maxinja

maxinja turns your marketing direction into work inside maxclicks. Give it a campaign or journey brief; its specialist agents build the audience, email or workflow and report what they saved. You can inspect the result, refine the brief and decide when to send or publish.

The same approach applies to segment conditions, evaluated fields, workflow logic and Adaptyle instructions: describe the intended behavior and review what it produces. These capabilities use generated logic rather than a manual query editor.

What you can ask it to build

For ongoing campaign work, the chat coordinates three kinds of deliverable. A follow-up can refine the same saved work:

Ask for	What it sets up
A template	The email itself: subject, content, sender, and a rendered preview you can look at.
A broadcast	Its name, the contact schema, the audience, the email, and the schedule.
A workflow	The steps, the connections between them, the configuration inside each step, and publishing it when you ask.

Use the dedicated segment, evaluated attribute and webhook controls to generate their conditions. Schemas and forms have their own setup screens. Initial onboarding also offers agent assistance with the data model and CSV mapping while setup is incomplete; that is separate from the ongoing campaign-building chat.

Use maxinja to investigate before you brief a campaign. Ask "Which customers have at least two orders but none in the last 60 days?" and it can query your workspace and report the result. These data queries are read-only. A workflow it builds can separately create or update records when that workflow runs. Product questions use the built-in reference manual.

Define behavior signals with Tracks and Traits

maxinja also has typed tools for listing and saving Track and Trait definitions. A Track describes typed activity independently of a business event schema. A Trait calculates a reusable measure from exactly one Track or business event source. The catalog tools can queue a refresh and inspect published values.

Track catalog definitions and the Collected event definitions configured in the Events UI are related but distinct contracts. The chat's Track tool does not create source write keys or define the collected event's nested Properties and Context schemas. Use the Events setup controls for that collection contract.

Give the subject, source activity, time window and calculation you mean: “For each contact, count qualifying product activity in the last 30 days; show me the current values before I use it in a journey.” A refresh is queued asynchronously; a preview reads committed values and does not prove the new calculation has finished. Check the publication status and data window. Use the computed attributes reference to understand refresh timing and missing data. A workflow’s threshold behavior belongs in its trigger configuration.

Where you talk to it

The chat pane. Click the maxinja button beside your work to open it, and describe what you want. The conversation stays with you as you move around the app, so one chat can go from a broadcast to the workflow that follows it. See working with the assistant.

Next to a field that needs logic. Examples include a segment, an Evaluated on demand attribute under Settings → Schemas → Attributes, and a webhook condition under Settings → Developers → Webhooks. You describe what you want, maxinja generates it, and you get back a readable description of the rule (plus, for a segment, how many contacts match). A second box under it takes your refinements.

On a workflow step. The step panel opens with a box for describing what the step should do. What you type there goes to the chat with that step already attached.

Inside an email. The editor’s maxinja input follows the selected subject, block or panel and edits the saved draft. Adaptyle instructions stay in that draft and run later when recipient content is rendered.

Describe the outcome, not the data

Start with the customer and the decision. maxinja can use your workspace definitions and query supplied records, but the source data must exist. Include facts that are absent from the workspace, and use @ to identify an existing campaign, segment or brand kit.

A useful campaign brief includes:

Audience: the customer behavior, time window and exclusions.
Message: the reason to act, offer and desired call to action.
Fixed facts: prices, dates, required wording and destination links.
Scope: whether you want a draft, a scheduled send or a published workflow.

Create a draft broadcast for customers with at least two orders and none in the last 14 days. Introduce the supplied new coffee using their purchase history. Keep the price and product link fixed. Use our published brand kit and leave the campaign unscheduled.

Inspect the matching contacts, sender, template and several recipient previews. A completion message describes the saved work; it does not establish that email has been delivered.

Audiences nothing else can express

A broadcast's audience picker offers every contact in a schema, or one saved segment. Anything narrower than that (bought twice, not in the last 60 days, excluding anyone who already got the September email) has to be asked for in the chat, where maxinja writes the filter for that one broadcast.

If you want to reuse the same audience later, ask for a segment instead: New segment on the audience screen, or the Segments page.

What it costs

AI requests use credits. On Premium, your available seat credits are used first for your actions, then the workspace wallet. Usage depends on the model, the amount of context and the work required; a campaign brief does not have a fixed generation price.

Separate building from execution when planning usage. An Adaptyle email invokes AI for each recipient whose personalized content is rendered. Previews and regenerations also use credits. A workflow step that calls a model adds usage on each run.

There is no fixed total quote for an assistant brief. The exchange operation and actual model/tool work can add charges, including delegated work, sample generation and images. Usage already incurred remains when work is stopped or fails. Inspect itemized charges under Settings → Billing → Usage. The email editor separately provides an estimate for recipient rendering and campaign sending.

The model it runs on, and where it assists

Settings, maxinja, in the General tab sets the model every new chat starts on, and the one the AI actions across the app use. A single chat can switch for itself: the gear icon in the message box opens AI settings for this session. The active exchange keeps the model and MCP selection it started with; changing session settings does not replace that running selection. Choose a model that supports the conversation’s attachments and required tools. Existing images and PDFs still matter when you switch models; maxinja does not silently replace an unsupported selection.

Runtime AI has its own settings. AI-calling workflow steps and email templates with Adaptyle instructions each require their own model and thinking settings. Those settings determine execution behavior and do not follow a later change to the workspace default.

The same tab carries Editor autocomplete. On Automatic, maxinja finishes the Liquid expression you are typing in the email editor, showing the rest of it as faded text you accept with Tab, and each suggestion is a small AI call against your credits. Off turns off both the suggestions and their cost, and you write Liquid by hand. The choice covers everyone in the space.

The MCP servers tab lists the MCP servers registered for the space. Register one and maxinja can call your own tools in a conversation. Both tabs are admin-only.

What it will not do

Workspace conversations require write access. The server checks access when a conversation starts, accepts a command and executes work. Read-only access alone does not authorize a maxinja run.
It can carry out a requested publication or send without another assistant approval stage. Product validation and execution gates still apply. See while maxinja works.
It is only in the app. maxinja is not part of the Public API, so nothing outside maxclicks can start a conversation with it.

While maxinja works: what happens after you hit send.
Working with the assistant: the chat pane itself.
Adaptyle: personalizing an email per recipient.
Segments and evaluated attributes: the two things you always describe rather than build.
Billing: credits and what they buy.