AnthROS logoAnthROS™

Lawful, on-policy, and provably so.

Every people decision on the right side of the law and your policy

AnthROS checks every people decision against current employment law and your own policy. It flags the risk, cites the rule, and leaves a record. It never invents an answer.

For HR, managers and employees. Deterministic. A defensible record on every decision.

Conversational for HR and staff
Ask in ordinary language: "how much notice for a three-year employee?", "what’s her maternity entitlement?"
Deterministic at the core
The answer is derived from statute and your policy, not predicted, with the rule and the clause cited.
Honest at the edge
Questions of judgment are routed to a person. It does not guess.
RAG is not enough for HR

A RAG chatbot can sound right and still be wrong. In HR, wrong is a liability.

A RAG chatbot

Predicts an answer from retrieved text. It can invent a policy clause, miss the statutory floor, or apply last year’s law.

  • Probabilistic
  • Unverifiable
  • You can't tell when it's wrong

AnthROS

Derives the answer from the codified law and your verified policy, and cites both.

  • Deterministic
  • Cited to the Act and the clause
  • Right by construction
Three roles, one reasoning core

The decision-safety layer for people decisions

One deterministic engine serves managers, employees and HR.

Use case 1 · Managers

The decision-check

Before a dismissal, rating, promotion or hire, AnthROS checks the decision against employment law and your policy, flags the risk, and records the reasoning.

Checks the decision · flags the risk · leaves a record

Use case 2 · Employees

The employee chatbot

Staff ask in plain language. AnthROS answers from the Act and your policy, cites the source, and hands anything needing judgment to HR.

Quick, cited answers · bounded · fewer HR tickets

Use case 3 · HR professionals

Guided Analysis for HR

AnthROS drives the intake, applies statute and policy, checks the floor, flags discretion, and produces a traceable output: a retrenchment plan, a leave determination, a WFA readiness check.

Structured reasoning · statute × policy · a defensible record

Employment contracts

Review and draft employment contracts inside the AI agent you already use

AnthROS connects over MCP to Claude Cowork, ChatGPT Work, Microsoft 365 Copilot Cowork and Google Gemini Spark. The agent drafts; AnthROS verifies every clause against the Employment Act and your policy.

Review an existing contract

Every term (notice, salary, hours, leave, rest days) is checked against the statutory floor. A term less favourable than the Act is flagged as void under s.8, with the section and the statutory minimum stated. Restraint of trade and similar clauses are flagged for a qualified person.

Clause-by-clause · floor-checked · every flag cited

Draft a new one

The agent drafts from your template and policy. AnthROS verifies each clause as it is drafted and keeps a record of the checks.

Drafted in the agent · checked by AnthROS · record kept

The reasoning that others get wrong

Your policy governs above the floor. The law overrides below it.

Most employers sit above the statutory minimum, so the answer usually lives in your policy. But any term less favourable than the Employment Act is void (section 8). AnthROS never quotes a policy term the Act voids, and never applies the statutory minimum where a more generous policy governs.

How AnthROS reads an entitlement
Your HR policy: governs
18 days annual leave · 2 months’ notice · enhanced family leave
Statutory floorEmployment Act · s.8
Below the floor: void
A term less favourable than the Act
Struck out · statute applies instead
From question to cited answer

Six steps, and a person only where judgment is required

01

Ask

Someone asks a question in plain language.

02

Clarify

It asks only the facts that matter: coverage, category, tenure, which policy applies.

03

Reason

It derives the answer from statute and your policy, applying the statutory floor.

04

Answer

It returns the answer with the Act section and the policy clause cited.

05

Flag

If the question turns on discretion, or a fact is missing, it flags or asks. It does not guess.

06

Trace

Every answer shows the rules applied, the policy used, and the floor checked.

One question. Statute and policy.

A reasoned answer a chatbot can’t give safely

“How much annual leave does she get?”

FactsCovered by the Act · in her second year of service
Statutory floorThe Employment Act minimum, which rises with length of service
Company handbook18 days
Reasoning18 sits above the floor → the handbook governs

Answer: 18 days. The handbook governs because it exceeds the statutory floor, cited to the Act and the handbook clause. Had the handbook said 5, AnthROS would flag that term as void under section 8 and apply the statutory minimum.

Every answer lands on one of four outcomes

Answer

The Act and your policy determine it. A cited answer is returned.

Ask

One decisive fact is missing (tenure, category, which policy applies) and can be supplied.

Flag

The question turns on discretion (fairness, discrimination, reasonableness) and goes to a person.

Out of scope

It falls outside the covered law and policy. It says so, plainly.

The law just changed

The general tools don’t know the new law. AnthROS does.

The Workplace Fairness Act, completed in 2025 and in force around end-2027, makes the tripartite guidelines binding: a statutory tort of discrimination, protected characteristics, strict time bars, a grievance-to-adjudication route, and penalties up to S$50,000 (S$250,000 for repeat breaches). A general model gives the pre-Act answer.

The questionGeneral AI, trained on the old regimeAnthROS, the current Act
Can an employee sue us for discrimination?No standalone claim, voluntary mediation onlyYes, a statutory tort of discrimination now exists
By when must a hiring-stage claim be raised?Unspecified / no fixed barWithin the Act’s strict time bar for that dispute type
Does the fairness law apply to us?Guidelines, advisory, non-bindingBinding, by employer-size threshold, phased in
What’s the exposure for a breach?Reputational / tripartite censurePenalties to S$50k, rising to S$250k for repeats
What it answers

The rule-based core of employment law and your policy

Notice periodsAnnual, sick, maternity, paternity & childcare leaveOvertime & salary computationRetrenchment notice & benefitsCoverage & eligibility under the ActWorking hours & rest daysWFA thresholds, time bars & processActual entitlement: statute and policy together
Who it’s for

Everyone who makes a people decision, and everyone who has to defend one

People managers & line leadersHR teamsIn-house counsel & GCCompliance & riskSMEs without in-house legalEmployees (self-service, bounded)
Fits your stack

Your HR systems act. AnthROS supplies the reasoned, cited answer.

HRIS

Workday, BambooHR and other systems of record.

Handbook & policies

Your handbook and policies, verified into rules.

HR service desk

Answers in the channel staff already use.

Statutory sources

MOM, CPF and the governing Acts.

Where to start

Bring your handbook and a few real questions

You bring

  • Your employee handbook / HR policies
  • 10 real HR questions your team gets asked
  • Your employee categories and coverage
  • Your leave and notice policies

You get back

  • A structured policy-rule inventory
  • The statute × policy floor-and-override map
  • Reasoned, cited answers to your sample questions
  • A report of where your policy dips below the statutory floor
The foundation

Proven engine. Traceable answers. Named science.

Runs on the Reasonex™ engine

The same deterministic reasoning core proven on Singapore civil procedure in MikeROS™, applied to employment law and HR policy.

An SUTD ARISE startup

Our Chief Scientific Officer, Prof. Ernest Chong, is on SUTD’s faculty and the originator of algebraic machine reasoning.

Questions buyers ask

See it answer your own HR questions

Bring your handbook and a few real questions. We’ll show the reasoning and the citations behind every answer.