Singapore starter kit for testing LLM applications: requirements, deadlines and compliance actions
Starter Kit for Testing LLM-Based Applications for Safety and Reliability (v1.0)
What this label means
- Verified
- — a named reviewer opened the official source and confirmed the record; the date and the reviewer are shown.
- Pending review
- — linked to the official source and in the queue for a reviewer to confirm.
- Source-linked
- — linked to the official source, not yet confirmed by a reviewer.
On this page 7 sections
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.
- Jurisdiction
- Singapore
- Instrument type
- Guidance
- Status
- Guidance
- Legal force
- Non-binding (guidance, strategy or standard)
- Issuing body
- Infocomm Media Development Authority (IMDA)
- Verification
- Pending review · source-linked, checked 15 Oct 2026
What is the Singapore starter kit for testing LLM applications?
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.
Status note: Recorded on 15 October 2026 from search-engine extracts of the official pages listed; the official text could not be opened from the research environment, so every date and duty here is pending review against it.
Who does it apply to?
Organisations building or deploying LLM-based applications; voluntary.
Developers, deployers and testers of LLM-based applications.
- Sectors
- Cross-sector / all sectors
- AI use cases
- Generative AI and foundation models
- Risk categories
- Not classified by the instrument
- AI system types
- Generative AI systemChatbot / conversational agent
When do the requirements apply?
Draft consulted on in 2025 (closed 25 June 2025); version 1.0 published January 2026.
The exact day of publication of version 1.0 and the start of the 2025 consultation were not confirmed.
Official sources
-
Starter Kit for Testing LLM-Based Applications for Safety and Reliability
Infocomm Media Development Authority · Tier 1 source
Cite this record
AIPolicyTracker (2026). “Singapore starter kit for testing LLM applications” [AIPT-POL-0242, record version 1, not yet verified]. https://aipolicytracker.org/id/AIPT-POL-0242 (accessed 21 October 2026). Data licensed CC BY 4.0.
Permanent id AIPT-POL-0242: it never changes or gets reused, and its address keeps working if this page moves.
Cite the official text alongside it: Starter Kit for Testing LLM-Based Applications for Safety and Reliability, Infocomm Media Development Authority, 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.
BibTeX
@misc{aipolicytracker2026_singaporestarterkitforte,
author = {{AIPolicyTracker}},
title = {{Singapore starter kit for testing LLM applications}},
year = {2026},
howpublished = {\url{https://aipolicytracker.org/policies/singapore-starter-kit-testing-llm-based-applications}},
url = {https://aipolicytracker.org/policies/singapore-starter-kit-testing-llm-based-applications},
urldate = {2026-10-21},
note = {Data licensed CC BY 4.0. Accessed 21 October 2026}
}
Using this in a product? Commercial use is allowed under CC BY 4.0, with attribution. Ask about an SLA-backed feed or a white-label licence.
Change history
Record history
No change to this record's tracked fields has been recorded since 15 October 2026, when field-level history began.
Record version 1: Added in the October 2026 sub-national research round. Recorded on 15 October 2026 from search-engine extracts of the official pages listed; the official text could not be opened from the research environment, so every date and duty here is pending review against it. Every earlier wording is in the GitHub repository.
Frequently asked questions
Is the Singapore starter kit for testing LLM applications in force?
The Singapore starter kit for testing LLM applications has the status "guidance"; it is not a binding law in force.
Is the Singapore starter kit for testing LLM applications legally binding?
No. The Singapore starter kit for testing LLM applications is a guidance; it sets expectations rather than legal requirements, unless another instrument gives it force.
Who does the Singapore starter kit for testing LLM applications apply to?
Organisations building or deploying LLM-based applications; voluntary.
When does the Singapore starter kit for testing LLM applications apply?
Draft consulted on in 2025 (closed 25 June 2025); version 1.0 published January 2026.
Where is the official text of the Singapore starter kit for testing LLM applications?
The official text is published by Infocomm Media Development Authority at 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 (Starter Kit for Testing LLM-Based Applications for Safety and Reliability). This record links to it and is checked against it.
Disclaimer: informational only, not legal advice. Verify every claim against the linked official sources and consult a qualified lawyer before acting.