Actionable intelligence needs accurate data
Decisions on policy, budgets and public services need answers that are correct, current and traceable. Too many AI vendors rely on general tools never built for your data.
AI that your organisation owns and controls
We research and build our own AI engine, then use it to create custom systems that turn large, complex and changing data into accurate answers, with full control of your data.
The problem
Where general-purpose AI breaks down
Your data sits in silos
Records live in separate systems, formats and teams. Each looks routine on its own. The pattern that matters only appears when they are connected.
Sovereign data cannot leave
Citizen records and sensitive state data are bound by residency and security rules. Sending them to a foreign AI service is a risk few institutions can accept.
Institutions do not need more AI. They need intelligence they can trust, trace and keep in-house.
Who we are
Gani Labs builds custom AI systems for organisations that need accurate answers
We are the custom build arm of Gani.AI. We design the complete system: the data model, retrieval, AI agents and deployment, on the same engine that runs Gani.AI's legal platform every day.
2024
Core engine in daily production use since
5,000+
Users on the engine through Gani.AI
ISO 27001
Certified information security
4
Markets: Indonesia, Singapore, Japan and India
Deeptech, not a wrapper
We build the core technology, not a layer on top of someone else's
Most AI vendors connect a general chatbot to your files. We research and engineer the parts that decide whether an answer is right: how knowledge is modelled, how it is found, how it changes over time, and how every answer is checked.
Our research and our engine are built in-house. Select a layer.
Layer 04 · Our research
Agentic graph retrieval
GIA-RUT: Graph-Inspired Agentic Retrieval with Unified Traversal
- The AI walks the graph step by step, choosing a tool at each step
- Combines database queries, live data, graph links and documents
- Checks that each fact is current before it reaches the answer
Temporal ontologies
Domain models that capture entities, relations and validity over time, first built for law.
Agentic graph traversal
Retrieval that plans its own path through connected records instead of matching text chunks.
Context engineering
Only material the user may see, linked to the question and still in force, reaches the model.
Expert-scored testing
Question sets written and scored by your own experts, re-run on every release and new model.
| Typical AI vendor | Gani Labs | |
|---|---|---|
| How knowledge is held | Text chunks in a vector index | A temporal knowledge graph of your entities |
| How answers are found | Similarity search, one step | Agentic traversal across graph, data and documents |
| Changing information | Whatever was indexed last | Knows which version was in force on any date |
| Sources | Sometimes, often loosely | Every fact traced to the record behind it |
| Models | One provider's API | Chosen and tested per task; can run offline |
| Proof of quality | Demos | Scored by your experts on real questions |
Side story · Where the engine comes from
We built it for law first: the hardest test for AI
Law changes constantly
Amendments replace articles. New regulations revoke old ones. The answer must be the one in force today.
Every answer needs a source
A lawyer cannot act on a claim they cannot trace to the article, decision or clause behind it.
Many languages and systems
Indonesian, Japanese and English law, each with its own structure and terms.
Confidential by default
Client matters can never leak, between users or outside the firm.
5,000+
Gani.AI users
~25
Enterprise clients
4
Regions live: Japan, Singapore, Indonesia, MENA
What law taught us
Three capabilities proved on legal work
Law ontology
Laws, articles, amendments, regulations and decisions as connected entities, each with the date it takes effect and what it replaces.
Advanced GraphRAG
Graph-Inspired Agentic Retrieval with Unified Traversal: the AI walks the graph step by step and checks every fact is current.
Advanced context management
Only what matters reaches the model: material the user may see, linked to the question and still in force.
A slice of the law ontology · select a node
Amendment
Replaces the text of an article from a set date. The engine keeps both versions and knows which one was in force on any day.
From law to any domain
The same patterns exist in every organisation
| Pattern | In law | In your organisation |
|---|---|---|
| One record replaces another | An amendment replaces an article | A revised SOP replaces the old one |
| A rule carries out a policy | A regulation implements a statute | A procurement rule implements a purchasing policy |
| A record explains an event | A court decision interprets a law | An inspection report explains a site incident |
| Access depends on role | Client matters stay inside the team | Each user sees only what their role allows |
An engine that stays accurate on law stays accurate on your data.
The engine
Three capabilities, one system you own
Finding the latest correct information
We model the entities in your data, how they relate and how their status changes over time. Retrieval then collects context in steps, choosing the right tool at each step and checking that the data is current.
Your ontology: entities, links, status
"Which sites had more incidents this month than last month, and why?"
Answer: the sites with more incidents, the likely cause at each, and the source of every fact.
Agents that plan, act and check their own work
One coordinator plans the task and hands each part to a specialist agent. They share the same tools, permissions and checks.
Autonomous agents
Work on their own, all the time, inside limits you set.
- Watch live data and detect changes
- Send alerts when a rule or limit is crossed
- Prepare regular status summaries
- Read and analyse only; never change records
Supervised agents
Work with a person, who stays in control of every decision.
- Answer questions and run analysis on request
- Compare options and show the evidence
- Propose actions for a person to approve
- Stop and wait before any important step
Agents see only what the user or role may see
Every step, tool and source is recorded
Important actions always need a person's approval
Documents, databases and live data in one system
SourcesERP and SQLSharePointRegistersDocumentsScans (OCR)Live feeds
- Step 1
Read
Connect directly, sync on a schedule, or read scans with OCR.
- Step 2
Structure
Pull out the fields you define. Tables become entities.
- Step 3
Link
Connect records to people, assets, places and events.
- Step 4
Track
Keep every version, so status is known at any date.
- Step 5
Reason
Detect changes, count trends, find conditions and limits.
Millions of records and thousands of files, each summarised, classified and indexed automatically. Scheduled jobs pick up new or changed data and record every run.
What people cannot see
The system connects facts no single person sees together
Each fact sits in a different system, format and team. Alone, none of them is a warning. The graph links them, and the AI explains what they mean together, with the source of each fact.
Live feed
Main route to Region 4 closed this morning
Database
Stock in Region 4 below the minimum level
InsightRegion 4 will run short soon, and its only supply route is blocked.4 sources · 4 formats · 1 answer
Scanned agreement
One supplier serves all of Region 4
Report, 3 months old
Demand in Region 4 is rising
All data
Only what you may see
Linked to the question
Still current
Answer with sources
Industries
One engine, built for every sector
Each sector has the same underlying problem: records that change, live in silos and must be traced. We model your domain on the same engine, so the system speaks your language from day one.
Government and public sector
Decisions on policy, budget and services
Policy, budget and service data is spread across ministries and agencies. Reports take weeks to compile and are out of date by the time they land.
- Regulation lookupThe rule in force today, with what it replaced
- Budget and procurementSpending, contracts and variations linked
- Citizen servicesAnswers drawn only from approved sources
- Cross-agency insightLinked data without moving raw records
A question it can answer
Data it connects
"Which programmes are over budget this quarter, and which contract changes caused it?"
Budget systemsProcurement recordsRegulationsAudit reportsAgency registers
How you benefit
- Faster briefings for ministers and senior officials
- Data stays in-country on sovereign or on-premise infrastructure
- Every figure traced to the system and record it came from
Legal, tax and compliance
Answers lawyers can cite and defend
Laws, tax rules and regulations change constantly. An answer built on a revoked article is worse than no answer at all.
- Legal researchAcross laws, amendments and decisions
- Contract reviewClauses checked against current rules
- Regulatory monitoringAlerts when a relevant rule changes
- Matter knowledgeKept inside each team, never shared
A question it can answer
Data it connects
"Does this data transfer clause still comply after the latest amendment?"
Statutes and regulationsCourt decisionsTax rulingsContractsMatter files
How you benefit
- Proven at scale on Gani.AI, used daily by 5,000+ users
- Citations by default to the exact article or clause
- Confidential matters isolated by role and team
Financial services
Risk and compliance you can explain to a regulator
Customer, risk and compliance data live in separate systems, and regulators expect every decision to be explained with evidence.
- Regulatory changeNew circulars mapped to internal policies
- Credit and KYC reviewFiles checked against current rules
- Risk signalsLinked across transactions and records
- Audit supportAnswers with a full evidence trail
A question it can answer
Data it connects
"Which loan policies are affected by the new central bank regulation, and what must change?"
Core banking dataCredit filesRegulator circularsInternal policiesTransaction logs
How you benefit
- Shorter compliance cycles from new rule to updated policy
- Explainable outputs every step and source recorded
- No data leaves your environment or jurisdiction
Healthcare and public health
Earlier warning, from data you already hold
Case reports, registers and field data arrive in different formats and at different speeds, so trends show up late.
- Early warningCase data combined with weather and surveys
- Guideline lookupThe current clinical protocol, with source
- Facility monitoringStock, staffing and capacity linked
- ReportingRoutine reports prepared automatically
A question it can answer
Data it connects
"Which districts will see more dengue cases next month, and why?"
Clinic case reportsDisease registersWeather feedsSupply recordsGuidelines
How you benefit
- Act weeks earlier on rising cases or shortages
- Patient data protected on your own servers if required
- Clear reasoning showing which signals drove each alert
Energy, utilities and infrastructure
Find the cause, not just the symptom
Asset, maintenance and sensor data rarely sit together, so working out why a failure happened can take days.
- Root-cause analysisReadings, logs and reports linked by asset
- Maintenance searchEvery inspection and work order for an asset
- Monitoring agentsAlerts when limits or patterns are crossed
- Permit complianceConditions tracked against current rules
A question it can answer
Data it connects
"Why did Substation 12 trip twice this month?"
Sensor and SCADA readingsMaintenance logsInspection reportsAsset registersPermits
How you benefit
- Faster investigations with the evidence already assembled
- Fewer repeat failures by linking cause to asset history
- Works offline for sites that cannot connect out
Logistics, supply chain and manufacturing
See shortages before they happen
Stock, supplier, route and demand signals sit with different teams. Most shortages are noticed only after they hit.
- Shortage alertsStock, demand and routes combined
- Supplier checksContracts, SLAs and single points of failure
- SOP lookupThe current revision, with what changed
- Incident analysisLinked to equipment, shifts and changes
A question it can answer
Data it connects
"Which regions will run short next week, and which suppliers can cover them?"
ERP and warehouse dataSupplier contractsLive route feedsDemand reportsSOPs
How you benefit
- Earlier action on disruptions and stock-outs
- Fewer blind spots across teams and systems
- Measured results scored in a pilot before scale-up
Questions are illustrative. In discovery, your team writes the real ones we are measured against.
Discuss your sectorSelected projects
Custom systems already built on our engine
Regional law firm
A firm-owned AI platform for its legal operations. Chosen over a leading US legal AI product after a head-to-head evaluation.
Outsourcer for public buyers
Graph-based retrieval over procurement rules and records, so staff always find the current rule and the records linked to it.
Research institute
52xFaster reporting, annual to weekly. 850K+ articles from 25+ countries, about 142K added a month.
Services company
A custom AI system for document-heavy operations, focusing on HR and outsourcing services.
Client names are confidential. References are available on request.
How we work with clients
Start small, measure the results, then expand
- Phase 1
Discover
Workshops to model the data, a review of sources, and a set of real questions to measure success.
- Phase 2
Pilot
One area built from start to finish. Your own experts score it with the question set.
- Phase 3
Expand
More data sources, users and locations. Security review completed and the system handed over.
- Phase 4 · Ongoing
Operate
Monitoring, re-testing when new models are released, and training for your team.
You see measured results before you commit to scale, and you own what we build.
Why Gani Labs
Built for work where accuracy is critical
Deeptech at the core
We research and build the engine ourselves, so we can fix accuracy at the source rather than work around someone else's product.
Proven on law first
Our engine was built and tested on legal work, where an outdated or unsourced answer is never acceptable.
Context and knowledge first
We model how information connects, so every answer is current, relevant and backed by sources.
Your data, your system
Data stays in your environment, on dedicated infrastructure or your own servers. You own what we build.
Tested and measured
Your experts score every major release against real questions. We report what did not work, too.
Built for your sector
One engine, modelled to your domain, whether that is public policy, finance, health, energy or supply chains.
Built by legal and engineering insiders: founders who built a top-10 Indonesian law firm, and an engineering team that runs the engine in production every day.
Security and deployment
Your data and models stay inside your organisation
Your environment
The system runs on infrastructure dedicated to you, in your jurisdiction. Your questions and documents stay there and never train anyone's model.
On-premise option
Models, databases, pipelines and monitoring on your own servers. No internet connection required.
Flexible model choice
We select and tune models for each task, test them on your own questions, and replace them when better ones arrive.
- Role-based access by project and team, checked at every level
- Audit logs of access, changes and permissions, kept at least a year
- Full tracking of every agent step, tool and source in an answer
- No training on client data. Files never shared directly from storage
- ISO 27001 certified, with single sign-on and admin controls
Questions
Frequently asked
What do you mean by deeptech?
We do not resell or wrap a general AI product. The parts that decide accuracy, including the knowledge graph, the retrieval method and the evaluation process, are researched and engineered by our own team and run in production every day on Gani.AI.
Is this a chatbot connected to ChatGPT?
No. Language models are one component we choose per task. Answers come from your own data, found by our retrieval engine and checked for currency and access rights before any model writes a response.
Do we need to move our data to the cloud?
No. The system can run on infrastructure dedicated to you in your jurisdiction, or fully on your own servers with no internet connection.
Which industries do you work with?
Government, legal and compliance, financial services, healthcare, energy and utilities, and logistics and supply chain. The engine adapts to any domain where records change over time and answers must be traced.
How do we know it works before committing?
We start with a pilot on one area. Your own experts score it against a set of real questions, and you decide whether to expand based on measured results.
Who owns what you build?
You do. The system, its configuration and your data stay with your organisation.
AI that your organisation owns and controls.
Tell us about the data you hold and the decisions it should support. We will come back with a scoped discovery plan.