{
 "schema": "aiblocks-page/1",
 "id": "self-reflection-grading-past-predictions-implementation-planner",
 "type": "skill",
 "name": "Agent prediction log builder",
 "summary": "Grade your AI agent's past predictions against what happened. Get a score log, a likely cause for each miss and lessons to review. Draft only.",
 "headline": "Agent prediction log builder",
 "subhead": "Give it the predictions your AI agent saved, what really happened and your grading rule. It scores each one with set math, tells a wrong read from a wrong action, and drafts lessons for a person to review. Nothing is run or changed.",
 "job": {
  "id": "build-software",
  "name": "Build and ship software"
 },
 "level": "intermediate",
 "thinking": "medium",
 "tested": true,
 "updated": "2026-11-03",
 "first_published": "2026-10-25",
 "inputs": [
  {
   "type": "question",
   "required": true,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  },
  {
   "type": "codebase",
   "required": false,
   "label": "Codebase",
   "what": "a project's code, in a folder or repo the AI can open"
  }
 ],
 "outputs": [
  {
   "type": "plan",
   "required": true,
   "label": "Plan",
   "what": "a dated plan: what to do, in what order, with a decision rule for each step"
  },
  {
   "type": "code_change",
   "required": false,
   "label": "Code change",
   "what": "a change to the code, with what it fixes and how it was checked"
  }
 ],
 "you_give": [
  "The predictions your agent saved, with the agent, the date saved, the number it watches, the direction and size it expected, and the check date",
  "What really happened, with the value before, the value at the check date and the dates",
  "Your grading rule, such as how close counts as right and the smallest change that counts as real",
  "How many graded results you want before a lesson is drafted (optional)",
  "Your grading code and tables (optional)"
 ],
 "you_get": [
  "A score log with one row per prediction: predicted, actual, score and result",
  "A list of predictions that could not be graded, with the reason for each",
  "A likely cause for each miss: wrong read or wrong action",
  "Draft lessons marked for review, only where there are enough results",
  "Gaps in the starter grading code, and test cases on made-up predictions"
 ],
 "use_when": [
  "Your agent has made 20 recommendations and you want to know how many were right.",
  "An agent keeps suggesting the same fix and you doubt it works.",
  "You want lessons for your agent based on results, not on opinions.",
  "You have a starter grading script and need to know what it misses before you rely on it."
 ],
 "skip_when": [
  "You turn Slack reactions and comments into lessons. Use the Agent feedback review system planner.",
  "You want to test one belief of your own with a small bet. Use the Prediction and bet planner.",
  "Nobody saved the predictions before the results came in. They cannot be graded fairly. Start saving them first, then come back.",
  "You want the agent to change its own live rules. This skill drafts lessons. A person approves each one."
 ],
 "output_sample": {
  "input": [
   "The predictions your agent saved, with save dates",
   "What really happened, with dates",
   "Your grading rule",
   "How many results you want before a lesson (optional)"
  ],
  "prerequisites": [
   "Predictions saved before the results were known",
   "Your grading script or tables, if you want the gaps listed (optional)"
  ],
  "output": [
   {
    "name": "Grading rule",
    "contains": "How direction, size and timing become a score, written out so you can check it by hand."
   },
   {
    "name": "Score log",
    "contains": "One row per prediction with predicted and actual change, the score, the result and the likely cause."
   },
   {
    "name": "Not graded",
    "contains": "Predictions skipped, with the reason, such as no save date or a window that has not ended."
   },
   {
    "name": "Patterns",
    "contains": "Accuracy for each agent and type of call, and whether there are enough results to act."
   },
   {
    "name": "Draft lessons",
    "contains": "Short lessons marked draft: stop doing this, keep doing that, or move this limit."
   },
   {
    "name": "Gaps in the starter",
    "contains": "What the starter script and tables get wrong, and the fix for each."
   },
   {
    "name": "Test cases",
    "contains": "Made-up predictions that check the score, the noise floor and the window."
   }
  ]
 },
 "output_shape": "BASIS\n<what was read; nothing was run>\nMISSING: <inputs and what each stops>\n\nGRADING RULE\n<direction> | <size> | <timing> | <smallest real change> | <how the score is worked out>\n\nSCORE LOG\n<id> | <agent> | <saved on> | <checked on> | <number watched> | <predicted> | <actual> | <score> | <result> | <cause> | <review status>\n\nNOT GRADED\n<id> | <reason>\n\nPATTERNS\n<agent and type> | <graded count> | <share correct> | <enough to act?>\n\nDRAFT LESSONS\n<id> | <type> | <lesson, under 60 words> | <applies to> | draft\n\nGAPS IN THE STARTER\n<#> | <what it does> | <why it matters> | <fix>\n\nTEST CASES\n<name> | <set-up> | <expected result>\n\nNEXT STEP\n<one smallest useful step>",
 "how_to_use": [
  "Open the skill in your AI. A chat AI works if you paste your predictions in. A coding AI such as Claude Code works better if you want it to read your scripts.",
  "Paste the saved predictions, what happened and your grading rule. Remove client names first.",
  "Read MISSING and NOT GRADED first. A prediction with no save date is not graded.",
  "Check three scores by hand using the math the skill shows. If they differ, fix the rule before you trust the rest.",
  "Read each draft lesson. Keep, change or drop it. Nothing goes into the agent's live rules until you say so.",
  "Run the test cases on a copy of your system, never on live data."
 ],
 "checks": [],
 "next": [
  {
   "name": "Simple code coach",
   "url": "https://useaiblocks.com/skills/simple-code-coach",
   "why": "Build it"
  }
 ],
 "source": null,
 "credits": [],
 "files": [
  "references/learning-events-schema.sql",
  "references/method-notes.md",
  "references/self-reflection-runner-starter.ts"
 ],
 "links": {
  "page": "https://useaiblocks.com/skills/self-reflection-grading-past-predictions-implementation-planner",
  "markdown": "https://useaiblocks.com/skills/self-reflection-grading-past-predictions-implementation-planner.md",
  "json": "https://useaiblocks.com/skills/self-reflection-grading-past-predictions-implementation-planner.json",
  "instructions": "https://useaiblocks.com/skills/self-reflection-grading-past-predictions-implementation-planner/SKILL.md",
  "download": "https://useaiblocks.com/skills/self-reflection-grading-past-predictions-implementation-planner.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/self-reflection-grading-past-predictions-implementation-planner",
  "api_document": "https://useaiblocks.com/api/v1/documents/skill/self-reflection-grading-past-predictions-implementation-planner",
  "mcp": "https://useaiblocks.com/mcp"
 }
}