Step 3 · Build & Validate

Robo Claw's Pilot, PoC and Validation Method for NGO Tourism and Exchange Operations

Based on the requirements defined in the Refine STEP, this builds Agents, Skills and Tool Policies within a limited scope of 1 region, 1 program, 1 inquiry type, 1 audience segment and 1 system connection, and validates misclassification, misrepresentation in summaries, misrecognition of traveler/participant information, misrecognition of health/allergy information, misrecognition of location information, misrecognition of booking/pricing information, oversight of information relevant to go/no-go decisions on running the program, contamination with personal/health/location information, misdirected sends, misdirected publication, incorrect updates, duplicate execution, duplicate bookings, Prompt Injection, SaaS/API outages, API specification changes, human approval, escalation, stopping, rollback and switching to manual operation before deciding whether to move to production.

Who This Is For

Who This Is For

This is for tourism/exchange program owners, safety managers, accessibility leads and personal data protection leads who defined requirements in the Refine STEP.

What You'll Decide

What You'll Decide in This Step

In the Build & Validate STEP, you build a limited-scope Pilot, run normal-case and abnormal-case testing, and then decide whether to move to production.

Pilot Scope

Pilot Scope Unit

Validating multiple regions and programs at the same time makes permission design and result evaluation more complex. We recommend limiting the first Pilot to the following unit.

1 Region, 1 Program

Even if you operate across multiple regions and programs, limit the first Pilot to 1 region and 1 program.

1 Inquiry Type

Narrow the target inquiry type to one, making risk easier to evaluate.

1 Audience Segment, 1 Language

Limit the target traveler segment and supported language to one each.

1 System Connection

Limit the connected booking/tourism information management system to one.

Industry Challenges

Challenges Commonly Faced in the Pilot

01

Test coverage is incomplete

Only normal cases are checked, and abnormal-case testing for personal/health information contamination and misdirected sends tends to be insufficient.

02

Decision criteria for moving to production are not set in advance

Progress can continue with it left unclear what needs to be satisfied to move to production after the Pilot ends.

03

There is no procedure for switching back to manual operation

When a problem occurs during the Pilot, a procedure for switching to manual operation is sometimes not prepared.

04

The safety manager gets involved too late

Without the safety manager's involvement from the test design stage, rework can occur later.

Method

Implementation Steps

1. Fix the Pilot scope

Fix the scope to 1 region, 1 program and 1 inquiry type.

2. Build the Agent, Skill and Tool Policy

Based on the design defined in the Refine STEP, actually build the Agent, Skill and Tool Policy.

3. Prepare test data

Prepare test booking/inquiry data that does not include production traveler information or health information.

4. Run normal-case testing

Confirm that the initial classification of inquiries, facility information search, and drafting of guidance text are performed correctly.

5. Run abnormal-case testing

Based on the abnormal-case test items below, confirm behavior for misrecognition, misdirected sends, information contamination and failures.

6. Validate human approval, stopping and rollback

Confirm that human approval functions correctly, and that stopping and rollback are possible when a problem occurs.

7. Validate the switch to manual operation

Confirm that the procedure for switching to manual operation functions when the Agent is stopped.

8. Decide whether to move to production

Comparing the test results against the Go/No-Go criteria, the program owner and safety manager decide whether to move to production.

Test Scenarios

Abnormal-Case Test Items

Below are example abnormal-case test items to validate in a Pilot for NGO/NPO tourism and exchange operations. Add and adjust them for your organization's operations and systems.

Test ItemAssumed ScenarioWhat to Confirm
MisclassificationAn inquiry/booking type is classified incorrectlyWhether misclassification is detected and human correction functions
Misrepresentation in summariesAn error occurs in the summarized content of an activity report/surveyWhether a human can check the difference between the content before and after summarizing
Misrecognition of traveler/participant informationBooking details or participant information are read incorrectlyWhether misrecognition is detected and a human can correct it before finalization
Misrecognition of health/allergy informationHealth/allergy information is recognized incorrectlyWhether the design has a human finalize it
Misrecognition of location informationItinerary/location information is recognized incorrectlyWhether it is presented only as a candidate, with a human finalizing it
Misrecognition of booking/pricing informationBooking or pricing details are recognized incorrectlyWhether the design has a human make the finalization decision
Oversight of go/no-go related informationAn important change in weather/transportation/safety information is overlookedWhether it is reliably escalated to the safety manager
Contamination with personal/health/location informationA traveler's personal/health/location information is unintentionally included in outputWhether it can be removed by pre-output filtering and human review
Misdirected sendsContent is sent to the wrong recipient or with the wrong content, to a traveler/local operatorWhether pre-send approval, send logs, and a cancellation procedure for misdirected sends function
Misdirected publicationIncorrect content is published to the web/social mediaWhether pre-publication approval, publication logs, and a cancellation procedure for misdirected publication function
Incorrect updatesBooking/participant information is updated incorrectlyWhether pre-update confirmation and preservation of change history function
Duplicate executionThe same process is executed multiple timesWhether duplication is prevented by an idempotency check
Duplicate bookingsThe same booking is registered more than onceWhether duplication is detected by checking booking history
Prompt InjectionAn instruction hidden in input data causes the Agent to behave unintentionallyWhether the design ignores suspicious instructions and does not proceed to finalization
SaaS/API outagesA connected SaaS/API does not respondWhether it stops safely on error and notifies the responsible person
API specification changesThe specification of a connected SaaS changesWhether the anomaly is detected and automatic execution is halted until revalidation is complete
Human approvalFinalization processing is about to run before approvalWhether the design prevents sending, booking, or publication from being finalized without approval
EscalationOutput occurs that is suspected to affect safety, accessibility or healthWhether it is reliably escalated to the program, safety and accessibility managers
Stopping and rollbackResponse after incorrect output/processing has occurredWhether execution can be stopped and a procedure exists to restore the prior state
Switching to manual operationThe Agent is temporarily unavailableWhether a procedure for switching to manual operation is in place and operations can continue
Production go/no-go criteriaThe go/no-go decision at the end of the PilotWhether the responsible person can decide in line with the Go/No-Go criteria

Data & Systems

Data and Systems Used

Test booking/inquiry data (anonymized/pseudonymized) Test health/accessibility data Pilot environment's booking management environment Tool Policy definitions Logs and audit trail Notification channels (Slack, Teams, etc.)

Human-in-the-loop

Where Human Approval Is Required

  • Content confirmation and approval of candidate check items and draft guidance text
  • Review by the responsible person of candidates involving personal, health or location information
  • Content confirmation before sending to travelers/local operators and before publishing to the web/social media
  • Decisions on stopping and rollback when an anomaly is detected

Measurement

KPI

Abnormal-case test pass rate

The proportion of defined abnormal-case test items that met the pass criteria

Human review rate

The proportion of outputs for which human review was carried out

Number of misdirected sends and duplicate bookings

The number of misdirected sends and duplicate bookings that occurred during the Pilot period

Pitfalls

Common Pitfalls

01

Skipping abnormal-case testing

Moving to production after checking only normal cases risks starting operations without noticing health information contamination or duplicate bookings.

02

Testing with production data

Using production data containing travelers' personal or health information as-is for testing creates an unnecessary risk of information leakage.

03

Deciding Go/No-Go criteria after the fact

Without defining criteria in advance, the decision to move to production becomes ad hoc.

Go / No-Go Criteria

Rollout Considerations

  • Safe-side behavior as expected has been confirmed for all defined abnormal-case test items
  • The human approval and escalation paths have been confirmed to actually function
  • The stopping/rollback procedure and the switch-to-manual-operation procedure have been actually tried and confirmed to function
  • The program owner and safety manager have reviewed the results and agreed to move to production
  • There is a clear prospect that the production monitoring/logging setup will meet the requirements of Deploy & Operate

FAQ

Frequently Asked Questions

How long should the Pilot period be?

It depends on workload and the number of test items, but a rough guide is often several weeks to about 1-2 months. We recommend prioritizing the thoroughness of abnormal-case testing rather than proceeding based on a fixed period.

Is it okay to use production traveler data for testing?

We do not recommend it. Prepare anonymized/pseudonymized test data and avoid testing with data that includes production personal information or health information.

What is checked in the test for go/no-go decisions on running the program?

We confirm that it stops at organizing information and presenting it for escalation, and that the design ensures the final go/no-go decision is always made by the safety manager.

Who decides whether to move to production?

We recommend that the program owner and safety manager decide by comparing the test results against the Go/No-Go criteria. When there are points related to accessibility or health, specialists also take part in the decision.

Would you like to organize your Pilot and PoC design together with us?

You can confirm the scope, test items and Go/No-Go criteria, and discuss your Pilot design on our official LP.

Talk to an Expert About Pilot Design