{ "name": "Reconcile feedback from three readers", "nodes": [ { "parameters": { "content": "## Reconcile feedback from three readers\nCompare three readers' actual notes on a draft, find agreements and conflicts, and turn them into a revision plan without pretending that every comment can be followed at once.\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): Every quote in the Comment (quote) column appears word for word in the three readers' notes. 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 \"agree\", \"conflict\" or \"single\" in the Relationship column. If it fails: try once more, then flag.\n- Check 3 (a plain rule, run automatically with no AI): Every row of the table has one of \"revise\", \"ask\" or \"keep\" in the Decision column. If it fails: try once more, then flag.\n- Check 4 (a plain rule, run automatically with no AI): The answer includes the words \"Questions to resolve\". If it fails: try once more, then flag.\n- Check 5 (a second AI prompt answers pass or fail): Compare {{steps.extract}} with {{steps.plan}} and the response. Does each distinct reader comment get an edit, a question or a reason to keep the draft, and are conflicts still visible? Answer FAIL and name any lost comment. If it fails: try once more, then flag.\n- Check 6 (you check it by hand): Read the original three notes beside the draft. Confirm that each proposed edit is feasible, resolve conflicting requests with the decision owner, and check facts before sending a revised draft. If it fails: flag it and carry on.\n\nFrom Logic Lab (logiclabhq.com). Free to use and adapt, with credit.", "height": 660, "width": 760, "color": 5 }, "id": "f35ef6be-d577-415b-a436-560093d9c605", "name": "About this workflow", "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ -40, -620 ] }, { "parameters": {}, "id": "73c11492-db69-4d4b-a8e2-af1cac77edad", "name": "Start", "type": "n8n-nodes-base.manualTrigger", "typeVersion": 1, "position": [ 0, 320 ] }, { "parameters": { "assignments": { "assignments": [ { "id": "7bc79b2e-753c-4d03-a86a-269882cf426d", "name": "draft", "value": "Sample: We propose a Saturday workshop pilot in June. Four sessions will serve 100 residents for $900. Registration will open next week. If successful, we will expand in August.", "type": "string" }, { "id": "e53d9d4d-2a0d-4270-aa0c-a7fbb2cbec76", "name": "readers", "value": "Sample: Program manager: Define successful before promising an August expansion. Finance reviewer: Explain the $900 estimate. Resident: Tell me where the sessions take place and whether they cost anything.", "type": "string" }, { "id": "6e6b39d7-d8db-4eb6-a432-9d8dbfcf8bbc", "name": "purpose", "value": "Sample: Give the community board enough information to decide whether to approve the June pilot.", "type": "string" } ] }, "options": {} }, "id": "489671d7-e9db-4074-ab52-2e552cdf7a22", "name": "Inputs", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 220, 320 ], "notes": "Paste your own material here: draft = Draft under review; readers = Three readers' notes; purpose = What the draft must do.", "notesInFlow": true }, { "parameters": { "promptType": "define", "hasOutputParser": false, "text": "=You are a careful editor recording feedback from three readers.\n\nYour task is to list each distinct comment from the readers' notes.\n\nReaders' notes:\n{{ $(\"Inputs\").first().json[\"readers\"] }}\nDraft:\n{{ $(\"Inputs\").first().json[\"draft\"] }}\n\nRules:\n- Name the reader and quote the relevant comment word for word. Split a comment that asks for two changes into two rows.\n- Name the draft passage or section it concerns. If none is clear, write Whole draft.\n- Do not merge two readers into one voice. Do not infer what a silent reader wanted.\n\nReturn one markdown table: | Reader | Comment (quote) | Draft part |{{ $(\"Check 1: Each comment quote appears in the readers' notes\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Each comment quote appears in the readers' notes. What was wrong: \" + $(\"Check 1: Each comment quote appears in the readers' notes\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "913e4bb6-e363-49c1-afc1-88601af4b683", "name": "1. Keep each reader's words separate", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 480, 320 ], "notes": "Quote each distinct note and identify the part of the draft it concerns. Returns: Each actual comment tied to its reader and a draft part.", "notesInFlow": true }, { "parameters": { "jsCode": "// Each comment quote appears in the readers' notes\n// Rule: Every quote in the Comment (quote) column appears word for word in the three readers' notes.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\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($(\"1. Keep each reader's words separate\").first().json.text ?? '');\nconst sources = {\n \"readers\": String($(\"Inputs\").first().json[\"readers\"] ?? ''),\n};\nconst result = runRule(\"column_quotes_source\", {\"column\":\"Comment (quote)\",\"input\":\"readers\"}, work, sources);\nreturn [{ json: result }];" }, "id": "f3b68bd5-99e7-44dc-acc2-3713db074412", "name": "Check 1: Each comment quote appears in the readers' notes", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 740, 320 ], "notes": "Every quote in the Comment (quote) column appears word for word in the three readers' notes.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "57eafec1-c4e2-4646-acd0-8ed7a9caaefc", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "1033042a-95e6-4af3-a465-06bcf7a13c45", "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": "e13dd1be-e268-4421-aedb-65c450db6b27", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "a5270012-5504-4429-a2e8-d2b4deed0713", "name": "Try again? (check 1)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1000, 520 ], "notes": "True = first failure: send back to \"1. Keep each reader's words separate\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "cd3ecc63-9f7d-464c-a2a1-85f5c3035616", "name": "flag", "value": "=Each comment quote appears in the readers' notes: did not pass. {{ $(\"Check 1: Each comment quote appears in the readers' notes\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "f4a30fb7-704d-48d0-a498-b4e99a1901d2", "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 an editor who reconciles feedback without voting by volume.\n\nYour task is to group comments about the same draft change and label the relationship between readers.\n\nReader comments:\n{{ $(\"1. Keep each reader's words separate\").first().json.text }}\nDraft purpose: {{ $(\"Inputs\").first().json[\"purpose\"] }}\n\nRules:\n- Use exactly agree, conflict or single in the Relationship column.\n- Agree means two or three readers seek compatible changes. Conflict means their requested changes cannot both be applied as stated. Single means only one reader raised the point.\n- Name the readers involved and keep their distinct reasons. Silence is not agreement.\n- Do not invent a consensus or choose a side yet.\n\nReturn one markdown table: | Draft part | Readers and requests | Relationship | What needs deciding |{{ $(\"Check 2: Each group has a clear relationship\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Each group has a clear relationship. What was wrong: \" + $(\"Check 2: Each group has a clear relationship\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "97813084-3e83-4a37-a0bc-bd4ed08dc021", "name": "2. Find agreements and conflicts", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 1260, 320 ], "notes": "Group notes about the same change and show where readers disagree or leave a gap. Returns: A grouped view of agreement, conflict and single-reader points.", "notesInFlow": true }, { "parameters": { "jsCode": "// Each group has a clear relationship\n// Rule: Every row of the table has one of \"agree\", \"conflict\" or \"single\" in the Relationship column.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\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. Find agreements and conflicts\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"column_values_in\", {\"column\":\"Relationship\",\"allowed\":[\"agree\",\"conflict\",\"single\"]}, work, sources);\nreturn [{ json: result }];" }, "id": "b3713688-c131-4297-a7b6-deb6a31afc9d", "name": "Check 2: Each group has a clear relationship", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1520, 320 ], "notes": "Every row of the table has one of \"agree\", \"conflict\" or \"single\" in the Relationship column.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "56eafd2e-c5e2-47d9-abd0-8d44aacab08f", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "902b7ee5-95e3-4c5c-a467-455377a8c18a", "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": "e23dd351-e168-428e-afdb-67574fdb6994", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "9d293211-3d01-4fca-a2e1-4d6f5ef48c58", "name": "Try again? (check 2)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1780, 520 ], "notes": "True = first failure: send back to \"2. Find agreements and conflicts\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "cc3ecad0-a07d-47df-a1a1-8462c40357a9", "name": "flag", "value": "=Each group has a clear relationship: did not pass. {{ $(\"Check 2: Each group has a clear relationship\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "f5a3114a-734d-4d89-a198-b0309919003f", "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 the draft's editor preparing a revision plan.\n\nYour task is to choose a next move for each feedback group.\n\nDraft purpose: {{ $(\"Inputs\").first().json[\"purpose\"] }}\nDraft:\n{{ $(\"Inputs\").first().json[\"draft\"] }}\nGrouped feedback:\n{{ $(\"2. Find agreements and conflicts\").first().json.text }}\nOriginal reader comments:\n{{ $(\"1. Keep each reader's words separate\").first().json.text }}\n\nRules:\n- Use exactly revise, ask or keep in the Decision column.\n- Revise only when the request fits the stated purpose and a concrete edit is possible. Ask when readers conflict or needed facts are missing. Keep when a requested change would undercut the purpose, and explain why.\n- Quote the draft words to change when there is a matching passage. Do not add facts that the draft or notes do not supply.\n- Give each reader's concern an answer, even when the edit is deferred.\n\nReturn one markdown table: | Draft part | Decision | Proposed edit or question | Reader concern answered |{{ $(\"Check 3: Each revision has a supported decision\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Each revision has a supported decision. What was wrong: \" + $(\"Check 3: Each revision has a supported decision\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "5615748e-fc65-41ed-a9fe-8e0c8b0bfee3", "name": "3. Plan the revision", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 2040, 320 ], "notes": "Decide which edit follows the draft purpose and which comment needs an answer. Returns: A revision plan with specific edits and open questions.", "notesInFlow": true }, { "parameters": { "jsCode": "// Each revision has a supported decision\n// Rule: Every row of the table has one of \"revise\", \"ask\" or \"keep\" in the Decision column.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\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($(\"3. Plan the revision\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"column_values_in\", {\"column\":\"Decision\",\"allowed\":[\"revise\",\"ask\",\"keep\"]}, work, sources);\nreturn [{ json: result }];" }, "id": "7783ede2-8411-4d47-a0e5-a3d83fd35d85", "name": "Check 3: Each revision has a supported decision", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 2300, 320 ], "notes": "Every row of the table has one of \"revise\", \"ask\" or \"keep\" in the Decision column.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "55eafb9b-c2e2-4320-aed0-91fdabcab222", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "902dbd7c-15e0-4445-a46a-4d6a77a682f3", "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": "df3dce98-e068-40fb-a0db-68ea52db6e4d", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "c12ba954-58ff-4d47-a6e3-5ff26af260a5", "name": "Try again? (check 3)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 2560, 520 ], "notes": "True = first failure: send back to \"3. Plan the revision\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "cf3ecf89-a17d-4972-a0a1-82cfc10352f0", "name": "flag", "value": "=Each revision has a supported decision: did not pass. {{ $(\"Check 3: Each revision has a supported decision\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "f6a312dd-724d-4bf6-a298-b1c39818feac", "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 an editor replying to three people who reviewed a draft.\n\nYour task is to write a concise response based on the revision plan.\n\nPlan:\n{{ $(\"3. Plan the revision\").first().json.text }}\nReaders' original notes:\n{{ $(\"Inputs\").first().json[\"readers\"] }}\n\nRules:\n- Say what will be revised, what remains a question, and what will be kept with a reason.\n- Where requests conflict, name the tradeoff and the decision needed. Do not say everyone agreed.\n- Do not claim an edit was made if the plan only proposes it. Do not invent a reader reaction.\n\nReturn markdown with headings Planned revisions, Questions to resolve and Response to each reader.{{ $(\"Check 4: Open questions are visible in the response\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Open questions are visible in the response. What was wrong: \" + $(\"Check 4: Open questions are visible in the response\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}{{ $(\"Check 5: Each reader's note has an answer\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Each reader's note has an answer. What was wrong: \" + $(\"Check 5: Each reader's note has an answer\").first().json.text + \"\\nFix that and give your full answer again.\" : \"\" }}" }, "id": "8ab9d39c-d626-40ef-a31f-101eb99d3e39", "name": "4. Write a short feedback response", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 2820, 320 ], "notes": "Summarize changes and explain unresolved comments to the three readers. Returns: A shareable response that keeps the decision and each reader's concern visible.", "notesInFlow": true }, { "parameters": { "jsCode": "// Open questions are visible in the response\n// Rule: The answer includes the words \"Questions to resolve\".\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n const norm = (s) => String(s ?? '')\n .toLowerCase()\n .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n .replace(/\\s+/g, ' ')\n .trim();\n const readTable = (text) => {\n const lines = String(text ?? '')\n .split(/\\r?\\n/)\n .map((l) => l.trim());\n const tables = [];\n let cur = null;\n const cells = (l) => l\n .replace(/^\\|/, '')\n .replace(/\\|$/, '')\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($(\"4. Write a short feedback response\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"has_text\", \"Questions to resolve\", work, sources);\nreturn [{ json: result }];" }, "id": "319cde96-a3b6-4d97-a09b-4f684349f0d9", "name": "Check 4: Open questions are visible in the response", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 3080, 320 ], "notes": "The answer includes the words \"Questions to resolve\".", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "54eafa08-c3e2-44b3-add0-906aaccab3b5", "leftValue": "={{ $json.pass === true }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "903a896f-15f2-4d66-a46c-8c01f7ae0838", "name": "Passed check 4?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3340, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "e03dd02b-df68-4f68-a1db-6a7d51db6cba", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "b91a539b-30fd-4fb8-a6dc-0d0deaf9e5ea", "name": "Try again? (check 4)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3340, 520 ], "notes": "True = first failure: send back to \"4. Write a short feedback response\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "ce3ecdf6-a27d-4b05-afa1-813cc2035483", "name": "flag", "value": "=Open questions are visible in the response: did not pass. {{ $(\"Check 4: Open questions are visible in the response\").first().json.reason }}", "type": "string" } ] }, "options": {} }, "id": "efa307d8-754d-40af-a798-b9a29718fd19", "name": "Flag check 4", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 3470, 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: Each reader's note has an answer\nCompare {{ $(\"1. Keep each reader's words separate\").first().json.text }} with {{ $(\"3. Plan the revision\").first().json.text }} and the response. Does each distinct reader comment get an edit, a question or a reason to keep the draft, and are conflicts still visible? Answer FAIL and name any lost comment.\n\nThe work to check (the answer from Step 4 (Write a short feedback response)):\n{{ $(\"4. Write a short feedback response\").first().json.text }}\n\nReply with exactly PASS or FAIL on the first line. On the second line, say in one sentence why. If it fails, name the exact item or line that fails. Do not add anything else." }, "id": "3ae1e712-4441-48c7-a8e2-20c83ab3b29d", "name": "Check 5: Each reader's note has an answer", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.7, "position": [ 3600, 320 ], "notes": "Answers PASS or FAIL. Compare {{steps.extract}} with {{steps.plan}} and the response. Does each distinct reader comment get an edit, a question or a reason to keep the draft, and are conflicts still visible? Answer FAIL and name any lost comment.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "5beb050d-c8e2-4c92-a8d0-888ba5caa8b0", "leftValue": "={{ String($json.text ?? '').trim().toUpperCase().startsWith('PASS') }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "id": "903cc806-15ef-4ecf-a46e-ca98f7abc9a1", "name": "Passed check 5?", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3860, 320 ], "notes": "True = passed. False = did not pass.", "notesInFlow": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "loose", "version": 2 }, "conditions": [ { "id": "e53dd80a-e668-4a6d-aadb-5f784cdb64db", "leftValue": "={{ $runIndex }}", "rightValue": 0, "operator": { "type": "number", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "id": "1d1d2f9e-bcfa-4a85-aade-cfe086f709e7", "name": "Try again? (check 5)", "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3860, 520 ], "notes": "True = first failure: send back to \"4. Write a short feedback response\" once. False = failed twice: flag it.", "notesInFlow": true }, { "parameters": { "assignments": { "assignments": [ { "id": "d13ed2af-9b7d-4000-aea1-7fa9c7035c62", "name": "flag", "value": "=Each reader's note has an answer: did not pass. {{ $(\"Check 5: Each reader's note has an answer\").first().json.text }}", "type": "string" } ] }, "options": {} }, "id": "f0a3096b-744d-4f1c-a898-bb359618fb86", "name": "Flag check 5", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 3990, 700 ], "notes": "Notes the problem and carries on. The note shows in Result.", "notesInFlow": true }, { "parameters": { "content": "**Check 6: check by hand**\nRead the original three notes beside the draft. Confirm that each proposed edit is feasible, resolve conflicting requests with the decision owner, and check facts before sending a revised draft.\n\nIf not: flag it and carry on. This check is also listed in Result.", "height": 200, "width": 240, "color": 3 }, "id": "e2339055-28c0-495c-a833-d81fce6d7a46", "name": "Check 6 (by hand)", "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 3840, 70 ] }, { "parameters": { "assignments": { "assignments": [ { "id": "3118dbc6-be0d-465f-a741-0bd46fc4c585", "name": "result", "value": "={{ $(\"4. Write a short feedback response\").first().json.text }}", "type": "string" }, { "id": "3289be67-6823-4bac-a881-fc1da6e1089a", "name": "flagged", "value": "={{ [$(\"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 : \"\"].filter(x => x).join(\"\\n\") || \"None\" }}", "type": "string" }, { "id": "49ff64fd-3d0a-4bfa-a67a-7a53c4d55e08", "name": "check_by_hand", "value": "- Read the original three notes beside the draft. Confirm that each proposed edit is feasible, resolve conflicting requests with the decision owner, and check facts before sending a revised draft.", "type": "string" } ] }, "options": {} }, "id": "cc681a73-d009-47c8-a7dd-bef9ad9c163e", "name": "Result", "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 4120, 320 ], "notes": "The final answer, anything flagged, and the checks left for you.", "notesInFlow": true }, { "parameters": { "options": {} }, "id": "ebb36589-c14a-448a-ac59-65bf9780a018", "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. Keep each reader's words separate", "type": "main", "index": 0 } ] ] }, "1. Keep each reader's words separate": { "main": [ [ { "node": "Check 1: Each comment quote appears in the readers' notes", "type": "main", "index": 0 } ] ] }, "Check 1: Each comment quote appears in the readers' notes": { "main": [ [ { "node": "Passed check 1?", "type": "main", "index": 0 } ] ] }, "Passed check 1?": { "main": [ [ { "node": "2. Find agreements and conflicts", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 1)", "type": "main", "index": 0 } ] ] }, "Try again? (check 1)": { "main": [ [ { "node": "1. Keep each reader's words separate", "type": "main", "index": 0 } ], [ { "node": "Flag check 1", "type": "main", "index": 0 } ] ] }, "Flag check 1": { "main": [ [ { "node": "2. Find agreements and conflicts", "type": "main", "index": 0 } ] ] }, "2. Find agreements and conflicts": { "main": [ [ { "node": "Check 2: Each group has a clear relationship", "type": "main", "index": 0 } ] ] }, "Check 2: Each group has a clear relationship": { "main": [ [ { "node": "Passed check 2?", "type": "main", "index": 0 } ] ] }, "Passed check 2?": { "main": [ [ { "node": "3. Plan the revision", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 2)", "type": "main", "index": 0 } ] ] }, "Try again? (check 2)": { "main": [ [ { "node": "2. Find agreements and conflicts", "type": "main", "index": 0 } ], [ { "node": "Flag check 2", "type": "main", "index": 0 } ] ] }, "Flag check 2": { "main": [ [ { "node": "3. Plan the revision", "type": "main", "index": 0 } ] ] }, "3. Plan the revision": { "main": [ [ { "node": "Check 3: Each revision has a supported decision", "type": "main", "index": 0 } ] ] }, "Check 3: Each revision has a supported decision": { "main": [ [ { "node": "Passed check 3?", "type": "main", "index": 0 } ] ] }, "Passed check 3?": { "main": [ [ { "node": "4. Write a short feedback response", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 3)", "type": "main", "index": 0 } ] ] }, "Try again? (check 3)": { "main": [ [ { "node": "3. Plan the revision", "type": "main", "index": 0 } ], [ { "node": "Flag check 3", "type": "main", "index": 0 } ] ] }, "Flag check 3": { "main": [ [ { "node": "4. Write a short feedback response", "type": "main", "index": 0 } ] ] }, "4. Write a short feedback response": { "main": [ [ { "node": "Check 4: Open questions are visible in the response", "type": "main", "index": 0 } ] ] }, "Check 4: Open questions are visible in the response": { "main": [ [ { "node": "Passed check 4?", "type": "main", "index": 0 } ] ] }, "Passed check 4?": { "main": [ [ { "node": "Check 5: Each reader's note has an answer", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 4)", "type": "main", "index": 0 } ] ] }, "Try again? (check 4)": { "main": [ [ { "node": "4. Write a short feedback response", "type": "main", "index": 0 } ], [ { "node": "Flag check 4", "type": "main", "index": 0 } ] ] }, "Flag check 4": { "main": [ [ { "node": "Check 5: Each reader's note has an answer", "type": "main", "index": 0 } ] ] }, "Check 5: Each reader's note has an answer": { "main": [ [ { "node": "Passed check 5?", "type": "main", "index": 0 } ] ] }, "Passed check 5?": { "main": [ [ { "node": "Result", "type": "main", "index": 0 } ], [ { "node": "Try again? (check 5)", "type": "main", "index": 0 } ] ] }, "Try again? (check 5)": { "main": [ [ { "node": "4. Write a short feedback response", "type": "main", "index": 0 } ], [ { "node": "Flag check 5", "type": "main", "index": 0 } ] ] }, "Flag check 5": { "main": [ [ { "node": "Result", "type": "main", "index": 0 } ] ] }, "Chat model": { "ai_languageModel": [ [ { "node": "1. Keep each reader's words separate", "type": "ai_languageModel", "index": 0 }, { "node": "2. Find agreements and conflicts", "type": "ai_languageModel", "index": 0 }, { "node": "3. Plan the revision", "type": "ai_languageModel", "index": 0 }, { "node": "4. Write a short feedback response", "type": "ai_languageModel", "index": 0 }, { "node": "Check 5: Each reader's note has an answer", "type": "ai_languageModel", "index": 0 } ] ] } }, "pinData": {}, "settings": { "executionOrder": "v1" }, "meta": { "template": "reconcile-three-readers-feedback" } }