deployment configuration.
Recorded run

One example in three screenshots

The three screenshots come from one recorded run in AiTrust. The data is synthetic: the user, the complaint and the contact details were made up for this example.

Step 1 of 3

Instruction in a conversation with the AI digital worker

The user writes to the AI digital worker, which operates in the AiTrust application as the “PM Orchestrator” agent. The user asks for a reply to a customer complaint and includes the complainant’s contact details in the instruction. The model is set to “Auto (by policy)”, which means it is selected according to the organization’s rules.

The caption at the top, with the word “INTENT” and the description “the user requests an action”, was added to the recording and is not part of the interface.

Step 1: the instruction typed in a conversation with the AI digital worker, which operates in the application as the “PM Orchestrator” agent (synthetic data).

Step 1: the instruction typed in a conversation with the AI digital worker, which operates in the application as the “PM Orchestrator” agent (synthetic data).

A conversation with an AI digital worker, which operates in the AiTrust application as the “PM Orchestrator” agent, with the model set to “Auto (by policy)”. The user types an instruction to prepare a reply to a customer complaint. At the top, a recording caption with the word “INTENT” and the description “the user requests an action”.
Step 2 of 3

Check before sending

The check panel assigns zone D to the query and shows the version that will be sent to AI: the e-mail address, phone number and account number were replaced with the [EMAIL], [PHONE] and [IBAN] tags. In total there are 3 redactions, that is, masked fragments of the content. The policy decision is Redact, which means restricting the content.

The user decides whether to send: they can cancel, edit the instruction, check it again or send the restricted version.

Step 2: the check before sending with zone D, 3 redactions and the Redact decision (synthetic data).

Step 2: the check before sending with zone D, 3 redactions and the Redact decision (synthetic data).

The “Security check before sending” panel with zone D: the version sent to AI with the [EMAIL], [PHONE] and [IBAN] tags, 3 redactions, the Redact decision and the Cancel, Edit prompt, Check again and Send restricted version buttons.
Step 3 of 3

Result and send report

After the restricted version was sent, the model prepared a draft reply. The tags from the version sent to the model appear in place of the contact details. The “AI send report” bar summarizes the check: zone D, redact, 3 redactions.

The “Message sent” notice refers to sending the query to the model, not the reply to the customer. The draft requires review and completion by a human.

Step 3: the draft reply with tags and the send report with zone D, the redact decision and 3 redactions (synthetic data).

Step 3: the draft reply with tags and the send report with zone D, the redact decision and 3 redactions (synthetic data).

Draft reply to the complaint with the [EMAIL], [PHONE] and [IBAN] tags in place of the contact details, and the “AI send report” bar with zone D, the redact decision and 3 redactions.

What the screenshots show

  • The AiTrust interface in this one example and this configuration.
  • The version of the query prepared for sending, the choices available to the user and the report attached to the response.

What the screenshots do not prove

  • The effectiveness of data detection in other queries or other data categories.
  • Stopping a send in other scenarios.
  • How the server-side mechanisms work (the screenshots show the interface).
  • Later approvals, sending the reply to the customer or preparing offers.

See the check before sending in a demo

We will show the workflow on synthetic data and discuss which data categories and decisions are worth setting for your processes.

Request an AiTrust demo

Leave your contact details. We’ll agree on the scope of the demo and show how AiTrust can support your organization’s processes.

The controller of the data provided in this form is Polski Instytut AI Sp. z o.o. We will use the data to answer your request and arrange the demo. More information, including your rights, is in the documents GDPR information notice and Privacy policy.

* required field

Want to add your company, phone or a description of the task? Open the full form