← Back to Work

AI-assisted workflow design

01 / 08

Designing Human–AI Collaboration for Workflow Creation

Turning a business goal into an editable workflow draft while keeping users in control

At a glance

Challenge Creating a template manually required enterprise users to understand each action first. As Moxo expanded to more businesses, relying on Customer Success for setup would not scale.

Response The team added a natural-language entry point. AI Copilot turns a business description into an editable first draft in the existing Builder canvas, so users can start without asking Customer Success to build the template.

Early signal More than 60 valid prompts arrived in the first six hours. That showed early interest, not long-term use or draft quality.

AI workflow creation concept showing a natural-language request becoming a structured workflow.
A natural-language request becomes a workflow draft that users can inspect and edit.

Context & Challenge

Turning business intent into reliable workflow logic

Moxo was already mature and needed to let more enterprise teams create Workflows on their own, without relying on Customer Success for every setup. The challenge was that Actions, Triggers, roles, and dependencies were hard to configure by intuition. Onboarding and Help Center guidance only went so far.

  1. Users can describe a business goal without knowing how to break it into Workflow logic.
  2. Natural language lowers the entry barrier, but it cannot fill in missing roles, Triggers, inputs, or dependencies.
  3. The team chose to let AI create an editable first draft. Users confirm the key details, then return to the existing Builder to review, edit, and publish.
A user states a business goal, AI identifies the roles, triggers, inputs, and dependencies that need clarification, and then creates a workflow draft.
The design reframed the problem from simplifying configuration to turning a user’s goal into a workflow they can review, edit, and publish.

Research Evidence

Customer Success showed us what AI needed to clarify

The Customer Success team shared the real SOP they use in customer conversations. It starts by clarifying the goal, roles, trigger, required information, order, and dependencies before anyone configures a Workflow.

I mapped that sequence into product behavior. When information was missing, AI asked for details that could change the workflow draft before generation.

This evidence defined what the product needed to clarify. It did not measure adoption, draft quality, or time saved.

Customer Success research evidence showing how clarification informed AI workflow behavior.
Customer Success clarification became the product rule: ask only for missing information that changes the workflow draft.

Design Strategy

Defining how AI and people work together

I compared three ways for AI and users to divide the work. I looked at input cost, handoff, user control, and implementation complexity.

Customer Success brought examples from real setup conversations. I worked with Product to set the boundary for the first release, then reviewed the states and delivery cost of each model with Engineering.

Evaluation criteria

Four questions guided the comparison

These are evaluation criteria, not steps in the user flow.

01

Input cost

How much information must users provide before AI can act?

02

Handoff

Is it clear when AI stops and the user takes over?

03

User control

Can users inspect, change, and approve the result?

04

Complexity

How much new state and engineering work does the model create?

Decision 01

AI generates first; people review and edit afterward

Editing with AI in real time made ownership and state changes hard to follow. A separate AI mode kept the states apart, but forced users to switch modes and cost more to build.

I recommended the AI-first model. AI creates the draft and opens it in the existing Builder. The user can inspect it, edit it, and decide whether to publish.

Three explored Human–AI collaboration models with AI first and human review selected.
The selected model gives AI the first draft and the user the final decision.

Decision 02

Ask key clarification questions instead of generating immediately

I compared three prompting approaches. Direct generation forced AI to guess missing roles and workflow logic. Asking for everything produced a long setup process.

The final approach asks only for information that changes the workflow structure, then moves the user into an editable draft.

Comparison of direct generation, asking every question at once, and the selected approach that asks only what changes the workflow structure.
The final flow asks only for details that affect the draft.

Decision 03

Turn the prompt into an editable workflow, not a conversational answer

I designed the handoff around three stages: describe the goal, fill the gaps that affect the workflow, and review the draft.

The draft opens in the existing Builder. Users can keep editing with familiar controls instead of rebuilding the workflow from scratch.

End-to-end AI workflow flow from prompt to clarification and generated workflow draft.
Prompt, clarification, and draft lead directly into the existing Builder.

Phase I · Launched

Validate one complete creation loop

Start with a prompt, clarify missing structure, generate a draft, and continue editing in Builder.

Validation focus: Can users get a complete, inspectable draft from business intent?

Phase II · Designed

Extend AI to existing actions

Let users request a local change while preserving the rest of the workflow, its order, and its dependencies.

Scope boundary: Designed for the next phase; not presented as a launched result.

Phase I · Launched

From business goal to an editable workflow draft

The existing Canvas already handled manual add, edit, and delete actions. This release added the AI creation entry point and defined the handoff between AI and Actions, while keeping the Canvas structure and manual editing behavior in place. The first release covered one complete path: describe a goal, answer focused questions, and edit the draft in Builder.

Step 01

Describe the business outcome

The user begins in natural language, explaining the process they want to create rather than configuring workflow objects first.

The entry point starts with business intent and a concrete workflow goal.

Step 02

Confirm the information that changes the draft

AI detects missing details and asks focused questions about roles, logic, or integrations before generation.

Focused clarification questions before workflow generation.
Only missing information that affects workflow structure is requested.

Step 03

Review and continue editing in Builder

The generated workflow opens in Builder. Users can check its structure, fix issues, and keep editing with familiar controls.

Generated workflow draft in the Builder interface.
Users review the AI draft, fix what is wrong, and continue in Builder.

Phase II · Designed

Use the same review model for changes to existing workflows

The next phase used the same handoff for existing workflows. AI could prepare a local change, but the user reviewed it before it was applied.

Expansion 01

Change one action without regenerating the workflow

A full regeneration could overwrite structure that users had already confirmed. Action-level AI kept the current workflow context and changed only the target action.

The flow had five steps: request, clarify, modify, review, and confirm.

Action-level AI flow for creating, modifying, reviewing, and removing a workflow action.
Action-level AI preserves the surrounding workflow and asks the user to review each local change.

Expansion 02

Turn repeated interactions into reusable patterns

Actions need different inputs, but they can use the same interaction rules: collect missing details, connect required tools, and confirm roles or business rules.

I ran recurring design reviews to apply these rules to new AI features and document the patterns for the team.

Three reusable AI patterns for missing information, tool connections, and workflow confirmation.
The same rules cover missing information, tool connections, roles, and business logic across different actions.

Expansion 03

Make problems visible and recoverable

Flow Checker showed where a problem occurred, what was missing, and what the user could do next.

The design defined the visible state and available actions for input, confirmation, processing, results, errors, and recovery.

Workflow Builder and Errors and warnings panel showing the recovery path: identify the problem, troubleshoot, and provide missing details.
Issues stay attached to the workflow context so users can understand and fix them without starting again.

Outcome & Measurement

What the launch showed, and what it did not

Phase I shipped the complete prompt-to-draft flow in the existing Builder. Users could begin with a business goal instead of configuring system objects first.

The first six hours after launch showed interest in this entry point. That signal did not prove repeat use, draft quality, or time saved.

60+ valid prompts

in the first six hours after launch.

Phase I launched

the end-to-end prompt-to-draft flow in the existing Builder.

Happiness · Planned

Confidence after generation

Do users understand the draft and feel ready to continue?

Engagement · Confirmed / Planned

Valid prompts and repeat use

Does the early signal continue after the first launch period?

Adoption · Planned

AI-started workflows

How often does AI become the chosen entry point for creation?

Retention · Planned

Repeat workflow creation

Do users return to Copilot for later workflow creation?

Task success · Planned

Drafts completed and published

Can users reach a usable workflow without excessive repair work?

What this did not prove

Prompt volume showed early interest only. We still needed to track repeat use, repair work, completed drafts, and published workflows.

The hard part was defining responsibility

Generating a workflow was only part of the problem. The harder decision was where AI should stop and when the user should take over.

Users needed to see the result, correct it, and continue in familiar tools. Without that, a fast draft would not be trustworthy.

Next Project

Designing a Multi‑role Mobile Workflow Experience

How the mobile app presents different workspace views for Coordinator and Assignee roles

View Project 02 →