DueCare is open-source software that helps platforms, NGOs, regulators, researchers, developers, and worker-support deployments spot recruitment fraud, illegal fees, passport retention, and contract substitution before they harm workers. It combines Gemma 4, harnesses, knowledge packs, graph extraction, anonymization gates, evaluation, and a public hub that receives only sanitized proposals and anonymized signals.
DueCare ships six audience-facing lanes — content moderation, case analysis, worker support, research, anonymized knowledge sharing, and custom API implementations — all sharing the same Gemma 4-centered safety stack.
Trust & safety teams, recruitment marketplaces, and high-volume UGC review queues.
Detect illegal fees, contract substitution, passport retention, deceptive ads, and other exploitative UGC patterns. The system flags and explains; your existing review pipeline acts.
→ read moreCaseworkers, labor regulators, embassies.
Run on the caseworker's own device. Surface the relevant laws and advisories, draft replies and complaint forms, and flag patterns across cases, without case data leaving local machines.
→ read moreMigrant workers, community channels, partner-hosted endpoints.
Answer questions about fees, contracts, passports, and rights in the worker's own language. The system never files complaints or instructs action; it points to verified resources and trusted caseworkers.
→ read moreAcademic researchers, policy analysts, journalists.
Study corridor risk, exploitation trends, and policy impact using version-pinned packs and an anonymized signal stream. Run the evaluation and research harnesses on Gemma 4; cite a hash; re-run months later.
→ read moreReviewed, redacted facts become reusable knowledge objects after local sanitization and human approval. Partners can improve corridor packs without exposing workers, private documents, names, contact details, or case narratives.
A containerized runtime with a small, well-defined API. Wire it into a Messenger or WhatsApp bot, a moderator console, an internal case-management system, or a sibling app. You own the channel; we provide the harness ecosystem, the rule packs, and the model layer.
Reference scenarios for Platform safety, NGO & regulator, Individual worker, Researcher, Anonymized knowledge sharing, and Developer / integration partner lanes, with the deployment architecture for each one in a single place.
Platform safety teams and recruitment marketplaces face a constant stream of posts, ads, listings, and messages, some of which target migrant workers with illegal fees, deceptive offers, or unsafe employers. The DueCare runtime classifies and explains UGC against curated corridor packs, returning a risk score and a suggested action your existing enforcement pipeline can act on.
Illegal recruitment fees, contract substitution, passport retention requests, deceptive job ads, sham agencies, and other exploitative UGC patterns.
A per-item risk score with a suggested action: hold, redline, escalate to human review, or notify the relevant authority.
Inside the platform's own VPC, on a self-hosted GPU. No user content leaves the platform environment.
It does not auto-enforce. The platform's existing trust & safety pipeline decides what action to take.
Caseworkers and labor regulators handle complex situations under time pressure. Running on the caseworker's own device, DueCare surfaces relevant laws and advisories, drafts replies and complaint forms, and flags patterns across recent cases.
Pulls the right corridor pack sections automatically; suggests follow-up questions; pre-fills complaint or referral forms with citations.
Flags patterns across recent local cases (e.g. a recurring fee scheme) without those cases ever leaving the device.
On the caseworker's laptop or workstation. No case data leaves local machines.
It does not file complaints, contact employers, or take any external action on the worker's behalf.
Migrant workers need answers now, on the device or channel they already use, in the language they actually speak. The worker/mobile lane uses cached corridor packs, local or partner-controlled inference, and a no-raw-upload boundary to the public hub. It points the worker to verified resources rather than acting on their behalf.
Through a partner-operated channel: an NGO chatbot, a government information line, or a sibling worker app.
Questions about typical fees, legal contract terms, passport retention rules, and where to seek verified help in this corridor.
On a worker-controlled device when an on-device build is available, or through a partner-hosted endpoint where the partner controls the channel and audit trail.
It will not file complaints, instruct action, or replace a verified caseworker. Drafted answers always point to verified humans.
Academic researchers, policy analysts, and journalists study migration corridors, exploitation trends, recruitment-market dynamics, and policy impact. DueCare gives them version-pinned packs, an anonymized signal stream, and a reproducible harness on Gemma 4 so claims about how a corridor is moving, or how a policy change landed, can be cited and re-run months later.
Corridor risk analysis, longitudinal trend tracking (fees, contract substitution, recruiter networks), policy-impact studies, and reproducible model evaluations.
Pack version (cryptographic hash), eval prompts, rubric, model artifact, runtime configuration. plus the anonymized signal aggregates queried at a point in time.
Locally on Gemma 4 or in a cloud notebook. Researchers control their own environment; the harness reads only public packs and aggregate signals.
It exposes no individual workers, employers, or cases. Aggregates are k-anonymized; raw case data never leaves local deployments.
The sharing lane turns reviewed, redacted evidence into reusable knowledge objects. Case files stay inside the local workbench; only sanitized, consent-aware facts with provenance and reviewer approval can reach the public hub.
Confirmed facts from reviewed evidence graphs: corridor, indicator, rule, source row, outcome, and pack version.
Names, phone numbers, IDs, document images, private narratives, employer-identifying details, and other sensitive PII.
Sanitization runs in the local or trusted deployment before any submission. The hub runs a second defensive PII scan before storage.
Future packs, GREP rules, worker guidance, platform moderation, and research queries improve from verified patterns without centralizing raw cases.
The runtime is a containerized service with a small, well-defined API. Wire it into a Messenger or WhatsApp bot, a moderator console, an internal case-management system, or a sibling app. You own the channel; we provide the harness ecosystem, the rule packs, and the model layer.
FB Messenger, WhatsApp Business, Telegram, custom web chat, voice IVR. Adapter handles channel-specific transport; the runtime stays the same.
Custom moderator dashboards, in-house case-management plug-ins, audit log exporters.
On-prem, in your VPC, or partner-hosted. Containerized; runs on standard GPU hardware.
The runtime image, the harness configuration, the rule pack catalog, and an API client. You provide the channel.