Hire an AI task handover and risk planner

Everything it can hand back

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

• A task list with the ones AI takes, the ones it assists and the ones that stay with people
• For each task AI takes, what it quietly does and a call to cut, keep or replace it
• A card for each handoff with what the step needs, returns and must never lose
• A list of ways the plan could fail, with a change for each

How it does the job well

• Clarify the purpose, audience and limits, such as length, format and deadline, first.
• Use the user's materials and voice. Ask for samples when tone matters.
• Be specific and concrete. Cut what does not serve the purpose.
• Say what you are unsure of and where to check it.

Mistakes it avoids

• Generic output that ignores the user's details.
• Inventing facts, quotes or sources.
• Long answers when a short one was asked for.

What a good result looks like

An example, not your task: You want AI to take work off a role, such as support, reporting or admin.

• Step 1: Tasks. Each task marked as draining, tiring or risky, and whether AI takes it, assists or people keep it.
• Step 2: Hidden value. What each task quietly does, who gains, what breaks without it, and a call to cut, keep or replace.
• Step 3: Handoffs. A card per step with what it needs, returns and must never lose, plus retry and limit rules.
• Step 4: Failure check. Ways the plan could fail, whether each is covered or exposed, and a change for each gap.
• Hand-back summary. Each step's file, any step not run, and every MISSING line in one list.

How the work is checked

• Step 1 marks every task as AI takes, AI assists or people keep. Step 2 gives each AI task a cut, keep or replace call. Step 3 has a card for every step that stays. Step 4 gives a change for each failure it finds. If one is missing, the run stopped at that step and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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 Fei-Fei Li and Charlie Munger would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Break the job into tasks. Splits a normal week into tasks, marks the ones that drain, tire or endanger people, and picks what AI takes, what it assists and what stays with people.
• Check what each task quietly does. Names each task's stated job, lists what it does unseen, asks who gains and what breaks without it, and calls it cut, keep or replace.
• Plan the handoffs. Writes a card for each step with what it needs, returns and must never lose, locks key facts so they travel whole, and sets rules for retries and limits.
• Try to break the plan. Lists what would guarantee failure, checks the plan against each one, puts anything that could end it first and writes a change for each gap.

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 hand-tasks-to-ai-without-losing-what-the-job-quietly-does 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/hand-tasks-to-ai-without-losing-what-the-job-quietly-does/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 job, who does it and a typical week
• Which tasks people dislike or find tiring
• What AI tools you can use (optional)
• Anything the job must never get wrong (optional)

Tools and access

• Any good chat AI: Sorting tasks and listing risks is text work any strong chat AI does.
• A short survey form: Asking the people who do the job is the best source of which tasks drain them.
• Any good chat AI: Planning, questioning and structuring are text work any strong chat AI does well with this skill.
• Claude Code: Can run the chain as files and code, save every step's request and reply, and do the counts in code.
• Claude: Follows long handoff cards closely and returns work in the fixed shape you ask for.
• Any good chat AI: Listing and testing failure modes is text reasoning that any strong chat AI handles with this skill.
• A spreadsheet: Handy for putting numbers on dependencies, cash and runway.

Functions and deliverables

• AI task handover and risk planner: Describe a role and its tasks. Get AI task options, hidden human duties, handoff notes and a failure-risk review.
  • A task list with the ones AI takes, the ones it assists and the ones that stay with people
  • For each task AI takes, what it quietly does and a call to cut, keep or replace it
  • A card for each handoff with what the step needs, returns and must never lose
  • A list of ways the plan could fail, with a change for each
• AI task opportunity reviewer: Break a job into tasks and find which ones drain or endanger people. See where AI can take the load in a role breakdown, with a person in charge.
  • The role broken into tasks, each marked for drain, tiredness or risk
  • The tasks where AI can take the load, and the human work it leaves
  • A named person in charge of each decision, and the risks to check
  • How to test it with the people who do the job
• Task removal impact reviewer: Share a task or rule you want to remove. Check what else it may do, who benefits and what a replacement would need.
  • The job in its simplest form
  • A list of hidden parts, each with who gains
  • What would break if it went, and an estimated cost
  • A decision: cut, keep or replace
• AI creative workflow handoff planner: List the steps in your creative AI workflow. Get clear instructions for passing facts and results between them, with claim limits kept intact.
  • Claim cards, each with its full wording, limits and source
  • A handoff card for each step (needs, may use, returns, never lose)
  • A bundle order (stable part first, then the part that changes) and run rules
  • A list of shortfalls and trade-offs
  • Any of its own checks the plan still misses, each named
• Plan failure reviewer: Find the ways your plan could fail before you commit. Paste your plan and goal, and get ranked failure risks with a fix for each.
  • The goal in one line
  • A list of failure modes specific to your plan, survival risks first
  • A change to the plan for each failure
  • The bet stated, and a set of attacks for the people you pick to argue against it
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Fei-Fei Li: Review an AI plan, dataset or test using Fei-Fei Li’s public approach. Start with affected people, check the examples and keep human judgement involved.
  • Your problem worked on the way Fei-Fei Li would: their questions, their method, their push-back
  • The answer or the work, in Fei-Fei Li's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Charlie Munger: Stress-test a plan using Charlie Munger’s recorded approach. Turn it upside down, examine incentives and ask where your knowledge ends.
  • Your problem worked on the way Charlie Munger would: their questions, their method, their push-back
  • The answer or the work, in Charlie Munger'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

• You want AI to take work off a role, such as support, reporting or admin.
• You are about to automate a task and have a feeling it does more than it seems.
• You are setting up several AI steps and want to know where a fact could get lost.

Limits to check before starting

• You want to automate a task nobody depends on: just hand it to your AI and skip the checks.
• You need to split one big problem into smaller parts, not a job into tasks: use the Big problem splitter.
• You want to rank which choices to make first: use the Decision priority planner.

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 handoff pack. It holds HANDOFF.md plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md". Claude Code and Claude Projects may need a paid Claude plan. Without them, paste each skill file into a chat in order and run one step at a time.
• Describe the job and a normal week. Ask two or three of the people who do it which tasks they dislike.
• Read the hidden-value step before you automate anything. Keep or replace whatever it flags.
• Run one small task first, and check the failure list before you add more.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/hand-tasks-to-ai-without-losing-what-the-job-quietly-does 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.