Modem

The customer context graph

One graph under every customer conversation

Modem links topics, people, and companies across every channel where feedback lands, then hands the merged picture to your team and your agents.

  • Superwhisper
  • Kernel
  • Sentry
  • Zumper
  • OpenCode
  • Polytomic
  • Fig
  • Composio

Your customers have thoughts.
Most of them get lost.

  • Finding it is hard

    Support sees the email, sales hears it on a call, product reads it in Slack. Nobody notices it's the 10th time this month.

  • Fixing it is slow

    Engineering finally gets a ticket, with half the context never captured. Scoping and fixing it both take longer.

  • Following up rarely happens

    The fix ships. Whoever heard the complaint never finds out, so the customer who asked never hears back.

Every concern, grouped and linked to the PRs that fix it

Modem groups what customers say into topics, then tracks the issues and pull requests working on each one. You always know what’s open, in progress, or completed.

How it works

From raw channels to a queryable graph

raw messagesone connected graph

Scattered messages become one graph

Modem reads every channel you connect and links what it finds. Duplicate reports merge into topics, and each topic keeps the original quotes.

DiscordZendeskGongone topic, three sources

Every channel lands on the same topic

A bug reported in Discord, Zendesk, and a Gong call is one topic with three sources. Counts stay honest because nothing gets counted twice.

MCP> who hit this bug?4 customers · 2 channelsquotes attached

Your agents query it over MCP

Claude Code, Cursor, and anything speaking MCP can ask the graph directly, so a task arrives with the affected customers and their exact words attached.

What it is

What a customer context graph is

A context graph stores customer feedback as relationships. The same issue reported in three channels becomes one topic with three sources. The person who emailed support and the person in your shared Slack channel resolve to one customer, linked to their company, plan, and history. Modem builds this graph automatically from the sources you connect and keeps it current as new feedback arrives. For the full concept, including what you can build by hand and where that breaks down, read the guide on what a customer context graph is.

  • Joined at capture time

    Deduping and linking happen as each message arrives, not as a research project when someone finally asks a question.

  • Quotes stay attached

    Every topic keeps the original customer words, so no summary paraphrases away the detail an engineer needs.

  • Accounts in the picture

    Requests tie back to companies, plans, and revenue, which turns "12 people asked" into a prioritization argument.

FAQ

Common questions about context graphs

What is a customer context graph?
A customer context graph stores feedback as relationships instead of rows. Topics, people, and companies are linked across every channel where feedback lands, with the original quotes attached. Modem builds one automatically from the sources you connect.
How is a context graph different from tags?
Tags label rows but do not connect them. Two tickets tagged exports still do not know they are the same issue or the same customer. A graph makes those joins at capture time, so counts and customer lists stay accurate as feedback arrives.
Can my agents query the context graph?
Yes. Modem exposes the graph over MCP at mcp.modem.dev and through the @modem-dev/cli package on npm. Claude Code, Cursor, ChatGPT, and any MCP-compatible agent can search topics, pull customer history, and ask questions against it.

Less digging, more shipping

Research takes minutes, and every fix comes with the list of who asked. Your agents self-serve answers faster through Modem's MCP instead of reading raw threads.

  • 3–4 hrs to 10 min

    Product research tasks that used to take an afternoon1

  • 5–10 times

    Customer touchpoints surfaced per bug fix, across every channel1

  • 98% fewer tokens

    Agents read Modem's context graph vs the raw threads underneath2

  1. Research time and touchpoints per fix: reported by Sentry's product team. Read the Sentry case study
  2. 98% fewer tokens: measured by Modem on real usage data, on average.

Trusted by teams that listen (and ship)

  • Kernel
  • Superwhisper
  • OpenCode
  • VLT
  • Sentry
  • Zumper
  • Mycroft
  • Fig
  • Novelcrafter
  • HumanLayer
  • Basedash
  • Polytomic
  • Composio
  • FusionAuth

“Things that would have taken three or four hours are ten-minute tasks now, and when we fix something, Modem shows us everyone who was waiting.”

Nicholas MeisenheimerProduct Manager @ Sentry
Read Case Study

“While I’m working on something I can just hop over and ask Modem, and get an answer in minutes – instead of searching across all the channels and getting out of the flow.”

Leonie GräßelFounder @ Novelcrafter
Read Case Study

Connects to every channel and tool, answers wherever you work

Modem reads the tools your customers and team already use, then hands the whole story to people and agents, sources attached. Explore all integrations

Chat

  • Slack
  • Discord
  • Teams
  • Email

Support

  • Intercom
  • Zendesk
  • Front
  • Plain
  • Pylon
  • Jira Service Desk

Calls

  • Gong
  • Fathom
  • ZoomSoon

Customers

  • Salesforce
  • Stripe
  • Canny

Analytics

  • PostHog
  • Mixpanel
  • Amplitude
  • Sentry

Code

  • GitHub
  • GitLab
  • Linear
  • Jira

Need an integration we don't have? Talk to us

  • Dashboard

    Navigate your customer graph using a complete web UI.

  • Agent

    Full-featured cloud agent, available in Slack, Teams, Discord, or web.

  • Plugins & MCP

    Bring your favorite desktop, terminal, or cloud agent.

  • CLI

    Query your Modem data from any terminal. Great for agents.

  • HTTP API

    The same data as everything else, as JSON over HTTP.

Security and compliance

Modem combines industry-standard compliance, enterprise-grade controls, and privacy-first product features at every layer.

  • SOC 2

    SOC 2 compliant. Independently audited against the AICPA Trust Services Criteria.

    Trust center →
  • SSO + SCIM

    Manage access at scale with SSO and SCIM provisioning from the identity provider you already run.

  • Governance

    Audited agent runs, roles, PII scrubbing, and custom retention.