Give your agents
the product context.

Give agents the product model, relationships, and evidence behind the work. Ask them to trace a component change, explain release blockers, or prepare a change request. Your team reviews the proposal in ManyRows.

7-day free trial · No card requiredView plans and trial limits

Hosted MCP server · REST Data API · Project permissions

Agents prepare the work. Your team reviews and approves.

  1. Understand the context

    Read the types, relationships, and current product records.

  2. Prepare the work

    Validate values and stage proposed changes for review.

  3. Review and approve

    The assigned people review the change and preserve the decision.

Connect the AI client you choose.

ManyRows provides the product model and workflows. Bring a compatible external AI client through MCP; a built-in assistant is not included.

Separate product work from AI usage.

Your ManyRows plan covers the workspace and its API limits. Your chosen AI provider manages its own subscriptions, usage charges and data handling.

Use the subscription you have.

Connect an MCP-compatible client to the project endpoint. Check whether your client and subscription support remote MCP and the required authentication method.

Choose your own workflows.

Use the client to inspect records, trace BOM relationships or prepare a change request. Access follows the connection’s granted scope, current project permissions and workflow rules.

Connect your AI through MCP

From understanding
to taking action.

Start with a concrete question: which assemblies use this part, what blocks this revision, or which changes need review? Agents work through the project’s permissions and existing workflows.

01

Understand the product

Explore the schema, read records, trace BOM structure, and follow where-used before planning the next step.

Connect an agent
02

Build and evolve the model

Describe your product and let an agent create record types, fields, and relationships for your team. With schema permissions, it can build on your existing model and validate new definitions.

Explore modelling
03

Keep records in sync

Use stable business keys, validation, and version checks to connect product records to the systems your team already uses.

Explore the API
04

Prepare governed changes

Stage edits to controlled records in change requests. The team can review proposed work before the approved product record changes.

Explore change control
05

Check release evidence

Ask what blocks the latest product revision. Get document and inspection evidence, source links, and next actions, with gaps in coverage made explicit.

Explore release evidence
06

Follow the review handoff

Owners and project administrators can follow recorded agent actions and linked reviews. The workspace inbox brings pending, returned, and rejected changes together.

Explore team review

Agent preparation.
Human approval.

Follow recorded agent actions to the affected records and reviews. Use the workspace review inbox to find pending decisions, inspect the full change, and request corrections or approve through the existing review policy.

See how changes work
ManyRows change request showing proposed changes and review detailsClick to enlarge ↗
Review proposed work against the product record.

Use the interface that fits the work.

MCP

Connect an AI client

Start with the agent guide for project identity, effective access, and task entry points. The hosted MCP server exposes permitted tools and leaves human-only decisions out of its executable catalog.

Read the MCP guide
REST

Build an integration

Use the JSON Data API for application integrations and automation. Discover capabilities, validate inputs, and make version-aware updates.

Read the API guide

A few practical questions.

Do we need AI agents to use ManyRows?

No. Your team can manage parts, BOMs, changes, and quality directly in the web workspace. Connecting AI agents is optional, and you can add them when they fit your workflow.

What does AI agent-ready mean?

ManyRows exposes its product model and supported workflows through a hosted MCP server and REST Data API. Agents can discover the schema and work with structured product records using the permissions granted to their connection.

How does an agent connect?

Connect an MCP-compatible client to your project’s hosted MCP endpoint. Use OAuth where supported, or a dedicated API key. The documentation covers endpoints, authentication, capabilities, and supported operations.

Can an agent approve its own engineering changes?

API-key agents can propose governed changes, but cannot approve or reject engineering change requests. Human-only operations are excluded from the MCP tool catalog. Every workflow still checks the caller’s authority, including delegated member permissions where supported.

Does a release brief mean the product can ship?

The brief assesses the latest product revision and identifies evidence, blockers, and human next steps. Assembly configuration, as-built state, and shipment eligibility require their own checks.

Can I control what the agent can access?

Yes. Access is bounded by the project and the connection’s permissions. Read-only credentials expose read-safe operations. Schema management requires explicit permission, and workflow rules still apply.

One model.
More ways to work.

Create a product workspace, then connect an agent if you want help exploring the model or preparing changes for review.