{
  "name": "Compare proposals against source documents",
  "nodes": [
    {
      "parameters": {
        "content": "## Compare proposals against source documents\nCompare proposals for one decision using the documents you supply, show the passage behind each material claim, mark missing evidence, and recommend what to verify before choosing.\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 Claim (quote) column appears word for word in the proposals to compare. If it fails: try once more, then flag.\n- Check 2 (a plain rule, run automatically with no AI): Every quote in the Passage (quote) column appears word for word in the source documents. 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 \"supported\", \"contradicted\" or \"not shown\" in the Status 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 \"Confirm before choosing\". If it fails: try once more, then flag.\n- Check 5 (a second AI prompt answers pass or fail): Compare the claims in {{steps.claims}} with the statuses in {{steps.compare}}. Is each material claim represented, and does the recommendation avoid treating a contradicted or not shown must-have as met? Answer FAIL with the omitted or overstated claim. If it fails: try once more, then flag.\n- Check 6 (you check it by hand): Open the source documents and check each passage used for a must-have. Ask the proposal owner about every contradiction or missing passage before you accept a recommendation. 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": "e2a592f4-6cb1-46a7-a25d-9eb617686309",
      "name": "About this workflow",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -40,
        -620
      ]
    },
    {
      "parameters": {},
      "id": "ebbcdff0-3a1c-4ad7-a200-373a2ce771e1",
      "name": "Start",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        0,
        320
      ]
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "77a5606c-be9e-4753-af67-2ec2e94dd909",
              "name": "proposals",
              "value": "Sample: Cedar Plan: $480 per month, weekly visits, materials included, starts June 3. Harbor Plan: $430 per month, weekly visits, materials included, starts June 10.",
              "type": "string"
            },
            {
              "id": "a6b11fd9-05c8-4226-a444-0dc7210499bc",
              "name": "sources",
              "value": "Sample: Cedar price sheet, May 2: Weekly visits, $480 per month. Materials are included. Earliest start June 3. Harbor email, May 4: Weekly visits, $430 per month. Materials are billed separately. Earliest start June 10.",
              "type": "string"
            },
            {
              "id": "ecf5d70b-c3a7-433a-a58f-5a01723407a0",
              "name": "decision",
              "value": "Sample: Choose office care with weekly visits, materials included and a June start.",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "3c88be19-ad6d-45a0-a4f4-c66fd9ab45a6",
      "name": "Inputs",
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        220,
        320
      ],
      "notes": "Paste your own material here: proposals = Proposals to compare; sources = Source documents; decision = Decision and must-haves.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "promptType": "define",
        "hasOutputParser": false,
        "text": "=You are a careful proposal reader.\n\nYour task is to list the material claims from each proposal that matter to this decision: {{ $(\"Inputs\").first().json[\"decision\"] }}\n\nProposals:\n{{ $(\"Inputs\").first().json[\"proposals\"] }}\n\nRules:\n- Keep the proposal name and quote each claim word for word from the proposal text.\n- Include price, timing, included work and each stated must-have. Split combined promises into separate rows.\n- Do not evaluate a claim yet. Do not invent a claim to fill a gap.\n\nReturn one markdown table: | Proposal | Claim (quote) |{{ $(\"Check 1: Every claim comes from a proposal\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Every claim comes from a proposal. What was wrong: \" + $(\"Check 1: Every claim comes from a proposal\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}"
      },
      "id": "0f034770-c778-4ab3-a0a0-61bea64900b1",
      "name": "1. List the material claims",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        480,
        320
      ],
      "notes": "Put the promises that matter to this decision in rows before weighing either proposal. Returns: A table of relevant claims, each tied to a named proposal.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "jsCode": "// Every claim comes from a proposal\n// Rule: Every quote in the Claim (quote) column appears word for word in the proposals to compare.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n    const norm = (s) => String(s ?? '')\n        .toLowerCase()\n        .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n        .replace(/\\s+/g, ' ')\n        .trim();\n    const readTable = (text) => {\n        const lines = String(text ?? '')\n            .split(/\\r?\\n/)\n            .map((l) => l.trim());\n        const tables = [];\n        let cur = null;\n        const cells = (l) => l\n            .replace(/^\\|/, '')\n            .replace(/\\|$/, '')\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($(\"1. List the material claims\").first().json.text ?? '');\nconst sources = {\n  \"proposals\": String($(\"Inputs\").first().json[\"proposals\"] ?? ''),\n};\nconst result = runRule(\"column_quotes_source\", {\"column\":\"Claim (quote)\",\"input\":\"proposals\"}, work, sources);\nreturn [{ json: result }];"
      },
      "id": "4b2563aa-b103-4637-a162-e34412ce90f1",
      "name": "Check 1: Every claim comes from a proposal",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        740,
        320
      ],
      "notes": "Every quote in the Claim (quote) column appears word for word in the proposals to compare.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "loose",
            "version": 2
          },
          "conditions": [
            {
              "id": "8caa4503-76cd-48ca-a3d8-77e9ed740fd8",
              "leftValue": "={{ $json.pass === true }}",
              "rightValue": "",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "407101c0-4085-4a9f-a8ec-22023fa93729",
      "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": "a36260d0-08ba-41e5-a401-4506f296c7e3",
              "leftValue": "={{ $runIndex }}",
              "rightValue": 0,
              "operator": {
                "type": "number",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "470c6588-e461-4215-ab80-590a0f0dbd97",
      "name": "Try again? (check 1)",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2.2,
      "position": [
        1000,
        520
      ],
      "notes": "True = first failure: send back to \"1. List the material claims\" once. False = failed twice: flag it.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "6ff53da1-aef4-4d10-aa59-8b1b7b0125b2",
              "name": "flag",
              "value": "=Every claim comes from a proposal: did not pass. {{ $(\"Check 1: Every claim comes from a proposal\").first().json.reason }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "11279d85-1ee8-4d84-acf5-afdf1ceaa20e",
      "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 source reader who checks proposals against documents.\n\nYour task is to match every claim below to one passage in the supplied documents.\n\nClaims:\n{{ $(\"1. List the material claims\").first().json.text }}\n\nSource documents:\n{{ $(\"Inputs\").first().json[\"sources\"] }}\n\nRules:\n- Quote the shortest passage that bears on each claim, word for word. Name its source document.\n- If no passage bears on a claim, put None found in Passage and name the source as None.\n- A passage that disagrees with the claim still belongs in the row.\n- Do not use outside knowledge. Do not treat the proposal itself as an independent source.\n\nReturn one markdown table: | Proposal | Claim (quote) | Source | Passage (quote) |{{ $(\"Check 2: Every evidence passage appears in the source documents\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Every evidence passage appears in the source documents. What was wrong: \" + $(\"Check 2: Every evidence passage appears in the source documents\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}"
      },
      "id": "e782e5d4-888d-4109-a316-07b612e155b3",
      "name": "2. Match each claim to a passage",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        1260,
        320
      ],
      "notes": "Find the source words that back or conflict with each claim, keeping source titles visible. Returns: Each proposal claim beside a source passage or None found.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "jsCode": "// Every evidence passage appears in the source documents\n// Rule: Every quote in the Passage (quote) column appears word for word in the source documents.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n    const norm = (s) => String(s ?? '')\n        .toLowerCase()\n        .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n        .replace(/\\s+/g, ' ')\n        .trim();\n    const readTable = (text) => {\n        const lines = String(text ?? '')\n            .split(/\\r?\\n/)\n            .map((l) => l.trim());\n        const tables = [];\n        let cur = null;\n        const cells = (l) => l\n            .replace(/^\\|/, '')\n            .replace(/\\|$/, '')\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($(\"2. Match each claim to a passage\").first().json.text ?? '');\nconst sources = {\n  \"sources\": String($(\"Inputs\").first().json[\"sources\"] ?? ''),\n};\nconst result = runRule(\"column_quotes_source\", {\"column\":\"Passage (quote)\",\"input\":\"sources\"}, work, sources);\nreturn [{ json: result }];"
      },
      "id": "ffb3eb19-0ca0-4aaa-a279-67d3006d8c34",
      "name": "Check 2: Every evidence passage appears in the source documents",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1520,
        320
      ],
      "notes": "Every quote in the Passage (quote) column appears word for word in the source documents.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "loose",
            "version": 2
          },
          "conditions": [
            {
              "id": "8baa4370-77cd-4a5d-a2d8-7656ee74116b",
              "leftValue": "={{ $json.pass === true }}",
              "rightValue": "",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "c07409d7-4082-4c08-a8e4-9cbdbfb0bc6e",
      "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": "a4626263-07ba-4052-a501-4699f196c650",
              "leftValue": "={{ $runIndex }}",
              "rightValue": 0,
              "operator": {
                "type": "number",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "c704e043-bc5e-4486-a382-bd692f14abbc",
      "name": "Try again? (check 2)",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2.2,
      "position": [
        1780,
        520
      ],
      "notes": "True = first failure: send back to \"2. Match each claim to a passage\" once. False = failed twice: flag it.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "6ef53c0e-aff4-4ea3-a959-89887c012745",
              "name": "flag",
              "value": "=Every evidence passage appears in the source documents: did not pass. {{ $(\"Check 2: Every evidence passage appears in the source documents\").first().json.reason }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "0e2798cc-21e8-423d-adf5-b1721beaa07b",
      "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 impartial decision analyst.\n\nYour task is to judge the evidence for each claim and whether each proposal meets the decision's must-haves.\n\nDecision and must-haves: {{ $(\"Inputs\").first().json[\"decision\"] }}\nClaims and evidence:\n{{ $(\"2. Match each claim to a passage\").first().json.text }}\n\nRules:\n- Use exactly supported, contradicted or not shown in the Status column.\n- Supported means the source passage backs the whole claim. Contradicted means it gives a different fact. Not shown means there is no relevant passage.\n- A missing or contradicted must-have cannot be treated as met. Say what needs confirmation.\n- Keep all proposals in the table. Do not average prices or add a fact from memory.\n\nReturn one markdown table: | Proposal | Material point | Status | Source or gap | Must-have impact |{{ $(\"Check 3: Each material point has one evidence status\").isExecuted ? \"\\n\\nYour last answer did not pass this check: Each material point has one evidence status. What was wrong: \" + $(\"Check 3: Each material point has one evidence status\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}"
      },
      "id": "a97e7cbf-3418-4f56-a47c-8e1de4bc599c",
      "name": "3. Compare support and fit",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        2040,
        320
      ],
      "notes": "Separate backed, contradicted and missing claims before applying the must-haves. Returns: A comparison showing what is supported and what prevents a decision.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "jsCode": "// Each material point has one evidence status\n// Rule: Every row of the table has one of \"supported\", \"contradicted\" or \"not shown\" in the Status column.\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n    const norm = (s) => String(s ?? '')\n        .toLowerCase()\n        .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n        .replace(/\\s+/g, ' ')\n        .trim();\n    const readTable = (text) => {\n        const lines = String(text ?? '')\n            .split(/\\r?\\n/)\n            .map((l) => l.trim());\n        const tables = [];\n        let cur = null;\n        const cells = (l) => l\n            .replace(/^\\|/, '')\n            .replace(/\\|$/, '')\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. Compare support and fit\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"column_values_in\", {\"column\":\"Status\",\"allowed\":[\"supported\",\"contradicted\",\"not shown\"]}, work, sources);\nreturn [{ json: result }];"
      },
      "id": "5124857c-a21a-4375-ad1c-c4d68a92ef37",
      "name": "Check 3: Each material point has one evidence status",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        2300,
        320
      ],
      "notes": "Every row of the table has one of \"supported\", \"contradicted\" or \"not shown\" in the Status column.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "loose",
            "version": 2
          },
          "conditions": [
            {
              "id": "8eaa4829-74cd-45a4-a1d8-74c3ef7412fe",
              "leftValue": "={{ $json.pass === true }}",
              "rightValue": "",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "c076486e-4080-4d71-a8e6-db54bfae7dd7",
      "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": "a56263f6-06ba-4ebf-a201-41e0f496cb09",
              "leftValue": "={{ $runIndex }}",
              "rightValue": 0,
              "operator": {
                "type": "number",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "2b07bc46-585b-4883-a785-996c0b123479",
      "name": "Try again? (check 3)",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2.2,
      "position": [
        2560,
        520
      ],
      "notes": "True = first failure: send back to \"3. Compare support and fit\" once. False = failed twice: flag it.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "6df53a7b-b0f4-4036-ac59-8e417901228c",
              "name": "flag",
              "value": "=Each material point has one evidence status: did not pass. {{ $(\"Check 3: Each material point has one evidence status\").first().json.reason }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "0f279a5f-20e8-40aa-aef5-b3051aea9ee8",
      "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 decision advisor who states uncertainty plainly.\n\nYour task is to write a short decision note from the evidence comparison.\n\nDecision: {{ $(\"Inputs\").first().json[\"decision\"] }}\nComparison:\n{{ $(\"3. Compare support and fit\").first().json.text }}\nProposals:\n{{ $(\"Inputs\").first().json[\"proposals\"] }}\n\nRules:\n- Name the strongest supported option, or say that no choice is ready if a material must-have is unverified.\n- Give at most three reasons linked to the comparison rows, and name one tradeoff.\n- List the exact questions to ask before signing. Treat a proposal claim with no independent passage as unverified.\n- Do not imply that a source was checked outside the documents above. Do not add estimates or facts.\n\nReturn markdown with these headings: Recommendation, Evidence, Tradeoff, Confirm before choosing.{{ $(\"Check 4: The note includes a confirmation list\").isExecuted ? \"\\n\\nYour last answer did not pass this check: The note includes a confirmation list. What was wrong: \" + $(\"Check 4: The note includes a confirmation list\").first().json.reason + \"\\nFix that and give your full answer again.\" : \"\" }}{{ $(\"Check 5: The comparison does not lose a material claim\").isExecuted ? \"\\n\\nYour last answer did not pass this check: The comparison does not lose a material claim. What was wrong: \" + $(\"Check 5: The comparison does not lose a material claim\").first().json.text + \"\\nFix that and give your full answer again.\" : \"\" }}"
      },
      "id": "ab39af98-a6c0-45dd-a6a6-ff7e9d014b8b",
      "name": "4. Write a conditional decision note",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        2820,
        320
      ],
      "notes": "Make a recommendation only as far as the source evidence permits. Returns: A conditional recommendation and a short list of source gaps to resolve.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "jsCode": "// The note includes a confirmation list\n// Rule: The answer includes the words \"Confirm before choosing\".\n// Runs with no AI. Returns pass (true or false) and a reason.\nconst runRule = function runRule(rule, value, work, sources) {\n    const norm = (s) => String(s ?? '')\n        .toLowerCase()\n        .replace(/[\\u2018\\u2019\\u201c\\u201d\"'`]/g, '')\n        .replace(/\\s+/g, ' ')\n        .trim();\n    const readTable = (text) => {\n        const lines = String(text ?? '')\n            .split(/\\r?\\n/)\n            .map((l) => l.trim());\n        const tables = [];\n        let cur = null;\n        const cells = (l) => l\n            .replace(/^\\|/, '')\n            .replace(/\\|$/, '')\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 conditional decision note\").first().json.text ?? '');\nconst sources = {\n\n};\nconst result = runRule(\"has_text\", \"Confirm before choosing\", work, sources);\nreturn [{ json: result }];"
      },
      "id": "fcf30200-3347-43b5-a3dd-71cab943d2cf",
      "name": "Check 4: The note includes a confirmation list",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        3080,
        320
      ],
      "notes": "The answer includes the words \"Confirm before choosing\".",
      "notesInFlow": true
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "loose",
            "version": 2
          },
          "conditions": [
            {
              "id": "8daa4696-75cd-4737-a0d8-7330f0741491",
              "leftValue": "={{ $json.pass === true }}",
              "rightValue": "",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "c064ff4d-407e-4eda-a8f3-a747bfa1b1e4",
      "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": "a6626589-05ba-4d2c-a301-4373f396c976",
              "leftValue": "={{ $runIndex }}",
              "rightValue": 0,
              "operator": {
                "type": "number",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "ab13beb9-606d-4e3c-af74-43b38b063206",
      "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 conditional decision note\" once. False = failed twice: flag it.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "6cf538e8-b1f4-41c9-ab59-8cae7a01241f",
              "name": "flag",
              "value": "=The note includes a confirmation list: did not pass. {{ $(\"Check 4: The note includes a confirmation list\").first().json.reason }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "0c2795a6-1be8-48cb-a7f5-a80021eaa9ed",
      "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: The comparison does not lose a material claim\nCompare the claims in {{ $(\"1. List the material claims\").first().json.text }} with the statuses in {{ $(\"3. Compare support and fit\").first().json.text }}. Is each material claim represented, and does the recommendation avoid treating a contradicted or not shown must-have as met? Answer FAIL with the omitted or overstated claim.\n\nThe work to check (the answer from Step 4 (Write a conditional decision note)):\n{{ $(\"4. Write a conditional decision note\").first().json.text }}\n\nReply with exactly PASS or FAIL on the first line. On the second line, say in one sentence why. If it fails, name the exact item or line that fails. Do not add anything else."
      },
      "id": "9238e658-a9db-4f3d-a903-2c962023a25b",
      "name": "Check 5: The comparison does not lose a material claim",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.7,
      "position": [
        3600,
        320
      ],
      "notes": "Answers PASS or FAIL. Compare the claims in {{steps.claims}} with the statuses in {{steps.compare}}. Is each material claim represented, and does the recommendation avoid treating a contradicted or not shown must-have as met? Answer FAIL with the omitted or overstated claim.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "loose",
            "version": 2
          },
          "conditions": [
            {
              "id": "90aa4b4f-72cd-427e-a7d8-7e35f1741624",
              "leftValue": "={{ String($json.text ?? '').trim().toUpperCase().startsWith('PASS') }}",
              "rightValue": "",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "c0673de4-c07b-46c3-a8f5-e5debf9f734d",
      "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": "a762671c-04ba-4b99-a801-4b52f696ce2f",
              "leftValue": "={{ $runIndex }}",
              "rightValue": 0,
              "operator": {
                "type": "number",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "cf1635fc-3c6a-46f9-a376-baf627035603",
      "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 conditional decision note\" once. False = failed twice: flag it.",
      "notesInFlow": true
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "73f543ed-b2f4-435c-ae59-916777011f66",
              "name": "flag",
              "value": "=The comparison does not lose a material claim: did not pass. {{ $(\"Check 5: The comparison does not lose a material claim\").first().json.text }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "0d279739-1ae8-4738-a8f5-a99320eaa85a",
      "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**\nOpen the source documents and check each passage used for a must-have. Ask the proposal owner about every contradiction or missing passage before you accept a recommendation.\n\nIf not: flag it and carry on. This check is also listed in Result.",
        "height": 200,
        "width": 240,
        "color": 3
      },
      "id": "4f9519b3-700d-47e8-a01c-546dad5c5aaa",
      "name": "Check 6 (by hand)",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        3840,
        70
      ]
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "e57b8548-b630-416b-a416-035e3cdff139",
              "name": "result",
              "value": "={{ $(\"4. Write a conditional decision note\").first().json.text }}",
              "type": "string"
            },
            {
              "id": "ca8ce779-7179-4800-a6d5-486f0511f906",
              "name": "flagged",
              "value": "={{ [$(\"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": "5a77883f-6d60-4b5e-a979-48053fa76f74",
              "name": "check_by_hand",
              "value": "- Open the source documents and check each passage used for a must-have. Ask the proposal owner about every contradiction or missing passage before you accept a recommendation.",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "41e9cf05-e01a-4dbc-a6ff-4b9bfd4b503a",
      "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": "74848dcb-e56a-448e-abb3-fac19a620414",
      "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. List the material claims",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "1. List the material claims": {
      "main": [
        [
          {
            "node": "Check 1: Every claim comes from a proposal",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check 1: Every claim comes from a proposal": {
      "main": [
        [
          {
            "node": "Passed check 1?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Passed check 1?": {
      "main": [
        [
          {
            "node": "2. Match each claim to a passage",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Try again? (check 1)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Try again? (check 1)": {
      "main": [
        [
          {
            "node": "1. List the material claims",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Flag check 1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Flag check 1": {
      "main": [
        [
          {
            "node": "2. Match each claim to a passage",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "2. Match each claim to a passage": {
      "main": [
        [
          {
            "node": "Check 2: Every evidence passage appears in the source documents",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check 2: Every evidence passage appears in the source documents": {
      "main": [
        [
          {
            "node": "Passed check 2?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Passed check 2?": {
      "main": [
        [
          {
            "node": "3. Compare support and fit",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Try again? (check 2)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Try again? (check 2)": {
      "main": [
        [
          {
            "node": "2. Match each claim to a passage",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Flag check 2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Flag check 2": {
      "main": [
        [
          {
            "node": "3. Compare support and fit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "3. Compare support and fit": {
      "main": [
        [
          {
            "node": "Check 3: Each material point has one evidence status",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check 3: Each material point has one evidence status": {
      "main": [
        [
          {
            "node": "Passed check 3?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Passed check 3?": {
      "main": [
        [
          {
            "node": "4. Write a conditional decision note",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Try again? (check 3)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Try again? (check 3)": {
      "main": [
        [
          {
            "node": "3. Compare support and fit",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Flag check 3",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Flag check 3": {
      "main": [
        [
          {
            "node": "4. Write a conditional decision note",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "4. Write a conditional decision note": {
      "main": [
        [
          {
            "node": "Check 4: The note includes a confirmation list",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check 4: The note includes a confirmation list": {
      "main": [
        [
          {
            "node": "Passed check 4?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Passed check 4?": {
      "main": [
        [
          {
            "node": "Check 5: The comparison does not lose a material claim",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Try again? (check 4)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Try again? (check 4)": {
      "main": [
        [
          {
            "node": "4. Write a conditional decision note",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Flag check 4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Flag check 4": {
      "main": [
        [
          {
            "node": "Check 5: The comparison does not lose a material claim",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check 5: The comparison does not lose a material claim": {
      "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 conditional decision note",
            "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. List the material claims",
            "type": "ai_languageModel",
            "index": 0
          },
          {
            "node": "2. Match each claim to a passage",
            "type": "ai_languageModel",
            "index": 0
          },
          {
            "node": "3. Compare support and fit",
            "type": "ai_languageModel",
            "index": 0
          },
          {
            "node": "4. Write a conditional decision note",
            "type": "ai_languageModel",
            "index": 0
          },
          {
            "node": "Check 5: The comparison does not lose a material claim",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "meta": {
    "template": "compare-proposals-against-sources"
  }
}