Skip to content
SME AI Impact
Innovation ExcellenceTalent & Recruitment· Knowledge retrieval

Glints Singapore

Glints cut internal fact-finding time by 90% with an agent that reads its own systems and source code.

Principal published result

90% reduction

Time spent fact-finding

Evidence grade

BCanonical source supported

Grade B — Canonical source supported

Research coverage

100% coverage

Ten evidence dimensions, not an AI maturity score

Sources

4

4 sources · 3 beyond T0

Open glints.com ↗Live site, not an official page of this showcase.

Share on LinkedIn

01The official record

Award citation, verbatim in substance
Homepage of Glints Singapore, captured 2026-10-18
Glints Singapore's homepage, captured 2026-10-18. Shown for identification and comment; it may differ from the award-winning implementation.Open live site ↗

Provides talent and managed workforce services across Singapore, Malaysia, Indonesia, Vietnam, the Philippines and Taiwan.

Published key challenges

  • Fragmented company knowledge. Critical information was spread across databases, business systems and employment laws in six different markets
  • Slow responses to queries. Routine questions often required help from Finance, Engineering or other specialists, with complex queries taking hours or days
  • Operational and compliance risks. Repeated queries distracted specialists from their work, while inconsistent answers created regulatory risks across different markets

Glimmer: Knowledge Mining AI Agent

  • Unified AI knowledge assistant: Answers questions in plain language using company data and internal knowledge, with supporting sources shown
  • Real-time enterprise data retrieval: Retrieves up-to-date client, employee, invoice and billing information from systems such as NetSuite and HubSpot
  • AI-enabled technical support: Reads the company's source code to answer platform questions and provide first-line support before unresolved issues are escalated
  • Built-in accuracy and governance: System automatically flags missing information, restricts citations to accessed sources and maintains audit logs

02SCQA case study

357 words
SSituation

Glints provides talent and managed workforce services across Singapore, Malaysia, Indonesia, Vietnam, the Philippines and Taiwan. Its staff answer questions that cross borders: what a client was billed, which employee is assigned where, and what a given market's employment law requires. Each answer depends on a different system and a different jurisdiction.

CComplication

Critical information sat across databases, business systems and the employment law of six markets. Routine questions needed help from Finance, Engineering or other specialists, and complex queries took hours or days. Repeated queries pulled specialists away from their own work. Worse, answers could differ between people and between markets, which created regulatory risk in an industry where an incorrect statement about pay or entitlement has consequences. The cost was not only time. It was the risk that two staff members would answer the same question differently in two markets.

QQuestion

How could staff get fast, consistent answers from company systems and six legal jurisdictions without queueing behind a specialist for every question?

AAnswer

Glints built Glimmer, a knowledge mining agent. Employees ask questions in plain language and the agent retrieves answers from company systems, internal knowledge, source code and employment law, showing the supporting sources. It pulls live client, employee, invoice and billing data from systems including NetSuite and HubSpot. It reads the company's source code to answer platform questions and provide first-line technical support before escalation. Governance is built into the retrieval: the system flags missing information, restricts citations to sources it actually accessed, and keeps audit logs. The citation reports a 90% reduction in fact-finding time, 1,700 specialist hours saved in six months, and S$120,000 of staff time saved each year. The design choice that matters is the citation constraint. An answer that must cite its source is auditable; an answer generated from general knowledge is not. The citation does not report how the agent handles a question that spans two jurisdictions, which is the hardest case in a six-market operation. The value of the agent compounds with market coverage, because every additional jurisdiction adds employment law that must be retrieved correctly rather than recalled from memory, and a wrong answer carries a regulatory cost.

Implementation takeaway

Constrain the agent to sources it actually read, and log the retrieval. In a regulated service, an uncited answer is a liability, not a feature.

03Verified business results

Company-reported
Published business outcomes for Glints Singapore, as reported in the award citation.
MetricPublished resultAttribution
Time spent fact-finding90% reductionCompany-reported; published in the IMDA/SBF award citation
Specialist hours1,700 saved in six monthsCompany-reported; published in the IMDA/SBF award citation
Staff time valueS$120,000 saved per yearCompany-reported; published in the IMDA/SBF award citation

The award citation publishes relative changes and absolute volumes, not paired before-and-after values. Baseline figures are therefore not shown, and no improvement percentage has been calculated from them.

04Technology stack

Evidence status per layer
Technology stack for Glints Singapore, with evidence status for each layer.
LayerImplementationVendor / in-houseEvidenceSource
AI modelLanguage model for question answering and code comprehensionNot disclosedunknownStatedT0-AWARDS
RetrievalRetrieval over internal knowledge, business systems and source codeIn-house, unnamedin-houseStatedT0-AWARDS
IntegrationNetSuite and HubSpot for client, employee, invoice and billing dataNetSuite, HubSpotvendorStatedT0-AWARDS
OrchestrationFirst-line technical support with escalation pathIn-house, unnamedin-houseStatedT0-AWARDS
GovernanceCitation restriction, missing-information flags and audit logsIn-house, unnamedin-houseStatedT0-AWARDS

A layer marked inferred includes a documented basis. Layers without a named vendor are left unnamed rather than filled with a plausible product.

05Implementation diagrams

Documented vs illustrative
Documented implementationEvidence-bounded
EmployeequestionGlimmer agentNetSuite andHubSpotInternalknowledge andcodeEmploymentlaw sourcesCitation andauditcontrolsCited answerto employeeINPUTPROCESSAISYSTEMOUTPUT

Components named in the award citation.

Illustrative reference architectureIllustrative only
Staffquestion inchatRouter: HR,finance,technical…Vector indexover policydocumentsERP and CRMread APIsGroundedanswergenerationCitationcheck andrefusalAnswer withsourcesINPUTPROCESSAISYSTEMOUTPUT

A feasible build for another multi-market service firm. This is not Glints' production system.

06Unconfirmed — technical inference

Not attempted

No public technical details were identified beyond the official award description. This case is not supported well enough to justify a technical inference, so none is offered.

07How another SME could build something similar

Advisory, not the winner's method

This section is guidance for other companies. It is not a description of what Glints Singapore did, and it is not endorsed by them.

Suitable for

  • · Recruitment and staffing firms
  • · Professional services
  • · Multi-country operations teams
  • · Internal IT and HR helpdesks

Minimum requirements

  • · Read access to the systems that hold the answers
  • · A curated policy and law corpus with effective dates
  • · Agreement on what the agent must refuse to answer

Three implementation paths

Level 1

Document assistant

Index policy documents and answer with citations in a chat interface.

Use when: Most questions are policy questions with a written answer.

Level 2

Systems-connected agent

Add read-only API lookups so the agent can answer questions about specific records.

Use when: Answers depend on live business data.

Level 3

Governed multi-source agent

Add permission-aware retrieval, audit logs, refusal handling and technical code search.

Use when: Multiple sensitive systems and regulatory exposure.

Suggested sequence

  1. 1Log one month of real questions and where the answers live
  2. 2Start with one domain, usually HR policy
  3. 3Require citations and measure answer accuracy against a human baseline
  4. 4Add system lookups only after the document corpus works
  5. 5Publish a refusal policy and an escalation path

Tools and alternatives

  • · Vector database
  • · Language model with grounded prompting
  • · ERP and CRM APIs
  • · Audit logging

Risks and PDPA considerations

  • · Confident answers from stale policy versions
  • · Leakage of salary or client data across permission boundaries
  • · Staff trusting the agent over the written policy

KPIs to track

  • Answer accuracy against expert review
  • Time to answer
  • Escalation rate
  • Citation coverage
  • Repeat-question rate

08Research gaps

What remains unknown
  • The underlying LLM family powering Glimmer is not disclosed, though NetSuite and HubSpot integrations are confirmed.
  • Cross-border conflict resolution between differing jurisdictions is not documented.
  • Precision and recall metrics for legal clause retrieval are not published.

Are you this company? Submit documentation to upgrade your evidence grade.

If you have published technical documentation, vendor whitepapers, or third-party audits, submit documentation to our research desk. We update evidence grades upon verification.

09Sources

4 records
  1. Infocomm Media Development Authority (IMDA) and Singapore Business Federation (SBF) · 16 October 2026 · Retrieved 18 October 2026 · T0 — Canonical awards source

    Canonical source. Page last updated 16 October 2026. Publishes one profile per winner: company description, three key challenges, named AI solution, solution components and three headline metrics. No individual winner URLs are published.

  2. Glints Singapore Pte Ltd · Retrieved 19 October 2026 · T1 — Direct primary source

    Recruitment platform website detailing talent marketplace, employer recruitment solutions, and AI-enabled talent discovery.

  3. Infocomm Media Development Authority (IMDA) · 13 October 2026 · Retrieved 19 October 2026 · T1 — Direct primary source

    Official government media release for SMEs Go Digital Day 2026 and inaugural SME AI Impact Awards at Suntec Singapore Convention & Exhibition Centre. Minister Josephine Teo presented awards to 30 SMEs.

  4. PR Newswire APAC (IMDA media release) · 21 May 2026 · Retrieved 18 October 2026 · T1 — Direct primary source

    Announces the inaugural awards, the two categories, the 30-winner ceiling, the Trustmark, and the 13 October 2026 announcement date.

Researched 18 October 2026 · Updated 18 October 2026 · Award citation retrieved 18 October 2026.

Glints Singapore is a winner of the SME AI Impact Awards 2026, organised by IMDA and SBF. This case study is independent analysis and is not an official company publication.

Related case studies

Similar technology and sector implementations

Homepage of Best Marketing Agency, captured 2026-10-18
Innovation ExcellenceMedia & Creative
Winner · Award Cohort 2026

Best Marketing Agency

Best Marketing Agency rebuilt its agency operating model around AI agents, and revenue per employee rose 71%.

Revenue per employee
71% increase
Workflow automationBCanonical source supported
Homepage of Kyanon Digital, captured 2026-10-18
Innovation ExcellenceICT/Consultancy
Winner · Award Cohort 2026

Kyanon Digital

Kyanon Digital productised its AI delivery stack, cutting new engagement setup time by 83%.

Setup time for new AI engagements
83% reduction
Platform engineeringBCanonical source supported
Homepage of Kopi Near Me, captured 2026-10-18
Adoption ExcellenceFood & Beverage
Winner · Award Cohort 2026

Kopi Near Me

Kopi Near Me runs automated coffee machines on one AI operating system, cutting enquiry processing by 70%.

Sales conversion
Up to 15% increase
Operations schedulingBCanonical source supported