Hire an AI product behaviour change planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A short question set to learn each user's preferred channel, timing and style
• A step-by-step nudge sequence by day and channel, with one action per message
• Messages for the nudge, the praise and the off-ramp
• A list of what to store about each user, and what not to store
• A check of each message for pressure, guilt and fake urgency
• A small test plan with a measure of success and a stop rule

How it does the job well

• Do not design nudges for children, health or money decisions without a note that a qualified person must review them.
• ❌ No overwhelming task dumps. If a user has 50 items pending, do not show them 50. Show them the 1 most critical item.
• ❌ No tone-deaf interruptions. Respect the user's focus hours and preferred communication channels.
• ✅ Always offer an "opt-out" completion. Provide clear off-ramps (e.g., "Great job! Want to do 5 more minutes, or call it for the day?").
• ✅ Leverage default biases. (e.g., "I've drafted a thank-you reply for this 5-star review. Should I send it, or do you want to edit?").
• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: Users sign up, start a task and drop off before they finish it.

• Preference questions. A short set of questions that learns each user's channel, timing and style, and where each answer is stored.
• Nudge sequence. Messages by day and channel, each with one small action and a draft ready to approve.
• Praise and off-ramps. Short messages that celebrate what was done and let the user stop for today.
• Stop rules. What happens when someone stops replying, and how they can restart.
• Data to store. Each field kept about a user, why it is kept, and what must not be stored.
• Pressure check. Each message checked for guilt, fake urgency or overload, with a fix.

How the work is checked

• Every requirement can be tested.
• Assumptions and risks are listed with how each will be checked.
• Dependencies and owners are named.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Kent Beck and Gary Halbert would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Learn the preferences. It writes a short set of questions for the user's channel, timing, tone and how often they want to hear from you.
• Break the task down. It cuts a long list into the smallest steps a person can finish quickly, and picks the single most important one to show first.
• Choose the nudge. It picks one message, one channel and one time, and drafts the work so the user only has to approve or edit it.
• Celebrate. It writes praise for what was done, such as "5 sent", rather than what is left.
• Offer an off-ramp. It adds a clear choice to do a little more or stop for the day, and pauses the nudges for anyone who stops answering.
• Plan the test. It names the measure, the starting group, the check for opt-outs and the rule for stopping.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id product-behavioral-nudge-engine only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/product-behavioral-nudge-engine/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• What your product does, and the action you want users to take
• Who the users are and where they get stuck now
• The channels you can use, such as email, SMS or in-app, and your quiet hours
• How you measure completion now, and any numbers you have (optional)
• Messages you send today (optional)

Helpful context (optional)

• Your current open and completion numbers for reminders.
• A list of the tasks users must finish, in the order they should happen.
• Your rules on quiet hours and consent.

Tools and access

• Claude, ChatGPT or Gemini with file upload: You can attach your current reminder messages and the plan can rewrite them.
• Your email, SMS or in-app message tool: A person sets up and sends the plan there. The AI only writes and checks it.

Functions and deliverables

• Product behaviour change planner: Get a nudge plan that helps users finish tasks. Each message has one small step, the best timing and an easy way to stop.
  • A short question set to learn each user's preferred channel, timing and style
  • A step-by-step nudge sequence by day and channel, with one action per message
  • Messages for the nudge, the praise and the off-ramp
  • A list of what to store about each user, and what not to store
  • A check of each message for pressure, guilt and fake urgency
  • A small test plan with a measure of success and a stop rule
  Source: Michael Sitarzewski and Agency Agents contributors.
• Process and behavior change planner: Split a messy change into small tidy-up steps and new-behaviour steps, so each one is easy to review and undo. Paste your diff or edit list.
  • Every edit labelled as structure or behaviour, with how easy it is to undo
  • A set of small tidy-up steps and a set of behaviour steps
  • Which tidy-ups help the behaviour change, and which are optional
  • The order, with when to run tests
• Small launch test planner: Plan a small launch test for an offer you doubt will sell. Get a few test places, what to measure and a roll out, change or drop rule.
  • The one question the test answers
  • Four or five test places with a reason for each
  • What to measure and how to record it
  • A roll-out, change or drop rule set before the test
• Small test and rollout planner: Plan a small ad test you can afford to lose. Give it your offer, price and costs. You get the break-even response and a rule to roll out or stop.
  • The sums, each figure sourced or labelled as an assumption
  • The break-even response
  • A test size and the one thing to change
  • A result table and rules for second test, rollout or stop
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Kent Beck: Plan a software change using Kent Beck’s recorded approach. List the cases, take small steps and keep code tidying separate from new behaviour.
  • Your problem worked on the way Kent Beck would: their questions, their method, their push-back
  • The answer or the work, in Kent Beck's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Gary Halbert: Rewrite a sales letter in plain personal language using Gary Halbert’s recorded habits. Make the offer concrete and the next action clear.
  • Your problem worked on the way Gary Halbert would: their questions, their method, their push-back
  • The answer or the work, in Gary Halbert's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Users sign up, start a task and drop off before they finish it.
• Your app sends reminders that people mute or ignore.
• Your team wants a first-week message plan that fits each person's own pace.
• You have a long to-do list for users and want to shrink it to one step at a time.

Limits to check before starting

• You want to understand why users do not come back at all. Use the Habit loop designer first.
• You need a full email series for new customers. Use the New customer onboarding sequence writer.
• You want to run a live test or send messages today. This plans and writes them. A person must approve, send and measure them in your own tools.
• You plan to infer a health condition, such as ADHD, from user data. This agent asks about preferences only. Do not collect or guess medical details.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. Or paste SKILL.md into a new chat, then paste references/source-agent.md after it.
• Write a short brief. Say what the product does, the action users skip, where they drop off, your channels and quiet hours.
• Your AI asks once for anything missing. Anything still unknown is marked as an assumption you can change.
• Read the sequence first. Check that every message has one action and a way to stop. Cut any that sound like pressure.
• Check the list of data to store. Remove anything you do not have consent to collect.
• Run the plan with a small group, using your own sending tool. Compare against the measure it names, and stop if people opt out.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/product-behavioral-nudge-engine for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.