Decide whether AI may be used for a legal task, who drafts and who checks. Australian law.
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Scores the AI option on adoption, efficiency and governance (step 2), caps governance by the recorded evidence, scores the manual route, and returns the decision, its reasons and the order of preference.
The `record` string the previous workflow tool returned, passed back unchanged.
Adoption feasibility: the anchor that is true for this option on this task.
Efficiency likelihood: the anchor that is true for this option on this task.
Governance suitability: the anchor that is true for this option on this task.
The AI option as configured, for example "Claude Code on a Team plan".
A recorded condition that removes the cause of a 2 on adoption or efficiency.
True when a document, setting or check is still outstanding.
Scores the AI option on adoption, efficiency and governance (step 2), caps governance by the recorded evidence, scores the manual route, and returns the decision, its reasons and the order of preference.
| Argument | Type | Description |
|---|---|---|
| record* | string | The `record` string the previous workflow tool returned, passed back unchanged. |
| adoption* | object | Adoption feasibility: the anchor that is true for this option on this task. |
| conditions | object | A recorded condition that removes the cause of a 2 on adoption or efficiency. |
| efficiency* | object | Efficiency likelihood: the anchor that is true for this option on this task. |
| governance* | object | Governance suitability: the anchor that is true for this option on this task. |
| option_name* | string | The AI option as configured, for example "Claude Code on a Team plan". |
| outstanding | boolean | True when a document, setting or check is still outstanding. |
| efficiency_confidence | string |
{
"type": "object",
"required": [
"record",
"option_name",
"adoption",
"efficiency",
"governance"
],
"properties": {
"record": {
"type": "string",
"description": "The `record` string the previous workflow tool returned, passed back unchanged."
},
"adoption": {
"type": "object",
"required": [
"score",
"reason"
],
"properties": {
"score": {
"type": "integer",
"maximum": 5,
"minimum": 1
},
"reason": {
"type": "string"
},
"sub_conditions": {
"type": "array",
"items": {
"enum": [
"A1",
"A2",
"A3",
"A4",
"A5",
"A6"
],
"type": "string"
}
}
},
"description": "Adoption feasibility: the anchor that is true for this option on this task."
},
"conditions": {
"type": "object",
"properties": {
"adoption": {
"type": "string"
},
"efficiency": {
"type": "string"
}
},
"description": "A recorded condition that removes the cause of a 2 on adoption or efficiency."
},
"efficiency": {
"type": "object",
"required": [
"score",
"reason"
],
"properties": {
"score": {
"type": "integer",
"maximum": 5,
"minimum": 1
},
"reason": {
"type": "string"
},
"sub_conditions": {
"type": "array",
"items": {
"enum": [
"E1",
"E2",
"E3",
"E4",
"E5",
"E6"
],
"type": "string"
}
}
},
"description": "Efficiency likelihood: the anchor that is true for this option on this task."
},
"governance": {
"type": "object",
"required": [
"score",
"reason"
],
"properties": {
"score": {
"type": "integer",
"maximum": 5,
"minimum": 1
},
"reason": {
"type": "string"
},
"sub_conditions": {
"type": "array",
"items": {
"enum": [
"G1",
"G2",
"G3",
"G4",
"G5",
"G6",
"G7",
"G8",
"G9",
"G10"
],
"type": "string"
}
}
},
"description": "Governance suitability: the anchor that is true for this option on this task."
},
"option_name": {
"type": "string",
"description": "The AI option as configured, for example \"Claude Code on a Team plan\"."
},
"outstanding": {
"type": "boolean",
"description": "True when a document, setting or check is still outstanding."
},
"efficiency_confidence": {
"enum": [
"low",
"moderate"
],
"type": "string"
}
}
}Returns the AI Law Framework’s rules: the five steps, the three pillars and their anchors, the decision rule, the four levels, the seven stages and their matrix, and the rules that admit no exception.
| Argument | Type | Description |
|---|---|---|
| part | string |
{
"type": "object",
"properties": {
"part": {
"enum": [
"all",
"steps",
"pillars",
"decision",
"levels",
"stages",
"rules"
],
"type": "string"
}
}
}Returns the framework’s notes for one jurisdiction, and which stored AI instruments apply to a task in a court or tribunal. Name the forum, or court "no" when no court is involved. A gap means no instrument is stored for that forum.
| Argument | Type | Description |
|---|---|---|
| task | string | What the work is, in a short phrase. Used to recognise the document and the subject. |
| court | string | no when no court or tribunal is involved. |
| forum | string | A forum code such as "ncat", "federal-court" or "vcat". Omit it to be asked which court applies. |
| audience | string | |
| jurisdiction* | string | A jurisdiction id or slug, for example "NSW", "VIC", "new-zealand". |
| document_type | string | affidavit, witness-statement, expert-report, submissions, pleadings, contract or chronology. |
| personal_information | boolean | True when the work puts personal information into an AI product. |
Returns one published precedent’s details: summary, when to use it, authorities, the AI-use guidance (level, what AI may and must not do, what the lawyer checks), licence, the date it states the law as at and how the library maintains it. The text itself is available through the signed-in firm connector.
| Argument | Type | Description |
|---|---|---|
| precedent_id* | string | The precedent id from search_precedents. |
{
"type": "object",
"required": [
"precedent_id"
],
"properties": {
"precedent_id": {
"type": "string",
"description": "The precedent id from search_precedents."
}
}
}Returns the framework’s research on one AI product and plan: its facts, the governance considerations found, and the cited sources with their review dates. Accepts a profile id or a product name.
| Argument | Type | Description |
|---|---|---|
| product* | string | A profile id from search_library, or a product name such as "Claude Team". |
| controls | array | Optional control ids, such as "trainingUse" or "inferenceRegion", to return only those considerations. |
{
"type": "object",
"required": [
"product"
],
"properties": {
"product": {
"type": "string",
"description": "A profile id from search_library, or a product name such as \"Claude Team\"."
},
"controls": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"description": "Optional control ids, such as \"trainingUse\" or \"inferenceRegion\", to return only those considerations."
}
}
}For a new user, or when asked what this is: what the AI Law Framework decides, the first questions it asks (country, then state or territory), the five steps, the skills and starting prompts, and a fictional sample matter the user can run to see a finished work record.
No arguments.
{
"type": "object",
"properties": {}
}Returns one task from the practice library: how AI may be used, its level, what the lawyer must review, its checkpoints, restrictions and sources, and its jurisdiction versions.
| Argument | Type | Description |
|---|---|---|
| task_id* | string | The task id from search_library, for example "A1-A20260923-1". |
| jurisdiction | string | Optional jurisdiction id or slug, for example "NSW", to include that version. |
{
"type": "object",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"description": "The task id from search_library, for example \"A1-A20260923-1\"."
},
"jurisdiction": {
"type": "string",
"description": "Optional jurisdiction id or slug, for example \"NSW\", to include that version."
}
}
}Sets the level of each of the seven stages of the task (step 3) from the recorded answers, research and decision, and returns what the lawyer and the AI may and may not do at each stage.
| Argument | Type | Description |
|---|---|---|
| record* | string | The `record` string the previous workflow tool returned, passed back unchanged. |
{
"type": "object",
"required": [
"record"
],
"properties": {
"record": {
"type": "string",
"description": "The `record` string the previous workflow tool returned, passed back unchanged."
}
}
}Adds the user’s answers to the clarifying questions to the work record. Returns the questions still open, or, once all are answered, the research the task requires.
| Argument | Type | Description |
|---|---|---|
| record* | string | The `record` string the previous workflow tool returned, passed back unchanged. |
| answers* | object | Answers keyed by question id. `from` is "user" when the user answered when asked, or "request" when the user had already said it (then `quote` holds their words). |
{
"type": "object",
"required": [
"record",
"answers"
],
"properties": {
"record": {
"type": "string",
"description": "The `record` string the previous workflow tool returned, passed back unchanged."
},
"answers": {
"type": "object",
"properties": {
"tool": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Which AI product, plan and settings are in use (for example Claude on a Team plan, or Codex under a ChatGPT Business workspace)?"
},
"state": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"NSW",
"VIC",
"QLD",
"WA",
"SA",
"TAS",
"ACT",
"NT",
"CTH",
"several",
"not_applicable",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "In Australia: which state or territory? Outside Australia, choose not applicable."
},
"sworn": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is any part sworn, affirmed or certified — an affidavit, witness statement or statutory declaration?"
},
"junior": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is the person directing the agent a junior working without supervision?"
},
"output": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "What exactly is being produced, and what must it be right about?"
},
"actions": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "In this setup, can the agent send, file or change a system by itself (email, a court portal, the document management system)?"
},
"country": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"AU",
"NZ",
"US",
"UK",
"UK-SCT",
"UK-NI",
"other"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "In which country is the work done, and whose law applies?"
},
"purpose": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Who will rely on it, and for what decision or step?"
},
"sources": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Which sources may be relied on, and are they available to the agent (documents provided, legislation, cases, firm precedents)?"
},
"template": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is there a firm template or playbook for this task that has already been tested with this tool?"
},
"information": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"public_only",
"confidential",
"personal",
"health",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "What is the most sensitive information the AI will see?"
},
"leaves_firm": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Will it leave the firm — to a client, another party, a court or a regulator?"
},
"responsible": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Who is the responsible lawyer who will check and approve the output?"
},
"substantive": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"substantive",
"procedural_internal",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is it substantive legal work, or procedural or internal?"
},
"jurisdiction": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Which court, tribunal or regulator (if any) will receive it? Say \"none\" if it stays with the firm and the client."
},
"ai_restriction": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"none",
"no_ai_written_content",
"no_ai_at_all",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Does any court rule, client instruction or firm policy restrict AI use on this matter?"
}
},
"description": "Answers keyed by question id. `from` is \"user\" when the user answered when asked, or \"request\" when the user had already said it (then `quote` holds their words).",
"additionalProperties": false
}
}
}Adds research findings, each with its source, quote and confirmation status, to the work record. Returns the required research still missing, or the scoring anchors and the governance ceiling the evidence sets.
| Argument | Type | Description |
|---|---|---|
| record* | string | The `record` string the previous workflow tool returned, passed back unchanged. |
| findings* | array |
{
"type": "object",
"required": [
"record",
"findings"
],
"properties": {
"record": {
"type": "string",
"description": "The `record` string the previous workflow tool returned, passed back unchanged."
},
"findings": {
"type": "array",
"items": {
"type": "object",
"required": [
"item",
"status",
"summary"
],
"properties": {
"item": {
"enum": [
"framework_guidance",
"forum_rules",
"current_law",
"tool_terms",
"capability_evidence"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The passage relied on."
},
"effect": {
"enum": [
"none",
"conditions",
"no_ai_written_content",
"no_ai_at_all"
],
"type": "string",
"description": "For forum_rules: what the rule requires."
},
"status": {
"enum": [
"confirmed",
"public_claim",
"not_confirmed",
"fails"
],
"type": "string"
},
"control": {
"type": "string",
"description": "For tool_terms: the control id this finding answers."
},
"summary": {
"type": "string"
},
"accessed": {
"type": "string",
"description": "Date read, YYYY-MM-DD."
},
"searches": {
"type": "array",
"items": {
"type": "string"
},
"description": "For not_confirmed: where you looked and what you searched for."
},
"source_url": {
"type": "string",
"description": "https:// address of the source read."
},
"source_title": {
"type": "string"
}
}
},
"maxItems": 20
}
}
}Searches the framework’s published practice areas, tasks, jurisdiction versions, jurisdictions, firm-wide obligations and software profiles. Returns titles, ids and ailawframework.com links.
| Argument | Type | Description |
|---|---|---|
| kind | string | |
| limit | integer | |
| query* | string | Words describing the task, area, jurisdiction or product. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"kind": {
"enum": [
"task",
"task-version",
"practice-area",
"obligation",
"jurisdiction",
"software"
],
"type": "string"
},
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"description": "Words describing the task, area, jurisdiction or product."
}
}
}Searches the published precedent library (letters, agreements, clauses, checklists, forms, policies and more for every practice area) by title, summary and when to use it. Returns ids, titles, kinds, practice area ids, jurisdictions and the date each states the law as at. The full text is available through the signed-in firm connector.
| Argument | Type | Description |
|---|---|---|
| area | string | Optional practice area id, for example "A1". |
| limit | integer | |
| query* | string | Words to search for, 2 to 200 characters. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"area": {
"type": "string",
"description": "Optional practice area id, for example \"A1\"."
},
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"description": "Words to search for, 2 to 200 characters."
}
}
}Opens a work record for one legal task and returns the clarifying questions the framework needs answered (step 1, define the task), less any already answered in `answers`. The first two are the country and, in Australia, the state or territory: ask them first. Read the skill ailf://skills/ai-law-framework before the first call.
| Argument | Type | Description |
|---|---|---|
| agent | string | The agent and product doing the work, for example "Claude Code" or "Codex". |
| answers | object | Answers keyed by question id. `from` is "user" when the user answered when asked, or "request" when the user had already said it (then `quote` holds their words). |
| request* | string | The user’s request, in their words. |
{
"type": "object",
"required": [
"request"
],
"properties": {
"agent": {
"type": "string",
"description": "The agent and product doing the work, for example \"Claude Code\" or \"Codex\"."
},
"answers": {
"type": "object",
"properties": {
"tool": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Which AI product, plan and settings are in use (for example Claude on a Team plan, or Codex under a ChatGPT Business workspace)?"
},
"state": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"NSW",
"VIC",
"QLD",
"WA",
"SA",
"TAS",
"ACT",
"NT",
"CTH",
"several",
"not_applicable",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "In Australia: which state or territory? Outside Australia, choose not applicable."
},
"sworn": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is any part sworn, affirmed or certified — an affidavit, witness statement or statutory declaration?"
},
"junior": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is the person directing the agent a junior working without supervision?"
},
"output": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "What exactly is being produced, and what must it be right about?"
},
"actions": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "In this setup, can the agent send, file or change a system by itself (email, a court portal, the document management system)?"
},
"country": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"AU",
"NZ",
"US",
"UK",
"UK-SCT",
"UK-NI",
"other"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "In which country is the work done, and whose law applies?"
},
"purpose": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Who will rely on it, and for what decision or step?"
},
"sources": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Which sources may be relied on, and are they available to the agent (documents provided, legislation, cases, firm precedents)?"
},
"template": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is there a firm template or playbook for this task that has already been tested with this tool?"
},
"information": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"public_only",
"confidential",
"personal",
"health",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "What is the most sensitive information the AI will see?"
},
"leaves_firm": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"yes",
"no",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Will it leave the firm — to a client, another party, a court or a regulator?"
},
"responsible": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Who is the responsible lawyer who will check and approve the output?"
},
"substantive": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"substantive",
"procedural_internal",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Is it substantive legal work, or procedural or internal?"
},
"jurisdiction": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Which court, tribunal or regulator (if any) will receive it? Say \"none\" if it stays with the firm and the client."
},
"ai_restriction": {
"type": "object",
"required": [
"value",
"from"
],
"properties": {
"from": {
"enum": [
"user",
"request"
],
"type": "string"
},
"quote": {
"type": "string",
"description": "The user’s own words, when `from` is \"request\"."
},
"value": {
"enum": [
"none",
"no_ai_written_content",
"no_ai_at_all",
"unsure"
],
"type": "string"
},
"detail": {
"type": "string",
"description": "Anything the user added."
}
},
"description": "Does any court rule, client instruction or firm policy restrict AI use on this matter?"
}
},
"description": "Answers keyed by question id. `from` is \"user\" when the user answered when asked, or \"request\" when the user had already said it (then `quote` holds their words).",
"additionalProperties": false
},
"request": {
"type": "string",
"description": "The user’s request, in their words."
}
}
}Returns the work record as markdown (steps 4 and 5): the task, the evidence, the decision, the plan, what the AI did, and the checks, approval and release left for the lawyer.
| Argument | Type | Description |
|---|---|---|
| notes | string | |
| output* | object | |
| record* | string | The `record` string the previous workflow tool returned, passed back unchanged. |
| agent_did | array | What the AI did, one line per stage worked on. |
| check_points | array | Each high-risk point to check against its document: dates, figures, key advice. |
| lawyer_checkpoints | array | The task’s review points from get_task_guidance. |
{
"type": "object",
"required": [
"record",
"output"
],
"properties": {
"notes": {
"type": "string"
},
"output": {
"type": "object",
"required": [
"title"
],
"properties": {
"title": {
"type": "string"
},
"version": {
"type": "string"
}
}
},
"record": {
"type": "string",
"description": "The `record` string the previous workflow tool returned, passed back unchanged."
},
"agent_did": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"description": "What the AI did, one line per stage worked on."
},
"check_points": {
"type": "array",
"items": {
"type": "object",
"required": [
"point"
],
"properties": {
"point": {
"type": "string"
},
"source": {
"type": "string"
}
}
},
"maxItems": 80,
"description": "Each high-risk point to check against its document: dates, figures, key advice."
},
"lawyer_checkpoints": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 30,
"description": "The task’s review points from get_task_guidance."
}
}
}{
"type": "object",
"required": [
"jurisdiction"
],
"properties": {
"task": {
"type": "string",
"description": "What the work is, in a short phrase. Used to recognise the document and the subject."
},
"court": {
"enum": [
"yes",
"no"
],
"type": "string",
"description": "no when no court or tribunal is involved."
},
"forum": {
"type": "string",
"description": "A forum code such as \"ncat\", \"federal-court\" or \"vcat\". Omit it to be asked which court applies."
},
"audience": {
"enum": [
"lawyer",
"barrister",
"litigant",
"judicial"
],
"type": "string"
},
"jurisdiction": {
"type": "string",
"description": "A jurisdiction id or slug, for example \"NSW\", \"VIC\", \"new-zealand\"."
},
"document_type": {
"type": "string",
"description": "affidavit, witness-statement, expert-report, submissions, pleadings, contract or chronology."
},
"personal_information": {
"type": "boolean",
"description": "True when the work puts personal information into an AI product."
}
}
}