Reported impact
Business outcome
Search times dropped to under two seconds, enabling auto dismantlers to double sales within months and scale the circular economy for auto parts.
- Customer Experience
- Revenue Growth
- Speed to Market
MongoDBSoftware / SaaSEnterprise Knowledge SearchSales AutomationAI and Machine LearningData PlatformGenerative AI / LLMCustomer ExperienceRevenue GrowthSpeed to Market2026 MongoDBMDB#00684aSoftware / SaaSEuropeLekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds with its existing search system.LekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds…May 18, 20266Enterprise Knowledge Search|Sales AutomationMongoDB Atlas · MongoDB Atlas Search · MongoDB Atlas Vector Search0 2026-05-18 6
LekoTech
Enterprise Knowledge Search · Sales Automation
LekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds with its existing search system.
LekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds with its existing search system.
LekoTech previously struggled with search latencies of up to 35 seconds, a delay that risked losing potential buyers to competitors if they couldn’t instantly confirm a part’s price and availability.
The business has reduced its search latency from 35 seconds to under two seconds, and in many cases, full inventory searches across 300,000 spare parts can be handled in less than 100 milliseconds.
Solution
LekoTech needed to digitize millions of unique car parts to promote reuse but faced latency of up to 35 seconds with its existing search system. Consolidating on MongoDB Atlas and Vector Search allowed LekoTech to manage complex metadata and offer fast natural-language queries. More importantly, LekoTech aimed to advance the circular economy by focusing exclusively on original equipment manufacturer (OEM) parts, which are manufactured to last a lifetime. “LekoTech’s primary aim is to help breakers and dismantlers manage parts and inventories digitally,” said Nikolin Ngjela, CTO and Co-founder at LekoTech. “Dismantlers often don’t have a close connection with technology,” explained Ngjela. “One of our biggest struggles as a startup was to both educate them and make our system easy to use.” To make this vast, fragmented catalog accessible to buyers and fleet operators, speed is paramount.
Data flow
Business documents, tickets, records, and other operational content stay in MongoDB Atlas Vector Search and MongoDB Atlas Search, where search indexes or vector embeddings are built and then queried in real time to supply grounded results to applications, assistants, or discovery features. Upstream and downstream integrations include AWS, APIs.
Solution architecture
- Storage
- MongoDB Atlas Stores the operational, document, and context data behind LekoTech's AI-powered search and assistant experiences.
- Serving
- MongoDB Atlas Vector Search Retrieves semantically relevant context from LekoTech's data for AI, search, and recommendation workflows.
- MongoDB Atlas Search Provides relevance-based text retrieval across LekoTech's documents and application data.
Architecture clues
- AI agents or assistants are layered on top of the MongoDB data platform.
- The deployment integrates with APIs.
- The deployment integrates with AWS.
- Vector search is part of the retrieval layer for semantic or generative-AI use cases.
Evidence from the source
“Dismantlers often don’t have a close connection with technology,”
“LekoTech’s primary aim is to help breakers and dismantlers manage parts and inventories digitally,”
“Our Fleet Management app is a consumer-oriented layer that lets vehicle owners and fleet operators access that data for everyday maintenance and parts sourcing.”
“reduce, reuse, and recycle,”
Transparency Evidence & methodology
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
How scores are calculated
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Customer reference value100/100
- Problem clarity20/20Measures whether the customer's operational problem is specific enough to compare.
- Implementation depth25/25Rewards named components, data flow, integrations, and architecture detail.
- Outcome specificity20/20Measures whether the reported benefit is concrete rather than a generic claim.
- Quantified impact25/253 metrics describe measurable impact.
- Deployment scale10/10Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
- Source authority20/25The main evidence is an official vendor-published customer story.
- Claim traceability21/2510 of 12 key fields link to a named source.
- Direct evidence20/204 direct source quotes retained.
- Date provenance10/10The publication date comes from the source page or publisher.
- Source transparency8/101 source reference document publisher, URL, authority, retrieval, and supported fields.
- Implementation specificity10/10Rewards source-backed components, data flow, quantified impact, and a specific outcome.
Traceability
Sources & provenance
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
- https://www.mongodb.com/solutions/customer-case-studies/lekotechMongoDBFirst-party
LekoTech customer story
Supports- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes
- Publication date
Date evidence
- Published on source page May 18, 2026 · MongoDB · First-partyOpen date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.
Related
Similar use cases
MongoDB Sample Apr 29, 2026 Tenali AI Tenali AI needed to help enterprise sellers answer deeply technical questions during live calls in under one second by searching Slack, PDFs, CRM data, and prior meeting content without the latency and synchronization… After switching embedding models, sales reps actively using Tenali's answers on live calls increased by over 40%. MongoDB Atlas · MongoDB Vector Search · Voyage AI 
Snowflake Sample Archived · Mar 19, 2026 Tipalti Tipalti needed a secure way to give internal teams timely, consistent AI-backed business insights without moving data into external inference services or depending on specialist prompt engineers. $75 billion in payments managed yearly AI_COMPLETE · Cortex AI · Snowflake MongoDB Sample Mar 3, 2026 Super AI Super AI needed to build a secure, hallucination-resistant RAG platform for a pharmaceutical client that could guide 15,000 field sales reps without exposing sensitive data or sacrificing response speed. Super AI scaled to enterprise securely with a 16-engineer team. MongoDB Atlas · MongoDB Atlas Vector Search