CMP42 // PRODUCT // HEADLESSREFUSED · NO FORCED UI
// Refused · No forced UI

NO FORCED UI.
AI IS THE UI.

Your team already uses ChatGPT, Claude, Slack. CMP42 does not compete with their interface — it feeds it. What we ship is the Podma Workbench and a migrations CLI: views, filters and saved views over a million rows.

// The bet

CRM UIS ARE DYING.

Your team already opens ChatGPT before they open Salesforce. They ask Claude to summarise a call before they log it. A partner drafts the follow-up note with a paste of the meeting transcript and “make it sound like me.” The workflow has changed. The database has not.

Legacy CRMs were built to be looked at. Every field, every pipeline, every dashboard exists because a human was going to click on it. That assumption is now legacy. AI does not click. AI reads structured context and writes structured actions.

Be honest about the role the CRM plays today: it is not the tool that runs the day, it is the database that gets consulted after the fact. If that is the honest role, let us build it for that role — a well-structured Context + Models + Processes graph and a fast, boring API, without a UI competing for your team’s attention.

// What headless means here

LESS SURFACE. MORE STRUCTURE.

Refused

No drag-and-drop pipeline builder

Pipelines are part of your ontology, not a canvas. Stages are declared in your model files, versioned in git and validated on every write — so an agent cannot write a stage that is not in the pipeline.

Delivered

A start page that counts

Records per object, deals by stage, lists, recent changes — the overview you need to decide anything, read straight from the graph. Ask your agent for the same numbers and you get them with citations. Want a standing view we did not build? The REST and GraphQL API is right there.

Delivered

The Podma Workbench

A direct view of the objects in your graph, for the moments when a human needs to work on the records themselves: views you can save as tabs, columns you show, hide, move, sort and filter, and a start page that counts what is in there. The same engine an agent reaches over MCP.

Delivered

A migrations CLI

Changes to your ontology happen in model files and are applied with a single command. The CLI is how the person who owns the data model works — reviewable, repeatable, in git.

The Podma Workbench is a real working surface, not a viewer. It supports reading and editing — inline for single cells, in a detail view for the full record — filtering by any field with saved views, bulk actions, and CSV or JSONL export. There is also a start page that counts what is in the graph. Access control is per Model with optional field-level restrictions,1 so a role can be granted read on Contact but with the phone number field masked.

¹ Planned for a future release.

// Your interface

YOUR TEAM ALREADY HAS AN INTERFACE.

It is called ChatGPT, Claude, Slack, or the app your engineers will build next month. CMP42 is designed to sit underneath all of them.

Where your team worksHow it reaches CMP42
Claude Desktop, Claude Code, Cursor, ClineDirectly, through the MCP tools generated from your models.
A custom agentThrough MCP, using the MCP SDK — or through REST and GraphQL.
Agents built on ChatGPT or other modelsThrough the surface you wire them to: MCP where the client supports it, otherwise REST or GraphQL.
Your team’s Slack botA bot you run, reading and writing through REST or GraphQL.
The app you build next monthREST or GraphQL — the same operations, auth and audit trail as the MCP tools.

Whatever the interface, every write is validated against your models and recorded against the human or agent that made it. All integration options → · Inside the engine →

// Common misreadings

WHAT HEADLESS DOES NOT MEAN.

Headless is a decision about where the interface lives — not a lack of visibility, control or care.

  • Not “you cannot see your data.” Podma shows the records; your agent answers with citations to the source objects; every object is versioned.
  • Not “you lose the overview.” Podma's start page counts what is in the graph, and anything it does not show you can build against the REST and GraphQL API. Control and overview are the point, not a trade-off.
  • Not “for developers only.” Most of your team works in the tools they already use. The CLI is for whoever owns the ontology; the API is for whoever builds on top.
  • Not a black box. Every write is attributable, every process run is logged and replayable, and human approval steps sit wherever judgement matters.
  • Not “start from zero.” CMP42 ships sensible defaults for contact, company, deal, task and activity, and generates MCP tools for them out of the box.
// Who does what

THREE ROLES. ONE GRAPH.

Your team

Ask and approve

Sales, partners and account managers ask their assistant for context and review what agents draft — at the human-in-the-loop steps you define in a Process.

Ontology owner

Shape the model

Whoever owns the data model edits model files, reviews changes in git and runs migrations with the CLI. The ontology is a product artefact, not a hidden setting.

Engineers

Build on top

Your engineers build the bot, the internal app or the dashboard against REST and GraphQL — or give an agent MCP tools and let it do the work.

// Questions on this

What people ask here

The same answers as in the CRM FAQ, next to the case they belong to.

BAS-02

What does "headless CRM" mean?

Headless means there is no user interface you are forced to use. There is no pipeline builder and no form for every field. Instead, CMP42 provides a structured graph of Context, Models and Processes and a fast API that any agent can read from and write to.

For keyboard work on large data sets there is the Podma Workbench: views, filters and saved views across a million records and more. Your team stays in its own tools, whether that is Claude, ChatGPT, Slack or in-house apps, and CMP42 supplies them with context.

Prompts and sources for this question

All 43 questions in the CRM FAQ