{ "name": "Draft three versions and pick the best", "nodes": [ { "parameters": { "content": "## Draft three versions and pick the best\nWrite three different versions of the same piece, rate each one against criteria you set, and keep the winner with the reason shown, so the choice is not just a feeling.\n\n**How to use**\n1. Open **Chat model** and pick your own credential. To use another AI service, delete that node, add the service's chat model node, and connect it to the Model plug under every step and AI check.\n2. Open **Inputs** and paste your material into each field. Examples are filled in so you can try it first.\n3. Click **Execute workflow**.\n4. Open **Result** to read the answer, anything flagged, and the checks left for you.\n\n**Checks**\n- Check 1 (a plain rule, run automatically with no AI): The answer includes the words \"Version C\". If it fails: try once more, then flag.\n- Check 2 (a plain rule, run automatically with no AI): Every row of the table has one of \"strong\", \"partly\" or \"weak\" in the Rating column. If it fails: try once more, then flag.\n- Check 3 (a plain rule, run automatically with no AI): The answer includes the words \"Winner: Version\". If it fails: try once more, then flag.\n- Check 4 (a second AI prompt answers pass or fail): Read the winner and the reason in the last answer next to the ratings table. Does the reason name criteria the person set, and do the ratings really support choosing that version? Answer FAIL if the reason uses criteria that were not listed or contradicts the table. If it fails: try once more, then flag.\n- Check 5 (a plain rule, run automatically with no AI): Every row of the table has something written in \"Reason\" (a blank or a dash does not count). If it fails: try once more, then flag.\n- Check 6 (a second AI prompt answers pass or fail): Compare the final text with the brief below. Does every date, name, number and promise in the final text come from the brief, with nothing invented? If it fails: try once more, then flag.\n- Check 7 (you check it by hand): Read the final text as the reader would. Is it the one you would send? If not, which version would you pick instead, and which criterion did the ratings miss? If it fails: flag it and carry on.\n\nFrom Logic Lab (logiclabhq.com). Free to use and adapt, with credit.", "height": 720, "width": 760, "color": 5 }, "id": "af13315e-166b-4307-ab26-e4b8ce1cd449", "name": "About this workflow", "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ -40, -680 ] }, { "parameters": {}, "id": "bc5267b2-1e5d-42b7-a1e9-69c417f1bb21", "name": "Start", "type": "n8n-nodes-base.manualTrigger", "typeVersion": 1, "position": [ 0, 320 ] }, { "parameters": { "assignments": { "assignments": [ { "id": "9bae3895-6c79-40f4-a696-7cbba80f49f2", "name": "brief", "value": "Sample: An email to all staff announcing that the office printer will be replaced on Friday 24 October. The old printer will be removed at noon. Staff should save print jobs to the shared drive instead of printing that afternoon. Questions go to Priya in facilities.", "type": "string" }, { "id": "9f9bc6cc-ec02-4e3f-a91b-aab2ef6035d5", "name": "reader", "value": "Sample: All office staff, mixed ages, most reading on a phone", "type": "string" }, { "id": "66ac4166-4ab2-4fb1-a134-b8702efe55bb", "name": "criteria", "value": "Sample:\nThe date and time are impossible to miss\nShort enough to read in under a minute\nFriendly, not bossy", "type": "string" } ] }, "options": {} }, "id": "655be877-adf8-4b00-a3f0-b5ad9862f5e6", "name": "Inputs", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 220, 320 ], "notes": "Paste your own material here: brief = What you need written; reader = Who will read it; criteria = What makes a version good.", "notesInFlow": true }, { "parameters": { "promptType": "define", "hasOutputParser": false, "text": "=You are an experienced writer who drafts for a wide range of readers.\n\nYour task is to write three versions of the piece described below. Each version must take a different approach. For example: Version A is direct and brief, Version B opens with the reason or a short example, Version C is warm and conversational. You may choose other approaches if they suit the piece better.\n\nWhat is needed:\n{{ $(\"Inputs\").first().json[\"brief\"] }}\n\nWho will read it: {{ $(\"Inputs\").first().json[\"reader\"] }}\n\nRules:\n- Use only the facts in the brief. Do not invent dates, names, numbers or promises.\n- Keep all three versions complete and ready to send, not outlines.\n- Do not make the three versions differ only in a few words. They should read differently from the first line.\n\nReturn the three versions in this shape and nothing else:\nVersion A (approach in a few words)\n(the full text)\nVersion B (approach in a few words)\n(the full text)\nVersion C (approach in a few words)\n(the full text){{ $(\"Check 1: All three versions are there\").isExecuted ? \"\\n\\nYour last answer did not pass this check: All three versions are there. What was wrong: \" + $(\"Check 1: All three versions are there\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "89ce57cf-dff5-455e-a019-7ea96f048180", "name": "1. Write three versions", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 480, 320 ], "notes": "Write three versions that take clearly different approaches. Returns: Three complete versions, each labeled with its approach.", "notesInFlow": true }, { "parameters": { "jsCode": "// All three versions are there\n// Rule: The answer includes the words \"Version C\".\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\n .split('|')\n .map((c) => c.trim());\n for (let i = 0; i < lines.length; i++) {\n const l = lines[i] ?? '';\n if (!l.startsWith('|')) {\n cur = null;\n continue;\n }\n if (!cur) {\n const next = lines[i + 1] ?? '';\n if (/^\\|?\\s*:?-{2,}/.test(next)) {\n cur = { header: cells(l), rows: [] };\n tables.push(cur);\n i++;\n }\n continue;\n }\n cur.rows.push(cells(l));\n }\n return tables;\n };\n // Every table that has this column, with \"None found\" rows left out.\n // Returns that column's cells from every such table, or null if no table has it.\n const findColumn = (name) => {\n let seen = false;\n const cells = [];\n for (const t of readTable(work)) {\n const i = t.header.findIndex((h) => norm(h) === norm(name));\n if (i < 0)\n continue;\n seen = true;\n for (const r of t.rows) {\n if (r.some((c) => norm(c) === 'none found'))\n continue;\n cells.push(r[i] ?? '');\n }\n }\n return seen ? cells : null;\n };\n const empty = (c) => !c || /^[-\\u2013\\u2014\\s]*$/.test(c);\n switch (rule) {\n case 'has_text':\n return norm(work).includes(norm(value))\n ? { pass: true, reason: 'Found.' }\n : { pass: false, reason: `The answer does not include \"${value}\".` };\n case 'lacks_text':\n return norm(work).includes(norm(value))\n ? { pass: false, reason: `The answer includes \"${value}\", which it should not.` }\n : { pass: true, reason: 'Not found, as it should be.' };\n case 'max_words': {\n const n = String(work ?? '')\n .split(/\\s+/)\n .filter(Boolean).length;\n return n <= Number(value)\n ? { pass: true, reason: `${n} words.` }\n : { pass: false, reason: `The answer has ${n} words; the limit is ${value}.` };\n }\n case 'table_cells_filled': {\n const problems = [];\n for (const col of value) {\n const f = findColumn(col);\n if (!f) {\n problems.push(`No table with a \"${col}\" column was found.`);\n continue;\n }\n f.forEach((c, i) => {\n if (empty(c))\n problems.push(`Row ${i + 1} has nothing in \"${col}\".`);\n });\n }\n return problems.length\n ? { pass: false, reason: problems.join(' ') }\n : { pass: true, reason: 'Every row is filled in.' };\n }\n case 'column_values_in': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const allowed = value.allowed.map(norm);\n const bad = [];\n f.forEach((c, i) => {\n if (!allowed.includes(norm(c)))\n bad.push(`Row ${i + 1} says \"${c}\".`);\n });\n return bad.length\n ? {\n pass: false,\n reason: `The \"${value.column}\" column must say ${value.allowed.join(' or ')}. ${bad.join(' ')}`,\n }\n : { pass: true, reason: 'Every row uses an allowed word.' };\n }\n case 'column_quotes_source': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const src = norm(sources[value.input] ?? '');\n const bad = [];\n f.forEach((c, i) => {\n // A quote may be shortened with \"...\"; each piece must be in the source.\n const pieces = c\n .split(/\\.\\.\\.|\\u2026/)\n .map(norm)\n .filter(Boolean);\n if (!pieces.length || !pieces.every((p) => src.includes(p)))\n bad.push(`Row ${i + 1}: \"${c}\" is not in the source.`);\n });\n return bad.length\n ? { pass: false, reason: bad.join(' ') }\n : { pass: true, reason: 'Every quote was found in the source.' };\n }\n case 'numbers_in_source': {\n const nums = (s) => (String(s ?? '').match(/\\d[\\d,]*(?:\\.\\d+)?/g) ?? []).map((n) => n.replace(/,/g, ''));\n const src = new Set(nums(sources[value.input] ?? ''));\n const missing = [...new Set(nums(work))].filter((n) => !src.has(n));\n return missing.length\n ? {\n pass: false,\n reason: `These numbers are not in the source: ${missing.join(', ')}.`,\n }\n : { pass: true, reason: 'Every number was found in the source.' };\n }\n default:\n return { pass: false, reason: `Unknown rule \"${rule}\".` };\n }\n};\n\nconst work = String($(\"1. Write three versions\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"has_text\", \"Version C\", work, sources);\nreturn [{ json: result }];" }, "id": "55ceea87-12d3-42ae-ad1a-e205e879f3d4", "name": "Check 1: All three versions are there", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 740, 320 ], "notes": "The answer includes the words \"Version C\".", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "ea06b0a1-dbfb-40ea-a09e-5c7f4094a218", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "70a6b64a-50ae-4b7f-a5a5-4db48f41cc69", "name": "Passed check 1?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1000, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "65bd859e-84a6-4805-acf8-356c35254423", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "6e82bd32-e9a2-46f5-ab45-ae0c807de457", "name": "Try again? (check 1)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1000, 520 ], "notes": "True = first failure: send back to \"1. Write three versions\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "86a177c3-67e1-4ab0-a66d-308d13ad7df2", "name": "flag", "value": "=All three versions are there: did not pass. {{ $(\"Check 1: All three versions are there\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "07ce5f57-61fd-49e4-a8a1-07f1b758dece", "name": "Flag check 1", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 1130, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "promptType": "define", "hasOutputParser": false, "text": "=You are a tough, fair editor who judges drafts only against the criteria given.\n\nYour task is to rate each version below against each criterion, one criterion at a time.\n\nThe criteria:\n{{ $(\"Inputs\").first().json[\"criteria\"] }}\n\nWho will read it: {{ $(\"Inputs\").first().json[\"reader\"] }}\n\nThe three versions:\n{{ $(\"1. Write three versions\").first().json.text }}\n\nRules:\n- Give each rating as exactly one word: strong, partly or weak.\n- Give a reason for every rating. Quote the words in the version that earned it.\n- Judge only against the listed criteria. Do not add your own criteria and do not give an overall rating yet.\n- Do not favor a version because it is longer or has more detail.\n\nReturn one markdown table with one row for every version and criterion pair, and nothing else:\n| Version | Criterion | Rating | Reason |{{ $(\"Check 2: Every rating is strong, partly or weak\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Every rating is strong, partly or weak. What was wrong: \" + $(\"Check 2: Every rating is strong, partly or weak\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}{{ $(\"Check 5: Every rating has a reason\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Every rating has a reason. What was wrong: \" + $(\"Check 5: Every rating has a reason\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "48fd1fea-930b-496d-aefc-2864bd4d44cf", "name": "2. Rate each version against your criteria", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 1260, 320 ], "notes": "Rate every version on every criterion, with a reason that points to the text. Returns: A table with a rating and a reason for every version against every criterion.", "notesInFlow": true }, { "parameters": { "jsCode": "// Every rating is strong, partly or weak\n// Rule: Every row of the table has one of \"strong\", \"partly\" or \"weak\" in the Rating column.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\n .split('|')\n .map((c) => c.trim());\n for (let i = 0; i < lines.length; i++) {\n const l = lines[i] ?? '';\n if (!l.startsWith('|')) {\n cur = null;\n continue;\n }\n if (!cur) {\n const next = lines[i + 1] ?? '';\n if (/^\\|?\\s*:?-{2,}/.test(next)) {\n cur = { header: cells(l), rows: [] };\n tables.push(cur);\n i++;\n }\n continue;\n }\n cur.rows.push(cells(l));\n }\n return tables;\n };\n // Every table that has this column, with \"None found\" rows left out.\n // Returns that column's cells from every such table, or null if no table has it.\n const findColumn = (name) => {\n let seen = false;\n const cells = [];\n for (const t of readTable(work)) {\n const i = t.header.findIndex((h) => norm(h) === norm(name));\n if (i < 0)\n continue;\n seen = true;\n for (const r of t.rows) {\n if (r.some((c) => norm(c) === 'none found'))\n continue;\n cells.push(r[i] ?? '');\n }\n }\n return seen ? cells : null;\n };\n const empty = (c) => !c || /^[-\\u2013\\u2014\\s]*$/.test(c);\n switch (rule) {\n case 'has_text':\n return norm(work).includes(norm(value))\n ? { pass: true, reason: 'Found.' }\n : { pass: false, reason: `The answer does not include \"${value}\".` };\n case 'lacks_text':\n return norm(work).includes(norm(value))\n ? { pass: false, reason: `The answer includes \"${value}\", which it should not.` }\n : { pass: true, reason: 'Not found, as it should be.' };\n case 'max_words': {\n const n = String(work ?? '')\n .split(/\\s+/)\n .filter(Boolean).length;\n return n <= Number(value)\n ? { pass: true, reason: `${n} words.` }\n : { pass: false, reason: `The answer has ${n} words; the limit is ${value}.` };\n }\n case 'table_cells_filled': {\n const problems = [];\n for (const col of value) {\n const f = findColumn(col);\n if (!f) {\n problems.push(`No table with a \"${col}\" column was found.`);\n continue;\n }\n f.forEach((c, i) => {\n if (empty(c))\n problems.push(`Row ${i + 1} has nothing in \"${col}\".`);\n });\n }\n return problems.length\n ? { pass: false, reason: problems.join(' ') }\n : { pass: true, reason: 'Every row is filled in.' };\n }\n case 'column_values_in': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const allowed = value.allowed.map(norm);\n const bad = [];\n f.forEach((c, i) => {\n if (!allowed.includes(norm(c)))\n bad.push(`Row ${i + 1} says \"${c}\".`);\n });\n return bad.length\n ? {\n pass: false,\n reason: `The \"${value.column}\" column must say ${value.allowed.join(' or ')}. ${bad.join(' ')}`,\n }\n : { pass: true, reason: 'Every row uses an allowed word.' };\n }\n case 'column_quotes_source': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const src = norm(sources[value.input] ?? '');\n const bad = [];\n f.forEach((c, i) => {\n // A quote may be shortened with \"...\"; each piece must be in the source.\n const pieces = c\n .split(/\\.\\.\\.|\\u2026/)\n .map(norm)\n .filter(Boolean);\n if (!pieces.length || !pieces.every((p) => src.includes(p)))\n bad.push(`Row ${i + 1}: \"${c}\" is not in the source.`);\n });\n return bad.length\n ? { pass: false, reason: bad.join(' ') }\n : { pass: true, reason: 'Every quote was found in the source.' };\n }\n case 'numbers_in_source': {\n const nums = (s) => (String(s ?? '').match(/\\d[\\d,]*(?:\\.\\d+)?/g) ?? []).map((n) => n.replace(/,/g, ''));\n const src = new Set(nums(sources[value.input] ?? ''));\n const missing = [...new Set(nums(work))].filter((n) => !src.has(n));\n return missing.length\n ? {\n pass: false,\n reason: `These numbers are not in the source: ${missing.join(', ')}.`,\n }\n : { pass: true, reason: 'Every number was found in the source.' };\n }\n default:\n return { pass: false, reason: `Unknown rule \"${rule}\".` };\n }\n};\n\nconst work = String($(\"2. Rate each version against your criteria\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"column_values_in\", {\"column\":\"Rating\",\"allowed\":[\"strong\",\"partly\",\"weak\"]}, work, sources);\nreturn [{ json: result }];" }, "id": "f442aefc-85b1-4dcd-ae56-cfea8427214b", "name": "Check 2: Every rating is strong, partly or weak", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1520, 320 ], "notes": "Every row of the table has one of \"strong\", \"partly\" or \"weak\" in the Rating column.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "e906af0e-dcfb-427d-af9e-5aec4194a3ab", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "f09f3105-50ac-4ce8-a5a7-8c4b0f4951ae", "name": "Passed check 2?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1780, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "66bd8731-83a6-4672-adf8-36ff34254290", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "e685b8b1-c1a0-4966-ab3e-5b27a084d27c", "name": "Try again? (check 2)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1780, 520 ], "notes": "True = first failure: send back to \"2. Rate each version against your criteria\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "85a17630-68e1-4c43-a56d-2efa14ad7f85", "name": "flag", "value": "=Every rating is strong, partly or weak: did not pass. {{ $(\"Check 2: Every rating is strong, partly or weak\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "08ce60ea-64fd-4e9d-a5a1-0338b658dd3b", "name": "Flag check 2", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 1910, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "promptType": "define", "hasOutputParser": false, "text": "=You are an editor making a final choice between drafts.\n\nYour task is to choose the winning version from the ratings below, and hand it back ready to use.\n\nThe criteria:\n{{ $(\"Inputs\").first().json[\"criteria\"] }}\n\nThe three versions:\n{{ $(\"1. Write three versions\").first().json.text }}\n\nThe ratings:\n{{ $(\"2. Rate each version against your criteria\").first().json.text }}\n\nRules:\n- Choose the version with the most strong ratings and no weak rating on a criterion that matters most. If two are close, say so and choose by the criterion listed first.\n- Fix only plain mistakes in the winner (typos, a missing fact from the brief). Do not rewrite it.\n- If a good line from a losing version would fit the winner, you may suggest it, but do not paste it in.\n- Do not pick a winner the ratings do not support.\n\nReturn in this shape and nothing else:\nWinner: Version (letter)\nWhy: (two or three sentences that name the criteria and point to the ratings)\nFinal text:\n(the winning version, ready to send)\nWorth borrowing:\n(a line from another version, or \"Nothing\"){{ $(\"Check 3: A winner is named\").isExecuted ? \"\\n\\nYour last answer did not pass this check: A winner is named. What was wrong: \" + $(\"Check 3: A winner is named\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}{{ $(\"Check 4: The reason follows the ratings\").isExecuted ? \"\\n\\nYour last answer did not pass this check: The reason follows the ratings. What was wrong: \" + $(\"Check 4: The reason follows the ratings\").first().json.text + \"\\nFix that and give your full answer again.\" : \"\" }}{{ $(\"Check 6: No facts were added\").isExecuted ? \"\\n\\nYour last answer did not pass this check: No facts were added. What was wrong: \" + $(\"Check 6: No facts were added\").first().json.text + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "5d53a292-b7ef-48e5-ab19-3118ba567aeb", "name": "3. Keep the winner and say why", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 2040, 320 ], "notes": "Pick the version that best meets the criteria, and show the reason in the open. Returns: The winner named with the reason, its final text, and any line worth borrowing.", "notesInFlow": true }, { "parameters": { "jsCode": "// A winner is named\n// Rule: The answer includes the words \"Winner: Version\".\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\n .split('|')\n .map((c) => c.trim());\n for (let i = 0; i < lines.length; i++) {\n const l = lines[i] ?? '';\n if (!l.startsWith('|')) {\n cur = null;\n continue;\n }\n if (!cur) {\n const next = lines[i + 1] ?? '';\n if (/^\\|?\\s*:?-{2,}/.test(next)) {\n cur = { header: cells(l), rows: [] };\n tables.push(cur);\n i++;\n }\n continue;\n }\n cur.rows.push(cells(l));\n }\n return tables;\n };\n // Every table that has this column, with \"None found\" rows left out.\n // Returns that column's cells from every such table, or null if no table has it.\n const findColumn = (name) => {\n let seen = false;\n const cells = [];\n for (const t of readTable(work)) {\n const i = t.header.findIndex((h) => norm(h) === norm(name));\n if (i < 0)\n continue;\n seen = true;\n for (const r of t.rows) {\n if (r.some((c) => norm(c) === 'none found'))\n continue;\n cells.push(r[i] ?? '');\n }\n }\n return seen ? cells : null;\n };\n const empty = (c) => !c || /^[-\\u2013\\u2014\\s]*$/.test(c);\n switch (rule) {\n case 'has_text':\n return norm(work).includes(norm(value))\n ? { pass: true, reason: 'Found.' }\n : { pass: false, reason: `The answer does not include \"${value}\".` };\n case 'lacks_text':\n return norm(work).includes(norm(value))\n ? { pass: false, reason: `The answer includes \"${value}\", which it should not.` }\n : { pass: true, reason: 'Not found, as it should be.' };\n case 'max_words': {\n const n = String(work ?? '')\n .split(/\\s+/)\n .filter(Boolean).length;\n return n <= Number(value)\n ? { pass: true, reason: `${n} words.` }\n : { pass: false, reason: `The answer has ${n} words; the limit is ${value}.` };\n }\n case 'table_cells_filled': {\n const problems = [];\n for (const col of value) {\n const f = findColumn(col);\n if (!f) {\n problems.push(`No table with a \"${col}\" column was found.`);\n continue;\n }\n f.forEach((c, i) => {\n if (empty(c))\n problems.push(`Row ${i + 1} has nothing in \"${col}\".`);\n });\n }\n return problems.length\n ? { pass: false, reason: problems.join(' ') }\n : { pass: true, reason: 'Every row is filled in.' };\n }\n case 'column_values_in': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const allowed = value.allowed.map(norm);\n const bad = [];\n f.forEach((c, i) => {\n if (!allowed.includes(norm(c)))\n bad.push(`Row ${i + 1} says \"${c}\".`);\n });\n return bad.length\n ? {\n pass: false,\n reason: `The \"${value.column}\" column must say ${value.allowed.join(' or ')}. ${bad.join(' ')}`,\n }\n : { pass: true, reason: 'Every row uses an allowed word.' };\n }\n case 'column_quotes_source': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const src = norm(sources[value.input] ?? '');\n const bad = [];\n f.forEach((c, i) => {\n // A quote may be shortened with \"...\"; each piece must be in the source.\n const pieces = c\n .split(/\\.\\.\\.|\\u2026/)\n .map(norm)\n .filter(Boolean);\n if (!pieces.length || !pieces.every((p) => src.includes(p)))\n bad.push(`Row ${i + 1}: \"${c}\" is not in the source.`);\n });\n return bad.length\n ? { pass: false, reason: bad.join(' ') }\n : { pass: true, reason: 'Every quote was found in the source.' };\n }\n case 'numbers_in_source': {\n const nums = (s) => (String(s ?? '').match(/\\d[\\d,]*(?:\\.\\d+)?/g) ?? []).map((n) => n.replace(/,/g, ''));\n const src = new Set(nums(sources[value.input] ?? ''));\n const missing = [...new Set(nums(work))].filter((n) => !src.has(n));\n return missing.length\n ? {\n pass: false,\n reason: `These numbers are not in the source: ${missing.join(', ')}.`,\n }\n : { pass: true, reason: 'Every number was found in the source.' };\n }\n default:\n return { pass: false, reason: `Unknown rule \"${rule}\".` };\n }\n};\n\nconst work = String($(\"3. Keep the winner and say why\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"has_text\", \"Winner: Version\", work, sources);\nreturn [{ json: result }];" }, "id": "b3306204-0824-4c03-a871-f9a6d950a92d", "name": "Check 3: A winner is named", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 2300, 320 ], "notes": "The answer includes the words \"Winner: Version\".", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "e806ad7b-d9fa-4dc4-a29e-5fa54294a53e", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "70a2391c-d0a9-44d1-a5a9-cae20f471317", "name": "Passed check 3?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 2560, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "63bd8278-82a6-44df-aef8-389237254749", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "0a882ff4-dd9e-46e3-af41-372a7c825b39", "name": "Try again? (check 3)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 2560, 520 ], "notes": "True = first failure: send back to \"3. Keep the winner and say why\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "88a17ae9-69e1-4dd6-a46d-2d6711ad7acc", "name": "flag", "value": "=A winner is named: did not pass. {{ $(\"Check 3: A winner is named\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "09ce627d-63fd-4d0a-a6a1-04cbb558dba8", "name": "Flag check 3", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 2690, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "promptType": "define", "hasOutputParser": false, "text": "=You are a careful reviewer. You do not fix or rewrite the work; you only decide whether it passes one check.\n\nThe check: The reason follows the ratings\nRead the winner and the reason in the last answer next to the ratings table. Does the reason name criteria the person set, and do the ratings really support choosing that version? Answer FAIL if the reason uses criteria that were not listed or contradicts the table.\n\nThe criteria:\n{{ $(\"Inputs\").first().json[\"criteria\"] }}\n\nThe ratings:\n{{ $(\"2. Rate each version against your criteria\").first().json.text }}\n\nThe work to check (the answer from Step 3 (Keep the winner and say why)):\n{{ $(\"3. Keep the winner and say why\").first().json.text }}\n\nReply with exactly PASS or FAIL on the first line. On the second line, say in one sentence why. If it fails, name the exact item or line that fails. Do not add anything else." }, "id": "b36f20c6-1302-4073-afba-6ae44e12f2a1", "name": "Check 4: The reason follows the ratings", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 2820, 320 ], "notes": "Answers PASS or FAIL. Read the winner and the reason in the last answer next to the ratings table. Does the reason name criteria the person set, and do the ratings really support choosing that version? Answer FAIL if the reason uses criteria that were not listed or contradicts the table.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "e706abe8-dafa-4f57-a19e-5e124394a6d1", "leftValue": "={{ String($json.text ?? '').trim().toUpperCase().startsWith('PASS') }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "f0ae3b8f-d0a7-463a-a5ac-09790f3a4724", "name": "Passed check 4?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3080, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "64bd840b-81a6-434c-aff8-3a25362545b6", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "0276da3b-e5af-4c9c-af39-b1e5fc7658c6", "name": "Try again? (check 4)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3080, 520 ], "notes": "True = first failure: send back to \"3. Keep the winner and say why\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "87a17956-6ae1-4f69-a36d-2bd412ad7c5f", "name": "flag", "value": "=The reason follows the ratings: did not pass. {{ $(\"Check 4: The reason follows the ratings\").first().json.text }}", "type": "string" } ] }, "options": {} }, "id": "02ce5778-5efd-452b-aba1-0caabc58e6ad", "name": "Flag check 4", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 3210, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "jsCode": "// Every rating has a reason\n// Rule: Every row of the table has something written in \"Reason\" (a blank or a dash does not count).\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\n .split('|')\n .map((c) => c.trim());\n for (let i = 0; i < lines.length; i++) {\n const l = lines[i] ?? '';\n if (!l.startsWith('|')) {\n cur = null;\n continue;\n }\n if (!cur) {\n const next = lines[i + 1] ?? '';\n if (/^\\|?\\s*:?-{2,}/.test(next)) {\n cur = { header: cells(l), rows: [] };\n tables.push(cur);\n i++;\n }\n continue;\n }\n cur.rows.push(cells(l));\n }\n return tables;\n };\n // Every table that has this column, with \"None found\" rows left out.\n // Returns that column's cells from every such table, or null if no table has it.\n const findColumn = (name) => {\n let seen = false;\n const cells = [];\n for (const t of readTable(work)) {\n const i = t.header.findIndex((h) => norm(h) === norm(name));\n if (i < 0)\n continue;\n seen = true;\n for (const r of t.rows) {\n if (r.some((c) => norm(c) === 'none found'))\n continue;\n cells.push(r[i] ?? '');\n }\n }\n return seen ? cells : null;\n };\n const empty = (c) => !c || /^[-\\u2013\\u2014\\s]*$/.test(c);\n switch (rule) {\n case 'has_text':\n return norm(work).includes(norm(value))\n ? { pass: true, reason: 'Found.' }\n : { pass: false, reason: `The answer does not include \"${value}\".` };\n case 'lacks_text':\n return norm(work).includes(norm(value))\n ? { pass: false, reason: `The answer includes \"${value}\", which it should not.` }\n : { pass: true, reason: 'Not found, as it should be.' };\n case 'max_words': {\n const n = String(work ?? '')\n .split(/\\s+/)\n .filter(Boolean).length;\n return n <= Number(value)\n ? { pass: true, reason: `${n} words.` }\n : { pass: false, reason: `The answer has ${n} words; the limit is ${value}.` };\n }\n case 'table_cells_filled': {\n const problems = [];\n for (const col of value) {\n const f = findColumn(col);\n if (!f) {\n problems.push(`No table with a \"${col}\" column was found.`);\n continue;\n }\n f.forEach((c, i) => {\n if (empty(c))\n problems.push(`Row ${i + 1} has nothing in \"${col}\".`);\n });\n }\n return problems.length\n ? { pass: false, reason: problems.join(' ') }\n : { pass: true, reason: 'Every row is filled in.' };\n }\n case 'column_values_in': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const allowed = value.allowed.map(norm);\n const bad = [];\n f.forEach((c, i) => {\n if (!allowed.includes(norm(c)))\n bad.push(`Row ${i + 1} says \"${c}\".`);\n });\n return bad.length\n ? {\n pass: false,\n reason: `The \"${value.column}\" column must say ${value.allowed.join(' or ')}. ${bad.join(' ')}`,\n }\n : { pass: true, reason: 'Every row uses an allowed word.' };\n }\n case 'column_quotes_source': {\n const f = findColumn(value.column);\n if (!f)\n return { pass: false, reason: `No table with a \"${value.column}\" column was found.` };\n const src = norm(sources[value.input] ?? '');\n const bad = [];\n f.forEach((c, i) => {\n // A quote may be shortened with \"...\"; each piece must be in the source.\n const pieces = c\n .split(/\\.\\.\\.|\\u2026/)\n .map(norm)\n .filter(Boolean);\n if (!pieces.length || !pieces.every((p) => src.includes(p)))\n bad.push(`Row ${i + 1}: \"${c}\" is not in the source.`);\n });\n return bad.length\n ? { pass: false, reason: bad.join(' ') }\n : { pass: true, reason: 'Every quote was found in the source.' };\n }\n case 'numbers_in_source': {\n const nums = (s) => (String(s ?? '').match(/\\d[\\d,]*(?:\\.\\d+)?/g) ?? []).map((n) => n.replace(/,/g, ''));\n const src = new Set(nums(sources[value.input] ?? ''));\n const missing = [...new Set(nums(work))].filter((n) => !src.has(n));\n return missing.length\n ? {\n pass: false,\n reason: `These numbers are not in the source: ${missing.join(', ')}.`,\n }\n : { pass: true, reason: 'Every number was found in the source.' };\n }\n default:\n return { pass: false, reason: `Unknown rule \"${rule}\".` };\n }\n};\n\nconst work = String($(\"2. Rate each version against your criteria\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"table_cells_filled\", [\"Reason\"], work, sources);\nreturn [{ json: result }];" }, "id": "38d3a2f8-0643-4517-a041-55de7ecd98ad", "name": "Check 5: Every rating has a reason", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 3340, 320 ], "notes": "Every row of the table has something written in \"Reason\" (a blank or a dash does not count).", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "ee06b6ed-d7fa-4a9e-ac9e-56334494a864", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "f0b07a26-d0a5-47a3-a5af-11900f38088d", "name": "Passed check 5?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3600, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "69bd8bea-80a6-41b9-a8f8-2f2039254a6f", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "e678ecbe-c1ad-4559-a33b-dd9898737cc3", "name": "Try again? (check 5)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3600, 520 ], "notes": "True = first failure: send back to \"2. Rate each version against your criteria\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "8aa17e0f-6be1-40fc-a26d-2a410fad77a6", "name": "flag", "value": "=Every rating has a reason: did not pass. {{ $(\"Check 5: Every rating has a reason\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "03ce590b-5dfd-4398-aca1-0e3dbb58e51a", "name": "Flag check 5", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 3730, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "promptType": "define", "hasOutputParser": false, "text": "=You are a careful reviewer. You do not fix or rewrite the work; you only decide whether it passes one check.\n\nThe check: No facts were added\nCompare the final text with the brief below. Does every date, name, number and promise in the final text come from the brief, with nothing invented?\n\nThe brief:\n{{ $(\"Inputs\").first().json[\"brief\"] }}\n\nThe work to check (the answer from Step 3 (Keep the winner and say why)):\n{{ $(\"3. Keep the winner and say why\").first().json.text }}\n\nReply with exactly PASS or FAIL on the first line. On the second line, say in one sentence why. If it fails, name the exact item or line that fails. Do not add anything else." }, "id": "19c92255-8c56-4736-a009-5543e36f223c", "name": "Check 6: No facts were added", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 3860, 320 ], "notes": "Answers PASS or FAIL. Compare the final text with the brief below. Does every date, name, number and promise in the final text come from the brief, with nothing invented?", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "ed06b55a-d8fa-4c31-ab9e-54a04594a9f7", "leftValue": "={{ String($json.text ?? '').trim().toUpperCase().startsWith('PASS') }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "f0a9be61-50a2-4f8c-a5b1-50278f3f8dd2", "name": "Passed check 6?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 4120, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "6abd8d7d-7fa6-4026-a9f8-30b3382548dc", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "0e7b6a4d-69aa-4c3a-a334-5853187b0208", "name": "Try again? (check 6)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 4120, 520 ], "notes": "True = first failure: send back to \"3. Keep the winner and say why\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "89a17c7c-6ce1-428f-a16d-28ae10ad7939", "name": "flag", "value": "=No facts were added: did not pass. {{ $(\"Check 6: No facts were added\").first().json.text }}", "type": "string" } ] }, "options": {} }, "id": "04ce5a9e-60fd-4851-a9a1-0984ba58e387", "name": "Flag check 6", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 4250, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "content": "**Check 7: check by hand**\nRead the final text as the reader would. Is it the one you would send? If not, which version would you pick instead, and which criterion did the ratings miss?\n\nIf not: flag it and carry on. This check is also listed in Result.", "height": 200, "width": 240, "color": 3 }, "id": "4d800c0a-7c91-4aa3-afb2-7a1c0285cc55", "name": "Check 7 (by hand)", "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 4100, 70 ] }, { "parameters": { "assignments": { "assignments": [ { "id": "42ddd2a6-c97e-4c0b-a6e0-17ec3c74acf9", "name": "result", "value": "={{ $(\"3. Keep the winner and say why\").first().json.text }}", "type": "string" }, { "id": "0666c5c7-7e33-4f20-a11a-16e5717aa1c6", "name": "flagged", "value": "={{ [$(\"Flag check 1\").isExecuted ? $(\"Flag check 1\").first().json.flag : \"\", $(\"Flag check 2\").isExecuted ? $(\"Flag check 2\").first().json.flag : \"\", $(\"Flag check 3\").isExecuted ? $(\"Flag check 3\").first().json.flag : \"\", $(\"Flag check 4\").isExecuted ? $(\"Flag check 4\").first().json.flag : \"\", $(\"Flag check 5\").isExecuted ? $(\"Flag check 5\").first().json.flag : \"\", $(\"Flag check 6\").isExecuted ? $(\"Flag check 6\").first().json.flag : \"\"].filter(x => x).join(\"\\n\") || \"None\" }}", "type": "string" }, { "id": "30cec85d-7a19-4f7e-a54c-6f3bac101834", "name": "check_by_hand", "value": "- Read the final text as the reader would. Is it the one you would send? If not, which version would you pick instead, and which criterion did the ratings miss?", "type": "string" } ] }, "options": {} }, "id": "bcee8013-de2d-4d1c-a744-ec61923e587a", "name": "Result", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 4380, 320 ], "notes": "The final answer, anything flagged, and the checks left for you.", "notesInFlow": true }, { "parameters": { "options": {} }, "id": "76220ca9-e584-45ee-a2e2-5e37ae6c44d4", "name": "Chat model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "typeVersion": 1.2, "position": [ 480, 840 ], "notes": "Attach your credential here, or swap in any chat model node.", "notesInFlow": true } ], "connections": { "Start": { "main": [ [ { "node": "Inputs", "type": "main", "index": 0 } ] ] }, "Inputs": { "main": [ [ { "node": "1. Write three versions", "type": "main", "index": 0 } ] ] }, "1. Write three versions": { "main": [ [ { "node": "Check 1: All three versions are there", "type": "main", "index": 0 } ] ] }, "Check 1: All three versions are there": { "main": [ [ { "node": "Passed check 1?", "type": "main", "index": 0 } ] ] }, "Passed check 1?": { "main": [ [ { "node": "2. Rate each version against your criteria", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 1)", "type": "main", "index": 0 } ] ] }, "Try again? (check 1)": { "main": [ [ { "node": "1. Write three versions", "type": "main", "index": 0 } ], [ { "node": "Flag check 1", "type": "main", "index": 0 } ] ] }, "Flag check 1": { "main": [ [ { "node": "2. Rate each version against your criteria", "type": "main", "index": 0 } ] ] }, "2. Rate each version against your criteria": { "main": [ [ { "node": "Check 2: Every rating is strong, partly or weak", "type": "main", "index": 0 } ] ] }, "Check 2: Every rating is strong, partly or weak": { "main": [ [ { "node": "Passed check 2?", "type": "main", "index": 0 } ] ] }, "Passed check 2?": { "main": [ [ { "node": "3. Keep the winner and say why", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 2)", "type": "main", "index": 0 } ] ] }, "Try again? (check 2)": { "main": [ [ { "node": "2. Rate each version against your criteria", "type": "main", "index": 0 } ], [ { "node": "Flag check 2", "type": "main", "index": 0 } ] ] }, "Flag check 2": { "main": [ [ { "node": "3. Keep the winner and say why", "type": "main", "index": 0 } ] ] }, "3. Keep the winner and say why": { "main": [ [ { "node": "Check 3: A winner is named", "type": "main", "index": 0 } ] ] }, "Check 3: A winner is named": { "main": [ [ { "node": "Passed check 3?", "type": "main", "index": 0 } ] ] }, "Passed check 3?": { "main": [ [ { "node": "Check 4: The reason follows the ratings", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 3)", "type": "main", "index": 0 } ] ] }, "Try again? (check 3)": { "main": [ [ { "node": "3. Keep the winner and say why", "type": "main", "index": 0 } ], [ { "node": "Flag check 3", "type": "main", "index": 0 } ] ] }, "Flag check 3": { "main": [ [ { "node": "Check 4: The reason follows the ratings", "type": "main", "index": 0 } ] ] }, "Check 4: The reason follows the ratings": { "main": [ [ { "node": "Passed check 4?", "type": "main", "index": 0 } ] ] }, "Passed check 4?": { "main": [ [ { "node": "Check 5: Every rating has a reason", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 4)", "type": "main", "index": 0 } ] ] }, "Try again? (check 4)": { "main": [ [ { "node": "3. Keep the winner and say why", "type": "main", "index": 0 } ], [ { "node": "Flag check 4", "type": "main", "index": 0 } ] ] }, "Flag check 4": { "main": [ [ { "node": "Check 5: Every rating has a reason", "type": "main", "index": 0 } ] ] }, "Check 5: Every rating has a reason": { "main": [ [ { "node": "Passed check 5?", "type": "main", "index": 0 } ] ] }, "Passed check 5?": { "main": [ [ { "node": "Check 6: No facts were added", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 5)", "type": "main", "index": 0 } ] ] }, "Try again? (check 5)": { "main": [ [ { "node": "2. Rate each version against your criteria", "type": "main", "index": 0 } ], [ { "node": "Flag check 5", "type": "main", "index": 0 } ] ] }, "Flag check 5": { "main": [ [ { "node": "Check 6: No facts were added", "type": "main", "index": 0 } ] ] }, "Check 6: No facts were added": { "main": [ [ { "node": "Passed check 6?", "type": "main", "index": 0 } ] ] }, "Passed check 6?": { "main": [ [ { "node": "Result", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 6)", "type": "main", "index": 0 } ] ] }, "Try again? (check 6)": { "main": [ [ { "node": "3. Keep the winner and say why", "type": "main", "index": 0 } ], [ { "node": "Flag check 6", "type": "main", "index": 0 } ] ] }, "Flag check 6": { "main": [ [ { "node": "Result", "type": "main", "index": 0 } ] ] }, "Chat model": { "ai_languageModel": [ [ { "node": "1. Write three versions", "type": "ai_languageModel", "index": 0 }, { "node": "2. Rate each version against your criteria", "type": "ai_languageModel", "index": 0 }, { "node": "3. Keep the winner and say why", "type": "ai_languageModel", "index": 0 }, { "node": "Check 4: The reason follows the ratings", "type": "ai_languageModel", "index": 0 }, { "node": "Check 6: No facts were added", "type": "ai_languageModel", "index": 0 } ] ] } }, "pinData": {}, "settings": { "executionOrder": "v1" }, "meta": { "template": "draft-three-versions" } }