Hire an AI project lessons review planner

Everything it can hand back

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

• A prep plan with a fresh format, a two-list form, numbers to pull and who will hear the lessons
• Themes from the lists with counts, contested items shown side by side and each theme beside your numbers
• A timed agenda with wording rules, facilitator lines, a slot for old hurts and questions for the next project
• Each lesson written as a rule with its root cause, ready to check next time

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 project has just ended, well or badly, and you want the team to learn without blame.

• Step 1: The prep. The reasons to review, a new format, the two-list form, numbers to pull and who hears the lessons.
• Step 2: The themes. Themes from the lists with counts, contested items, numbers beside each theme and what no one can see.
• Step 3: The agenda. A timed agenda with wording rules, facilitator lines, a slot for old hurts and questions for next time.
• Step 4: The rules. Each lesson with its root cause, a rule and how to check it next time.
• 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 Ed Catmull and Ray Dalio would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plans the prep. Picks why you are reviewing, a format that differs from the last one, the two-list form, the numbers to pull and the people who will hear the lessons.
• Sorts the answers. Groups the lists into themes, shows contested items side by side and sets each theme beside your numbers as a question.
• Challenges first conclusions. Asks what in the process, not the result, supports each claim and lists what no one can see.
• Writes a blame-free agenda. Times each theme, has the person closest tell it in the first person, adds wording rules and facilitator lines, and sets a slot for old hurts.
• Turns lessons into rules. Finds the root cause of each problem and writes a rule the next team can check.

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 honest-project-review 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/honest-project-review/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 project, its dates and the people by role
• The format of your last review and any records you keep (optional)
• After the prep, each person's two lists and the numbers
• After the meeting, what was said and decided

Tools and access

• Any good chat AI: Drafting a plan, a form and an invitation is text work any strong chat AI does well with this skill.
• A shared form or document: People can answer the two lists alone and in writing before the meeting.
• Any good chat AI: Grouping and counting free text is work any strong chat AI does well with this skill.
• A shared spreadsheet: The numbers and the themes can sit side by side.
• Any good chat AI: Writing an agenda with clear rules is text work any strong chat AI does well with this skill.
• A visible timer: A timer on the wall keeps each topic to its limit without anyone having to be the bad guy.
• Any good chat AI: Structuring decisions and writing plans is text work any strong chat AI does well with this skill.
• A notes app or document: Gives you one place to keep rules and the dates to check them.

Functions and deliverables

• Project lessons review planner: Share project results and team feedback. Get review preparation, themes, a meeting agenda and lessons from the actual discussion.
  • A prep plan with a fresh format, a two-list form, numbers to pull and who will hear the lessons
  • Themes from the lists with counts, contested items shown side by side and each theme beside your numbers
  • A timed agenda with wording rules, facilitator lines, a slot for old hurts and questions for the next project
  • Each lesson written as a rule with its root cause, ready to check next time
• Project review prep planner: Plan a project review that gets honest answers. Give it a finished project. You get a new format, a two-list form, numbers to pull and who hears the lessons.
  • The reasons for this review and a format that differs from the last one
  • A two-list form and an invitation to send
  • Four to six numbers to pull, each with a definition, a source and an owner
  • Who will hear the lessons, in what form, and the meeting rules
• Team review theme sorter: Sort a team's do-again and never-again lists into themes, with who raised each and what your numbers show. Built for a project review.
  • Five to eight themes with counts on each list
  • Contested themes shown side by side
  • Each theme beside the numbers, written as a question
  • Challenges to first conclusions, and what cannot be seen
  • A neutral list of old hurts and two questions for each top theme
• Blame-free review agenda writer: Turn your project review themes into a timed agenda with no-blame wording rules, a slot for old hurts and questions for next time.
  • A timed agenda that fits your meeting length
  • A first-person owner and a time limit for each theme
  • Wording rules and facilitator lines
  • A ten-minute slot for old hurts, with a rule for replies
  • Three to five questions for the next project, each with an owner
  • A plan for who keeps the record
• Lessons learned principle writer: Turn a mistake into a rule you can check. Give it what happened and your goal. You get the root cause, a rule and a check date.
  • A list of the problems without softening
  • A root cause about a choice or habit
  • A rule with the situation it applies to
  • Two past cases tested, a critic named and a check date
• 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.
• Ed Catmull: Plan feedback or protect rough creative work using Ed Catmull’s recorded approach. Name the problem, keep the creator’s choice and find hidden issues.
  • Your problem worked on the way Ed Catmull would: their questions, their method, their push-back
  • The answer or the work, in Ed Catmull's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Ray Dalio: Review a choice or a mistake using Ray Dalio’s recorded approach. Set the goal, hear other views and draft a rule to test.
  • Your problem worked on the way Ray Dalio would: their questions, their method, their push-back
  • The answer or the work, in Ray Dalio'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

• A project has just ended, well or badly, and you want the team to learn without blame.
• Your last review turned into polite thanks or an argument.
• You want the lessons to reach people who were not on the project.

Limits to check before starting

• Your project is still running: wait until it ends, or hold a short check-in with your team instead.
• You are reviewing your own work alone: write a few notes yourself on what to repeat and what to stop.
• Your project was small and had two or three people: have a short chat, and use only steps 1 and 3.

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".
• Send the form from step 1 and collect the lists and numbers. Bring them to step 2.
• Hold the review using the agenda, then bring what was said and decided to the last step.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/honest-project-review 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.