Product

Entity resolution
infrastructure for developers

Tilores is a serverless API that ingests customer data from any source, resolves duplicates in real-time, and returns unified entity profiles via GraphQL — all without infrastructure to manage.

Available on AWS Marketplace · Other hyperscalers and on-premise also supported


Architecture

Serverless. Horizontally scalable. Zero maintenance.

Tilores runs entirely serverless — it scales up and down instantly to handle any volume with no manual intervention. No servers, no databases, no DevOps.

Ingest & Transform

Push records via API, connectors, or bulk import. Data is cleansed, normalized, and enriched before matching.

Match & Resolve

Proprietary matching engine supports both deterministic rule-based and probabilistic ML-based matching using data science algorithms — choose what fits your use case.

Query

Retrieve unified entity graphs via GraphQL or SQL. Sub-100ms queries, type-safe schemas, full audit trail.


Matching Engine

Fuzzy matching that understands the real world

Tilores goes beyond exact matches. Our matching engine handles the messiness of real-world customer data — typos, nicknames, format variations, and more.

Name variations
"Jon Smith" ↔ "Jonathan Smith" ↔ "J. Smith"
Transliterations
"Müller" ↔ "Mueller" ↔ "Muller"
Address normalization
"St. 14" ↔ "Street 14" ↔ "Straße 14"
Phone formats
"+49 30 1234" ↔ "030-1234" ↔ "00493012­34"
Email domains
"john@gmail.com" ↔ "john@googlemail.com"
Custom attributes
Device IDs, transaction references, any field you define
How matching works
1. Data Transformation

Incoming records are normalized, cleaned, and enriched. Names are standardized, addresses parsed, phone numbers formatted.

2. Rule-Based & ML Matching

Configurable deterministic rules compare attributes using fuzzy and data science algorithms — transparent and fully explainable. Probabilistic ML-based matching is also available for teams that want learned models.

3. Entity Assembly

Matched records are assembled into entity graphs with confidence scores, source attribution, and full data lineage.

4. Continuous Resolution

As new data arrives, entities are updated in real-time. No batch jobs, no stale data.


New: IdentityRAG

Give your LLM a unified
view of every customer

IdentityRAG connects Tilores entity resolution to LangChain and Amazon Bedrock. Your AI chatbot gets a complete, deduplicated customer 360 — not fragments from a single database.

Retrieves unified customer profiles before generating LLM responses

Creates accurate golden records from disparate data sources

Response times under 150ms for identity resolution

Works with any LLM via LangChain integration

IdentityRAG Flow
1
User asks
"What's Sarah Johnson's order history?"
2
IdentityRAG resolves
Finds all records for Sarah across CRM, Shopify, ERP, Support
3
Golden record created
Unified profile with 14 orders, 2 emails, 4 source systems
4
LLM responds
"Sarah has 14 orders totaling €2,847. Her last order was..."

Integrations

Connect in minutes, not months

Prebuilt connectors for popular platforms, plus a flexible API for everything else.

SA
Salesforce
HU
HubSpot
SN
Snowflake
GR
GraphQL
WE
Webhooks
EV
Event Streams

Why Tilores

Tilores vs. the alternatives

Building entity resolution in-house takes years. Existing tools aren't built for real-time. Tilores gives you both.

Feature
Tilores
AWS ER
DIY
Real-time resolution
Sub-10ms latency
GraphQL API
No infrastructure to manage
No ML expertise required
Fuzzy matching built-in
Prebuilt connectors
GDPR compliant
Time to production
Minutes
Days
Months

Ready to unify your customer data?

Talk to our team about your use case, or download the evaluation build to try it with your own data.