Hire an AI annual letter and results reviewer

Everything it can hand back

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

• A list of up to eight promises, each with its cost
• Three to six input metrics with owners, targets and a proxy test
• Free cash flow beside earnings, a payback test and a score out of 100
• A value tally for each group and your weakest link
• A letter of 700 to 1,200 words

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.
• Treating a template as legal advice.

What a good result looks like

An example, not your task: You write a year-end letter to your team, partners or owners.

• Principles. A short list of promises on how you will choose when short and long term pull apart, each with its cost.
• Input metrics. Three to six numbers you control, each with an owner, a target and a proxy test, plus one output kept as a check.
• Cash view. Free cash flow beside earnings, what growth costs, and a score out of 100.
• Value tally. A value estimate for each group you serve, with assumptions in view and the group you serve least well.
• Letter. A draft of 700 to 1,200 words that puts the bad news first and says what you will stop.
• Hand-back summary. Each step's file, any step not run, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed 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 Jeff Bezos and Abraham Lincoln would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Write the long-term principles. Finds where short and long term pull apart and writes one plain promise for each, with the cost it names.
• Pick the input metrics that matter. Traces your results to the inputs you control and picks three to six. Tests each for proxy risk and keeps one output as a check.
• Check the cash behind the earnings. Works out free cash flow, sets it beside earnings and tests whether growth pays back. Gives a score out of 100.
• Tally the value you create. Builds a cautious estimate for owners, staff, partners and customers with assumptions in view. Names the group you serve least well.
• Write the letter. Opens with the result and the bad news, restates the promises, shows metrics, cash and value, owns the mistakes and says what you will stop.

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 annual-letter 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/annual-letter/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

• Your business, who the letter is for and the hard trade-offs you face
• Your reported numbers by year, with earnings, depreciation, working capital and capital spending
• Share or owner counts, and figures for staff, partners and customers (optional)
• The year's mistakes

Helpful context (optional)

• The cash flow statement
• Customer survey results
• Pay and benefits totals
• Last year's letter

Tools and access

• Any good chat AI: Holds the principles, metrics and results across the steps.
• A spreadsheet: Check the cash and value sums before they go in the letter.
• Any good chat AI: Turning trade-offs into plain promises is text work any strong chat AI does well with this skill.
• Any good chat AI: Tracing causes from a table of results is text and number work any strong chat AI does well with this skill.
• Any good chat AI: Doing linked sums on a few years of figures is work any strong chat AI does well with this skill, if you check the arithmetic.
• Any good chat AI: Building cautious estimates with stated assumptions is text and number work any strong chat AI does well with this skill.
• Any good chat AI: Joining several inputs into one clear letter is text work any strong chat AI does well with this skill.

Functions and deliverables

• Annual letter and results reviewer: Review the year's results and cash. Draft an annual letter with long-term goals and useful measures.
  • A list of up to eight promises, each with its cost
  • Three to six input metrics with owners, targets and a proxy test
  • Free cash flow beside earnings, a payback test and a score out of 100
  • A value tally for each group and your weakest link
  • A letter of 700 to 1,200 words
• Long-term business principles writer: Describe your business and its hard trade-offs. Get a short list of plain promises on how you will choose.
  • Up to eight promises, each starting with what you will do
  • A cost line under every promise, including the one on explaining your reasoning
  • A check that seven areas are covered: customers, time, measures, failure, cash, people and sharing reasons
  • A list of promises dropped because you would not keep them in a bad year
  • A closing line that this is your way, not the only right way
• Business activity metric planner: Pick input metrics you control from the numbers you report. Get three to six inputs, a proxy test for each and one output to check them.
  • Outputs listed and traced to inputs
  • Three to six input metrics that touch the customer
  • A proxy test for each, with a guard where needed
  • One output kept as a check
  • An owner, target and review date for each input
• Cash versus earnings checker: Share profit, cash spending and share counts for three or more years. Get free cash flow and a score for how well cash backs earnings.
  • Free cash flow for each year
  • Free cash flow beside earnings
  • A payback test on growth spending
  • A cash per share or per owner view
  • A score out of 100 and what it means
• Stakeholder value calculator: Build a cautious value created tally for owners, staff, partners and customers. Each figure shows its assumption, and you see who you serve least.
  • One bottom-line figure per group
  • The assumption beside each
  • A customer estimate on one measure
  • A total and the weakest estimate
  • The group you serve least well and one change
• Annual letter writer: Write an annual letter to your team or owners from your results. It puts the bad news first, owns mistakes, and says what you will do and stop.
  • A letter of 700 to 1,200 words
  • The result and bad news first
  • Promises, metrics, cash and value in one story
  • Mistakes with cost and change
  • What you will do and stop next year
• 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
• Jeff Bezos: Review a product or stuck decision through Jeff Bezos’s recorded approach. Start with the customer, test what can be undone and write the reasoning.
  • Your problem worked on the way Jeff Bezos would: their questions, their method, their push-back
  • The answer or the work, in Jeff Bezos's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Abraham Lincoln: Work through team conflict, hard choices and plain speeches using Abraham Lincoln’s recorded approach. Start with facts and a shared goal.
  • Your problem worked on the way Abraham Lincoln would: their questions, their method, their push-back
  • The answer or the work, in Abraham Lincoln'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 write a year-end letter to your team, partners or owners.
• You have results and metrics but no story that joins them.
• You want to tell the bad news in a way people trust.

Limits to check before starting

• You need a monthly update or a one-project report: write a short status note yourself instead.
• You only want to check whether profit is backed by cash: use the Cash versus earnings checker.
• You already have your principles and only need the letter: use the Annual letter writer.

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's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your business, your numbers and the year's mistakes. It works step by step and saves each result.
• Read the metric plan and the weak numbers before the letter is written. Fix any that are too generous.
• Send the draft to two readers before it goes 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/annual-letter 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.