Case studies / Customer support
Customer support
Assistants and agents that answer customers and the teams that help them.
Approach
9 write-ups
Tag:
-
ZendeskNewCustomer supportBuilding an Open Service Directory registry for your platform’s support services
Problem Support services needed a way to be discovered and used by AI assistants across platforms.
Solution Built an Open Service Directory registry that ingests published service manifests, validates them, stores the full entries, and indexes key fields for searchable AI assistance.
Read on zendesk.engineeringDetails -
SnowflakeNewCustomer supportFrom Support Transcripts to Trusted AI Agents: Building a Knowledge Architecture with Snowflake…
Problem Support engineers waste time locating past resolutions across many systems.
Solution Snowflake built a knowledge architecture that stores support transcripts, creates embeddings, and uses RAG to let agents retrieve and answer similar issues.
Read on medium.comDetails -
TwilioNewCustomer supportHow to build an AI agent that remembers returning customers
Problem Customers have to repeat themselves because AI agents forget prior interactions.
Solution Twilio built a memory system that links identifiers, recalls relevant past facts, and writes new details back, so agents recognize and remember returning customers across channels.
Read on twilio.comDetails -
AgodaCustomer support
How Agoda is evolving engineering support with AI agents
Problem Engineers struggled to collect needed details and route support requests when issues were described in free text.
Solution Created OpsBot AI, an LLM‑powered Slack bot that reads engineers' problem descriptions, extracts relevant context, fills request forms, and routes tickets to the right team.
Read on medium.comDetails -
SalesforceCustomer support
How AI Agents Get Trusted Customer Context with Data 360 Data Graphs
Problem Agents lacked reliable, up‑to‑date customer information, leading to generic or incorrect responses.
Solution They built a Data 360 graph that stores verified customer data and connects it to Agentforce, letting agents retrieve trusted context in real time.
Read on engineering.salesforce.comDetails -
HoneycombCustomer support
Fin's CTO on Building Great Engineering Organizations in the AI Era
Problem Engineers spent too much time manually reviewing pull requests, slowing development.
Solution Created an AI‑driven PR review tool that automatically checks code changes using LLMs and observability data, removing the need for human reviewers.
Human reviewers eliminated
Read on honeycomb.ioDetails -
IntercomCustomer support
How to make the case for giving your AI Agent system access
Problem Customers asked for changes that the AI could explain but not execute, so support reps still had to intervene.
Solution They added system access to the AI Agent, turning simple scripted tasks into full‑process procedures that can read and write data in CRM, billing, and order tools.
Read on intercom.comDetails -
IntercomCustomer support
Extending Fin as the most open Agent platform
Problem Customers wanted an AI agent that could work inside their existing helpdesk without switching vendors.
Solution They created an open Agent platform with public APIs, CLI, and a proprietary model, letting HubSpot and Freshdesk users add the agent in under an hour.
Read on intercom.comDetails -
IntercomCustomer support
Speed-to-lead is a solved problem
Problem Customers waited hours for a sales rep, losing interest before a reply.
Solution They built an AI Agent that talks to prospects instantly, handling qualification, discovery, and demos in one chat, anytime and in any language.
Read on intercom.comDetails
No write-ups match these filters.