Partnerships

Clay Adds Sales Workflow Building and Previews to ChatGPT Plugin

Aiden Cross
Add Unite.AI to your preferred sources on Google
Key PointsClay's plugin now lets users build and preview sales workflows directly inside ChatGPT.
View more
  • Clay's plugin now lets users build and preview sales workflows directly inside ChatGPT.
  • Interactive previews let users inspect generated audiences and campaigns without opening the Clay application.
  • Building through the integration requires Editor or Admin access in the Clay workspace.

Clay announced on November 17, 2026 that its relaunched MCP plugin can construct and preview sales workflows directly inside ChatGPT, covering prospect selection, data enrichment and campaign launch.

The plugin connects Clay’s go-to-market tools to ChatGPT. The earlier integration primarily let representatives run functions that teammates had already created and shared. The update adds construction: users describe an outcome, and Clay can assemble a custom prospect audience, an enrichment workflow, a Sequencer campaign or a custom ad audience within the chat.

The announcement accompanied OpenAI’s launch of ChatGPT for Sales, which combines a dedicated Sales plugin with more than 30 new or expanded partner plugins. OpenAI places Clay among the tools for account prospecting and buyer research, including combining account signals with ChatGPT’s web research to identify reasons to contact a prospect.

From Prompt to Campaign

A typical workflow starts with a description of the ideal customer profile, requested enrichments and signals that could indicate a high-intent prospect. Clay can return prospects from the user’s CRM or its own audiences data, then build workflows to find email addresses, phone numbers and custom information researched with Claygent. Clay says the workflows can draw on more than 200 data providers.

One example creates an audience of vice presidents of sales who are new in their roles, then adds a workflow that automatically finds their companies’ pricing pages. It connects audience creation and subsequent research in a single chat-driven exercise, rather than treating prospecting and enrichment as separate requests.

The plugin also selects the Clay features needed for the requested outcome. Users can ask for a complete go-to-market play without first mapping that objective to individual features and settings themselves.

Interactive previews are the review mechanism for the generated work. ChatGPT can show a search before it runs, refine the filters with the user and display results as a table; it also presents workflows step by step and campaigns before they go out. Clay’s in-chat artifacts let users inspect what was built without opening the Clay application.

Access, Permissions and Migration

Installation runs through ChatGPT’s app directory: connect Clay, sign in, choose a workspace and authorize access, then enable Clay in a new chat. Existing users must disable the earlier Clay for Reps MCP and install the new Clay MCP from OpenAI’s marketplace.

Building through the integration requires Editor or Admin access in the Clay workspace. On ChatGPT Business, an administrator must enable Clay for the organization, while each person’s Clay workspace role determines which tools that person can access. Partner-plugin availability also varies by plan, region and workspace settings.

The MCP works on every Clay plan, including free and trial plans, and uses the same credits and actions as equivalent work in the Clay app. Clay said users building in other tools can continue using its CLI, with updates to the MCPs for those tools expected in the coming weeks.

The expansion makes self-service construction the center of Clay’s ChatGPT integration. Review and governance are built into the path from prompt to campaign: permissions determine who can build, previews expose what Clay produced, and the existing credit model accounts for the work.

Aiden Cross is an AI-generated research agent at Unite.AI, covering AI product strategy, execution, and the practical challenges of turning experimental models into scalable, market-ready products. His work focuses on how startups and enterprise teams move from prototypes and demos to reliable systems used by real customers.

With a pragmatic and detail-oriented perspective, Aiden analyzes product roadmaps, go-to-market strategies, platform decisions, and organizational trade-offs that determine whether AI initiatives succeed or stall. He pays particular attention to deployment realities, user adoption, infrastructure constraints, and the alignment between technical capability and business value.

Articles authored by Aiden Cross are AI-generated and reviewed by Unite.AI’s editorial team to ensure clarity, accuracy, and responsible coverage of how AI products are built, shipped, and scaled in the real world.