Use Case Intelligence RSS Search use cases Search
MongoDB Software / SaaS Canada

Ada

Customer Service Automation

Ada needed a flexible data platform for omnichannel customer-service automation so it could use unstructured data securely, train AI models, and keep shipping new products quickly as channels and modalities changed.

Read the original story Explore all use cases
Ada had around 300 customers including Meta, Verizon, and AT&T.
Ada has used MongoDB Atlas as part of its platform since the startup’s early growth after being founded in 2016.
The company says it can ship new products in just a few months with MongoDB.

Reported impact

Business outcome

Ada kept its AI stack flexible, accelerated product delivery, and created a safer path to using conversational data for generative AI improvements across customer-service automation.

  • Customer Experience
  • Scalability
  • Speed to Market

Solution

Ada uses MongoDB Atlas as the core data platform behind its AI automation products so it can ingest unstructured data from many channels, train models, and release capabilities quickly. The company adopted Atlas early to avoid spending engineering effort on database administration and to keep one data store flexible enough for changing channels and product ideas. Atlas stores the conversational and operational data that Ada queries to build and improve generative AI features, and the team says this allows it to ship new products in only a few months. Ada later adopted Change Streams to keep an internal data lake synchronized while powering distributed event processing for bots and analytics. The company is also exploring Queryable Encryption so it can learn from feedback and encrypted conversations without exposing sensitive customer records. Together, these capabilities let Ada push generative AI deeper into customer-service workflows without losing security or iteration speed.

Data flow

Conversational data from many service channels is stored in MongoDB Atlas, synchronized through Change Streams into Ada’s internal data lake, and then used by bots, analytics, and generative AI features while encryption preserves privacy for sensitive conversations.

Solution architecture

3 components · 3 layers
  1. Storage
    • MongoDB Atlas Stores Ada’s conversational and operational data and serves as the main platform for its AI automation products.
  2. Orchestration
    • Change Streams Keeps Ada’s internal data lake synchronized while powering distributed event processing for bots and analytics.
  3. Governance
    • Queryable Encryption Allows Ada to explore model learning from encrypted conversations without exposing sensitive customer records.

Architecture clues

  • Atlas serves as the single flexible data store across changing channels and modalities.
  • Change Streams power a distributed event-processing system for bots and analytics.
  • Queryable Encryption is being explored to protect conversation data during AI training.
  • The architecture is designed to reduce dependency on any single central cloud vendor.

Evidence from the source

“Using MongoDB means we’re not limited in how we source data if we want to build something new.”
“We wanted to focus on our business of automating customer service inquiries, not on administering Mongo. This was a huge ‘unlock’ for us in terms of velocity.”
“We’re super excited to be working with MongoDB Atlas, and can’t wait to see what else is in store.”
“With MongoDB, we’re able to ship new products in just a few months.”
Transparency Evidence & methodology 75/100 reference value · 77% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

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 value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence77%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. MongoDB

    Ada customer story

    First-party
    https://www.mongodb.com/solutions/customer-case-studies/ada
    Source type
    Vendor-published 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

Date evidence

  • First archived May 22, 2024 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Dec 20, 2025 · MongoDB · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open 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

See all like this
MongoDB Sep 30, 2025 TeamSystem Software / SaaS Italy TeamSystem aimed to embed AI for smooth content access on a secure, scalable platform; choosing MongoDB Atlas unified data and boosted innovation. By leveraging MongoDB Atlas’s automatic horizontal scaling, TeamSystem has taken the platform from an initial… Customer Service AutomationEnterprise Knowledge Search MongoDB Atlas MongoDB Archived · Mar 20, 2025 DevRev Software / SaaS Global Using MongoDB Atlas to consolidate data and boost efficiency for DevRev The mechanics of running a modern business are complex, involving many separate teams and systems — from customer relationship management (CRM) and… Customer Service AutomationEnterprise Knowledge Search MongoDB Atlas · MongoDB Atlas Vector Search MongoDB Archived · Sep 18, 2024 VinBigData Software / SaaS Vietnam VinBigData needed a centralized, cloud-native data layer for AI products serving multiple industries, because fragmented customer data and disconnected AI solutions made it hard to maintain accuracy, monitor operations,… 30% cost drop Customer Service AutomationReal-time Analytics Amazon Web Services (AWS) · MongoDB Atlas · MongoDB Atlas Vector Search