# Starter Kit for Testing LLM-Based Applications for Safety and Reliability (v1.0)

- **Record type**: Policy instrument
- **Jurisdiction**: Singapore
- **Instrument type**: Guidance
- **Status**: Guidance
- **Binding**: No — guidance, strategy or standard
- **Issuing body**: Infocomm Media Development Authority (IMDA)

## In brief

The Singapore starter kit for testing LLM applications is a non-binding guidance of Singapore, issued by the Infocomm Media Development Authority (IMDA). Its current status is guidance. Organisations building or deploying LLM-based applications; voluntary. Voluntary guidelines for testing applications built on large language models against five risks: hallucination and inaccuracy, bias in decision-making, undesirable content, data leakage and adversarial prompts.

## Summary

Voluntary guidelines for testing applications built on large language models against five risks: hallucination and inaccuracy, bias in decision-making, undesirable content, data leakage and adversarial prompts. Baseline tests are available on Project Moonshot.

## Scope

Organisations building or deploying LLM-based applications; voluntary.

## Who it applies to

Developers, deployers and testers of LLM-based applications.

## Key dates

Draft consulted on in 2025 (closed 25 June 2025); version 1.0 published January 2026.

## Notes on dates

The exact day of publication of version 1.0 and the start of the 2025 consultation were not confirmed.

## Provenance

- **Permanent id**: AIPT-POL-0242 (https://aipolicytracker.org/id/AIPT-POL-0242; never changes or gets reused)
- **Record page**: https://aipolicytracker.org/policies/singapore-starter-kit-testing-llm-based-applications
- **Official source**: https://www.imda.gov.sg/-/media/imda/files/about/emerging-tech-and-research/artificial-intelligence/starter-kit-for-testing-llm-based-applications-for-safety-and-reliability.pdf
- **Source document**: Starter Kit for Testing LLM-Based Applications for Safety and Reliability
- **Published by**: Infocomm Media Development Authority
- **Review status**: pending review
- **Confidence**: medium
- **Facts last confirmed**: never confirmed against the official source
- **Retrieved**: 2026-10-21
- **Licence**: https://creativecommons.org/licenses/by/4.0/
- **Cite as**: AIPolicyTracker (2026). "Starter Kit for Testing LLM-Based Applications for Safety and Reliability (v1.0)" [AIPT-POL-0242, record version 1, not yet verified]. https://aipolicytracker.org/id/AIPT-POL-0242 (accessed 21 October 2026).

> This record is a structured summary with a link to the official text. It is not legal advice. Open the official source before relying on any date or duty. How current each record type must be is published at https://aipolicytracker.org/verification; what a record must carry at all is published at https://aipolicytracker.org/coverage.