How Fiber AI Uses Elasticsearch to Scale Sales Automation to $1M ARR

Fiber AI is a Y Combinator-backed startup that automates outbound sales prospecting, drawing on a database of 850 million LinkedIn profiles, 40 million companies, and 13 million job postings. The company built its search infrastructure on Elasticsearch, which now searches across a billion rows in under one second. Within six months of launch, Fiber AI reached $1M in annual recurring revenue while operating with a team of eight people.

Impact

$1M+ ARR

Annual recurring revenue at launch

40–50%

Increase in targetable outreach prospects

80%+

Reduction in monthly infrastructure costs

Dozens of terabytes

Database size managed

Under 1 second

Query speed on 1 billion rows

Challenge

Fiber AI needed to search a database of over 850 million records with sub-second response times while adding new search criteria on short notice — requirements that existing columnar and SQL-based solutions could not meet without prohibitive cost or engineering overhead.

Solution

Fiber AI built its prospecting search on Elasticsearch, which handles billion-row queries in under one second and allows new search criteria to be added with a few hundred lines of DSL code, while hot/warm data tiering keeps infrastructure costs manageable as data scales to terabytes.

Tools & Technologies

What Leaders Say

When I first tried Elasticsearch, I was blown away. I ran a search on a billion rows in just one second, whereas other products took 30 minutes. I honestly don’t know how we managed without it.

Neel Mehta, CTO and co-founder, Fiber AI

No other tool I know has increased our productivity like Elasticsearch. It allows us to add new features for our customers every week. The amount of time and effort it saves is enormous.

Neel Mehta, CTO and co-founder, Fiber AI

With Elasticsearch, customers have increased their sales outreach response rates by 40 to 50% with virtually no loss in performance.

Aditya Agashe, CEO and co-founder, Fiber AI
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

Fiber AI was co-founded by Aditya Agashe and Neel Mehta, two Forbes 30 Under 30 honorees who set out to automate the most time-intensive parts of B2B sales: finding the right prospects and initiating contact. Their platform enables sales development and business development teams to search a proprietary database aggregating data from more than 50 providers — including BuiltWith, Crunchbase, and G2 — and automatically generate personalized outreach messages.

The core engineering challenge was speed. Fiber AI’s database contains 850 million LinkedIn profiles, data on 40 million companies, and 13 million job postings. To deliver useful search results, the system needed to handle complex multi-variable queries — such as finding companies in India with between five and ten product managers — at sub-second latency. Early testing of ClickHouse, other columnar databases, and vectorized SQL solutions on PostgreSQL all fell short. A query that took Elasticsearch one second took other tools 30 minutes.

With Elasticsearch at the core, Fiber AI built a search layer that can accept a broad query like “rev ops” and automatically map it to “revenue operations” through hundreds of configured synonyms and stop-word rules. The team also uses Elasticsearch’s data tiering (hot/warm architecture) to manage the database as it scaled from gigabytes to dozens of terabytes, cutting monthly infrastructure costs by over 80% without degrading query performance.

The operational results are concrete. Fiber AI’s customers report a 40–50% increase in the share of prospects that are actually targetable for outreach — reducing the time spent building prospecting lists from two to three hours to near-zero. Monthly infrastructure costs dropped from mid-five figures to under $10,000. The company closed deals with Ramp, DocuSign, Flatfile, Lumos, and Secureframe in its first months of operation.

Fiber AI is now adding auto-response features that include meeting links and FAQs, with continued integration of Elastic’s AI capabilities. The team credits Elasticsearch not just as infrastructure but as the primary driver of their ability to ship new search features weekly — capabilities that would otherwise have required months of custom development.

Similar Cases

L
Lusha
300%
increase in outbound leads

Lusha is a B2B sales intelligence platform with 1.5 million users and a database of over 200 million business contacts. By deploying Elasticsearch as both a full-text search engine and a vector database for AI-powered lead recommendations, Lusha helps customers generate 300% more leads, achieve conversion rates up to 10x higher, and realize return on investment of up to 1,000%.

TechnologyEElasticsearch
D
Docusign
Under 1 minute
document retrieval time

Docusign, the Intelligent Agreement Management (IAM) platform serving 1.6 million customers and over 1 billion users across 180 countries, built its AI-powered Navigator repository on Elasticsearch to index and search billions of agreements in real time. The deployment enables customers to find specific documents in under a minute—tasks that previously took hours—while handling millions of new agreements added to the platform each day.

TechnologyEElasticsearchMAMicrosoft Azure
A
Apna
20%
increase in employers paying for premium access

Apna, India’s largest jobs and professional networking platform with 50 million registered users and 600,000 employers, built its candidate search and AI job matching infrastructure on Elasticsearch running on Elastic Cloud on Google Cloud. Semantic search capabilities allow employers to find candidates by intent—not just keywords—while AI algorithms analyze candidate profiles to surface the most relevant matches. The result: a 20% increase in employers paying for premium access, 20% higher platform team productivity, and a 50% improvement in employee productivity.

TechnologyEElasticsearch
C
Cypris
Weeks → 15 minutes
research report generation time

Cypris is an AI-powered R&D intelligence platform that enables teams to analyze over 500 million technical and market data points—patents, scientific literature, funding data, and news—in seconds. The company built its core RAG architecture on Elasticsearch for vector search and semantic retrieval, replacing a problematic prior search provider. The platform now generates detailed research reports in 15 minutes rather than weeks, supports 30% quarterly enterprise customer growth, and manages more than 10 terabytes of indexed data without scalability constraints.

TechnologyECElastic CloudEElasticsearch
WE
WP Engine
~5 milliseconds
search query response time

WP Engine, the leading WordPress hosting platform serving more than 1.5 million users across 200,000 websites in 150+ countries, deployed Elastic’s Search AI Platform alongside Google Cloud Vertex AI and Gemini to build Smart Search AI and enable retrieval-augmented generation (RAG) capabilities for its customers. The integration allows WP Engine to deliver natural language search, context-aware product recommendations, and AI-powered chatbots to website owners without requiring them to stitch together multiple vendors. Response times dropped to as low as five milliseconds, and the platform handled traffic spikes from hundreds of thousands to tens of millions of queries per minute with zero downtime.

TechnologyEElasticsearchGVGoogle Vertex AI
CA
Contextual AI
90%+
rag accuracy achieved in production

Contextual AI is an enterprise AI platform company that specializes in production-ready Retrieval Augmented Generation systems for complex knowledge tasks. The company built its context engineering platform on Elasticsearch, using hybrid search combining BM25 and vector search to power accurate, scalable AI agents for enterprise customers. With this foundation, Contextual AI’s agents achieve over 90% accuracy on demanding production tasks—well above the 65–75% range typical of traditional RAG approaches.

TechnologyEElasticsearch
A
Allspice
20% → 97%
ingredient matching accuracy

Allspice, a food technology startup building a kitchen operating system for consumers and recipe publishers, deployed Pinecone’s vector database to solve the inherent messiness of ingredient data that traditional text search could not handle. The implementation raised ingredient matching accuracy from roughly 20% to 97%, enabling the launch of recipe importing as a core product feature and expanding into a platform-wide semantic layer for search, recommendations, and conversational AI.

TechnologyTtext-embedding-3-largePPinecone
S
Sommo
500–800
additional leads generated monthly

Sommo built an AI-powered SRS generator in Make in a single day, generating 500–800 additional leads per month and achieving a 5x increase in active website users.

TechnologyMMakeOOpenAI