Hire an AI client scope change and decision tracker

Everything it can hand back

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

• A scope comparison that sorts the request into in scope, out of scope and unclear, with the clause for each
• What the change does to current work, hours and dates
• Delivery options, each with the cost and date effect your evidence supports
• A draft client reply with open questions
• A record of any decision the client has given, with its source
• A MISSING list, CHECKS MISSED and a short record for the next review

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

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: A client emails "can we also add this?" and you need to see what it does to your signed scope and your hours.

• Changed since last review. Each new request or client reply, with its source and date.
• Scope comparison. Each part of the request marked in scope, out of scope or unclear, with the contract clause that says so.
• Capacity impact. What existing work and hours move if the change is accepted, shown as ranges.
• Delivery options. The ways you could respond, each with the cost and date effect your evidence supports.
• Draft client reply. A short, plain reply with open questions, for you to edit and send.
• Decision status. Whether the change is proposed, accepted or declined, with the quote and date that show it. Unclear replies stay open.

How the work is checked

• Each part of the request is marked in scope, out of scope or unclear, with a clause.
• The capacity impact uses ranges and names the existing work that moves.
• The options show only the cost and date effects the evidence supports.
• Accepted changes carry the client's words and a date. All others are open.
• 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.

Capabilities

• Compare with the last review. Reads the saved record if it belongs to this client and engagement, or sets a first baseline. Lists what changed in the request or in the client's reply. If nothing changed, it says so and stops.
• Read the contract. Finds the deliverables, exclusions, change process, fee and notice clauses in the signed engagement and quotes each with its clause number. It does not interpret them.
• Check the hours. Sets the request against real commitments, skills and available hours, with ranges and not single guesses. It shows what moves if you say yes.
• Draft options and a client brief. Writes the options with the cost and date effects the evidence supports, plus open questions and approval status.
• Record the client's decision. If the client's reply clearly accepts or declines, it records the commitment and its source with the Executive action register keeper. If the reply is unclear, the old commitments stay and the open decision is listed.

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 client-scope-decision-review-assistant 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/client-scope-decision-review-assistant/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

• The signed engagement or statement of work, with its date
• The client's change request, as they wrote it
• Your current commitments and each team member's available hours
• Effort evidence for the change, such as past similar jobs or a range estimate
• Your approval rules, such as who may accept a change and any price limit
• Your last review and the client's reply, if there is one (optional)

Helpful context (optional)

• The signed engagement, not a draft.
• The client's own words for the request and for the reply.
• A named person who may approve a change.

Tools and access

• A capable chat AI with file support: Reads the contract and emails together, and can save the record file. In plain chat it returns the same tables as text.
• A chat AI that reads files: It can quote the contract by clause, so the comparison rests on the document and not on memory.
• Your time tracking or project tool: Past hours on similar work make effort estimates something you can support.

Functions and deliverables

• Client scope change and decision tracker: Compare a client change request with the signed scope. Get delivery options and a draft reply, with new work kept as proposed until the client accepts.
  • A scope comparison that sorts the request into in scope, out of scope and unclear, with the clause for each
  • What the change does to current work, hours and dates
  • Delivery options, each with the cost and date effect your evidence supports
  • A draft client reply with open questions
  • A record of any decision the client has given, with its source
  • A MISSING list, CHECKS MISSED and a short record for the next review
• Client scope change planner: Share the signed scope, change request and available hours. Get a scope comparison, delivery options and a client decision draft.
  • A scope comparison: original scope against the requested change, with clause references
  • The effect on your team's hours and on work already promised
  • Two or three delivery options, each with cost and date effects you can support
  • A draft decision brief for the client, with open questions and approval status
  • A list of what you could not verify, such as a missing clause
• Action item tracker: Share meeting notes or email threads. Get action items with owners, deadlines and unresolved commitments.
  • action-register.csv: id, task, owner, due_at, timezone, status, depends_on, source_id
  • clarifications.md
  • proposed-task-changes.md
• Client communication planner: Share how you work with clients. Get clear channels, update dates and a record for decisions and approvals.
  • A client table with one main channel, document home and update day per client
  • An update calendar for weekly, monthly and quarterly check-ins
  • A decision log format with its fields
  • Named sign-off roles and a backup for each
  • An escalation path for delays, risks and client staff changes
  Source: erphq.
• 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.

Tasks you can use it for

• A client emails "can we also add this?" and you need to see what it does to your signed scope and your hours.
• A client replies to your options, and you need to know if that counts as a clear yes.
• Your team is full, and you must show what existing work moves if the change goes ahead.
• You review a change request every few weeks and want each one compared with the last review.

Limits to check before starting

• The work is a construction or building contract. Use the Construction variation cost and approval tracker.
• You want a risk review of contract clauses for a lawyer. Use the Contract clause risk reviewer.
• You only want to reprice a client by their hours and fees. Use the Client fee and work-hour reviewer.
• You are writing the first change request form and nothing is in dispute. Use the Change request writer.
• You want the AI to send the reply or decide what is in scope. It drafts, and a person decides.

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 agent pack and add it to Claude, ChatGPT or Gemini. Add these five pieces from the pack: Prepare a client scope change brief, Plain-words contract summary, Team capacity planner, Stakeholder update writer and Executive action register keeper. If one is missing, stop and ask for it.
• Say if this is a first run. If not, paste your last review and its record.
• Attach the signed engagement, the change request, your commitments and the available hours. Write your approval rules in two or three lines.
• Read the scope comparison first. Check each clause it quotes against the contract.
• Pick an option with the person who can approve it. Edit the draft reply yourself before you send it.
• When the client answers, paste the reply and run it again. The agent sends nothing.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/client-scope-decision-review-assistant 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.