AI Blocks › Think it through and decide
Lessons learned principle writer
Describe a mistake and what happened. Get the root cause and a rule you can check next time.
Lessons learned principle writer is a free AI skill for the job "Think it through and decide". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · Made by AI Blocks · Level: beginner
What it does
Most people learn from a mistake once, in the moment, then forget. The same error returns because the lesson was a feeling, not a rule. And the lesson is often about the outcome ("that went badly") and not the choice that led to it. This skill puts the mistake against the goal it blocked, lists the problems without softening them, and traces back to a root cause: what in your own choices, habits or traits made it likely. It writes the lesson as a rule with the situation it applies to, tests the rule against two past cases and names the person whose criticism of it would count most. It sets a date to check the rule against the next result. It blames no named person.
You give it
- What happened, in plain order
- The goal it got in the way of
- Two or three past cases that look similar (optional)
- Who knows the area best (optional)
You get
- 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
Use it when
- A launch, hire or campaign went wrong and you want to avoid repeating it.
- The same kind of mistake has happened twice.
- You want a team habit of writing down what was learned.
How to use it
- Start a chat with the skill. Open it if you added it to your AI, or copy it and paste it in.
- Write what happened and what you were trying to do. Be plain.
- Add any older cases that feel the same.
- Read the root cause. If it only blames bad luck, ask for another pass.
- Save the rule in your lessons file and check it on the date given.
Workflows that use it
- Run a project review where people tell the truth
- Decision review tracker
- Experiment results review agent
- Monthly lost deal reviewer