Use Invent

Invent is a forward deployed AI Agent built into Relevance AI. You say how the work should run, and Invent builds and manages the Agent team that does it. It works across your entire project rather than inside any one Agent or Tool, so it can create, edit, and understand almost anything in the platform. The Invent panel showing its greeting, suggested actions, and the message composer

The Invent panel showing its greeting, suggested actions, and the message composer

What can Invent do?

Each area below is something Invent can reach directly. In all of them it acts with your own permissions, inside the project you have open.

Agents

Invent builds and runs your Agents end to end.

Create, update, publish, and delete an Agent
Read, search, and edit its system prompt
Attach and detach the Tools it can use
Trigger a run and poll the result
Read a task's summary, messages, and metadata
Cancel a running task

Tools

Invent assembles Tools a step at a time, or starts from one that already exists.

Create, update, publish, delete, and bulk delete Tools
Add, update, reorder, and remove steps
Set what the Tool returns
Trigger a run, poll the result, and cancel one mid-flight
Read the latest run or look back through previous runs
Search and clone public Tools and Marketplace listings
Browse the Tool step library, check what a step needs, and build a Tool from one

Workforces

Invent wires Agents into a Workforce and runs it.

Create, update, publish, and delete a Workforce
Turn its Trigger on or off
Trigger a run and poll the result
Read a task's messages and metadata
Cancel a running task

Knowledge

Invent manages the Knowledge tables your Agents read from.

Create, update, and delete Knowledge tables
Add, update, and delete rows
Read a whole table or a single row
Export the contents

Triggers

Invent sets up what starts an Agent without you.

List the Triggers already on an Agent
Create a Trigger
Enable or disable one
Delete one

Evals and performance

Invent can build the whole quality setup, run it, and watch it.

Build and maintain the reusable Checks library
Create scenarios, and attach or detach Checks on them
Configure how a scenario is simulated
Group scenarios into test sets
Run an evaluation, poll it, and cancel or delete a run
Read run summaries and individual test results
Create Performance dashboards and attach Checks to them
Read a dashboard's time series and its run history
Create, update, and delete alarms
Configure the pre-publish check and poll its status

Version control

Agents, Tools, and Workforces all keep a version history, and Invent can move through it. It asks before restoring, and the live published version stays untouched until you publish.

List the versions of an Agent, Tool, or Workforce
Read any single version
Rename a version
Restore an earlier version into the current draft

Analytics and monitoring

Invent reads the same numbers you do when something looks wrong.

Pull a scorecard for an Agent, Tool, or Workforce
Read the error records behind a problem
Chart usage over time, or break it down by resource
Chart Agent activity over time
Read the current task counts, including what is waiting for review, escalated, or errored
List the tasks themselves

Integrations and MCP

Invent uses what you have already connected; authenticating an account stays yours to do.

See which accounts are connected and which providers are available
Check whether a Tool has the integrations it needs
Check whether an API key is available
List the Slack channels it can post to
List your project's MCP servers and the Tools they expose, and call them

Working with you

Invent works in the open rather than silently.

Ask you questions before it builds
Read a plan back and confirm it with you
Spawn subagents to work in parallel
Read, write, edit, list, and delete the files in a conversation

Project setup

Invent keeps the project around the work tidy.

Read your project's details
Create, rename, and delete folders
List the LLM models available to you
Set and clear task priority on a resource
File a bug report to the Relevance AI engineering team

Where to find Invent

The Invent entry points on the Relevance AI home page

Left sidebar: Click Invent under Build.
Home page: Click Build with Invent.
Floating button: Click the floating button to open the Invent panel from any page in your project.

Access controls

Availability

Invent is available to organization admins by default. An organization admin can turn on Invent for everyone in an individual project from that project's settings.

Approval controls

Session approvals
Tool permissions

The Ask first and Auto-accept options in the Invent message composer

Use the approval control beside the message composer to set how Invent handles tool approvals for the current session:

Ask first pauses before tools set to Ask or Always ask run. Tools set to Auto still run without approval.
Auto-accept lets tools set to Ask run without approval. Tools set to Always ask still require your approval.

Invent Permissions settings showing approval controls for individual tools

Tool permissions save how Invent should handle each action for you in the current project. Set an entire category at once or choose a different setting for an individual tool.

Setting	What it means
Auto	Runs without asking.
Ask	Requests approval unless Auto-accept is on for the session.
Always ask	Requests approval every time, even when Auto-accept is on.

Run actions default to Auto, create and edit actions to Ask, and destructive actions such as deleting or publishing to Always ask. Setting a destructive action to Auto allows Invent to perform it without another tool-approval prompt.

Open Invent settings

In the Invent panel, click the three-dot menu, then select Invent settings.

Open Permissions

Select Permissions, configure categories or individual tools, then click Save.

These settings control approval prompts, not access. Invent still uses your existing project, asset, and integration permissions. Each user manages their own preferences in each project; organization and project admins cannot use this screen to grant access or set approval rules for other users.

Enterprise security controls

Project isolation

Invent's access to Relevance AI is scoped to the active project at the API-key and fine-grained authorization layers, not only in the interface. Each internal platform request uses the active project ID and the caller's API key, then passes through the standard authorization checks. Enabling Invent in a sandbox project does not grant it access to assets in a production project.

Integration reach

Within the active project, Invent can use connected integrations such as Salesforce or Gmail with credentials available to that project. The project is the access boundary, so connect only sandbox credentials if the project must remain isolated from production data.

Data egress

Conversation content is sent to the selected LLM provider to generate responses. Web search is off by default and used only when enabled for a message. Voice is feature-gated and off by default. Memory is off unless the user enables it. Audit data and operational metrics stay within Relevance AI unless the organization has configured enterprise event streaming to a customer-controlled destination.

How to use Invent

Invent is expensive to run and consumes significant credits. Use it deliberately and keep an eye on your usage.

Invent features

Set up and use Invent
Manage performance

Start a task

The Invent start menu with suggested prompts and the message composer

Describe a process you know end to end, including the outcome, systems, judgment calls, and measure of success. Invent works through it with you before building the Agent team.You can also choose a task suggested from your project setup, such as creating evals if none exist.

About you

About You tells Invent who you are so it tailors every response to your role and work from the first message — no re-explaining your context each session. It shapes how Invent talks to you and what it assumes about your work, but it doesn't change Invent's role or hardcode any Tool configuration.It adjusts the level of technical detail, makes domain-aware assumptions, and lets Invent address you by name at natural moments.To set it up:

Open Invent settings

In the Invent panel, click the three-dot menu, then select Invent settings.

Open General

Select General, enter your details under About You, then click Save.

Model selection and credit usage

Model selection

The model dropdown sets which large language model (LLM) powers your Invent session.The dollar signs show each model's relative credit cost. Labels such as Fast, Balanced, Powerful, and Thorough summarize the trade-off between speed, cost, and capability. The icons beside each model show whether it can work with images and file attachments.Your plan determines the default model. You can switch models at any time from the dropdown in the Invent panel.

Credit usage

The counter beside the model selector shows the credits used in your current session and updates with each interaction.

Task status and history

Invent task history showing approve, idle, and other statuses

Past sessions in your conversation history show each task with a status: approved (the action was applied), idle (waiting for your input), or completed. You can review what Invent did and track credit spend across sessions from the history view.

Memories

When Memory is enabled, Invent can save and recall details you want it to remember across conversations, such as naming conventions, preferred models, workflows, and recurring constraints.To view, search, edit, or delete your memories:

Open Invent settings

In the Invent panel, click the three-dot menu, then select Invent settings.

Open Memory

Select Memory, manage your memory settings, then click Save.

Deleting a memory removes it permanently. Invent will re-learn that information if it comes up again in future conversations.

Bug reporting

When Invent hits a platform issue it can't fix, it logs a bug to the Relevance AI engineering team on your behalf. These reports go directly to engineering rather than support, so you won't receive progress updates.

Invent's job continues after launch. It watches live performance, spots where quality slips, and proposes improvements it has already tested.

Scheduled check-ins

Before setting up a scheduled check-in, add an email or Slack notification channel in Alerts so Invent can notify you about the result.

Schedule a check-in

Tell Invent what to review and when. It can suggest an interval based on the Agent's activity.

What happens when a check-in runs

Invent reviews evals, errors, and recent activity. If it finds an issue, it sends a summary and suggested fix. If everything looks healthy, it stays quiet.

Alerts

Add at least one email address or Slack channel so Invent can notify you when a scheduled check-in finds something.

Open Invent settings

In the Invent panel, click the three-dot menu, then select Invent settings.

Open Alerts

Select Alerts, add an email address or Slack channel, then click Save.

Restore a version

Ask Invent to roll an asset back to an earlier version — for example, "Restore the previous version of this tool". Invent copies that version into the current draft, leaving the live published version unchanged until you publish. This restores an earlier version of an existing asset; it doesn't recover one that's been deleted.Invent always asks you to confirm before restoring, and appends (restored) to the version name so the restored state is easy to identify later. For a full guide to version history — including how to restore and rename versions from the builder UI, and how retention works — see Version history.

Manage Evals with Invent

Invent can build an initial Evals suite, review results, investigate failed Checks, and diagnose performance alarms for Agents and Workforces.

Learn more about Evals

Learn how to create scenarios and reusable Checks, run evaluations, and monitor live performance.

Create Evals
Review performance
Fix failing Evals
Configure an alarm

Invent can turn an Agent or Workforce's real usage into a starting Evals suite, including a test set, scenarios, and reusable Checks.

Start from your Agent or Workforce

On the Run page, select Create with Invent from the testing banner. If a recent Agent task is available, you can instead select Automate testing beside it so Invent uses that run as the example.

Describe what success looks like

Add any outcomes, edge cases, or requirements that the Evals should cover. A representative task gives Invent useful context about the inputs, expected behavior, and tools involved.

Review and run the Evals

Invent creates the Evals setup and runs the test. Open Evaluate → Runs to review the score and see which Checks passed or failed.

Start with a task that represents normal production use, then ask Invent to add edge cases once the baseline Evals are working.

MCP vs Invent

Invent and the Relevance AI MCP are often compared, but they solve different problems. Invent builds things inside Relevance AI from natural language. The MCP connects Relevance AI to the outside world — letting external clients call your Tools, and letting your Agents reach into external services.

Invent

A forward deployed agent inside Relevance AI. Describe the process you want to run and it builds or edits Agents, Tools, and Workforces for you, landing changes in draft for review.Reach for it when you want to build, edit, or debug something inside Relevance AI by describing the outcome.

Relevance AI MCP

A bridge to other tools. Call your existing Relevance AI tools from external clients like Cursor or Claude with the MCP Server, or let your Agents call services like Notion and Linear with the MCP Client.Reach for it when the Tool already exists and you want to run it from Cursor or Claude, or let an Agent call an outside service.

The two are complementary, not competing. Invent uses the same MCP tool surface under the hood — so a common pattern is to build your Agents and Tools with Invent, then call them from Cursor or Claude through the MCP in your day-to-day work.

Frequently asked questions (FAQs)

How do I get started with Invent?

Choose a process you know well and can explain from beginning to end. Tell Invent the outcome you need, the systems involved, the decisions that require judgment, and how you measure success. Invent will work through the process with you before it builds the Agent team.

Who can use Invent?

Invent is available to organization admins by default. An organization admin can turn on Invent for everyone in an individual project from that project's settings.

How does project isolation work for Enterprise customers?

Which integrations can Invent access in an Enterprise project?

Where can Enterprise Invent data be sent?

Does Invent publish changes automatically?

By default, Invent makes changes in draft so you can review them before they go live. Auto-accept lets Invent apply changes without pausing for each approval, but restoring an earlier version always requires confirmation.

Can I resume a previous Invent conversation?

Yes. Invent saves conversations as sessions automatically. Open the Chats dropdown in the Invent panel to browse or search previous sessions and continue where you left off.

How does Invent track credit usage?

The Invent panel displays a real-time credit counter that updates with each interaction. The counter tracks the credits used in your current session.

Overview

Invent

Agents

Tools

Workforce

Knowledge

What can Invent do?

Where to find Invent