Hire an AI due diligence document indexer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A document index with name, owner, date, version, location, what it covers and its disclosure status
• A request coverage map showing which files answer each request and which requests have none
• Flags for missing, old and conflicting versions
• A reviewer handover with file locations, owner contacts, limits on disclosure and open requests
• Questions about access that someone must answer before sharing

How it does the job well

• Turn every request into owned actions: who, what and by when.
• Work from the real calendar, notes and lists. Never invent meetings, people or dates.
• Put the most important decision or deadline first, then the details.
• Prepare drafts and proposals. Sending, booking and changing records waits for approval.

Mistakes it avoids

• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.
• Adding process when a short checklist would do.

What a good result looks like

An example, not your task: A buyer, investor or lender has sent a long request list and you must answer it.

• outputs/step-01-source-note-summariser.md. The document index, the request coverage map and flags for missing, old or conflicting versions.
• outputs/step-02-handover-note-writer.md. The reviewer handover with approved file locations, owner contacts, disclosure limits and open requests.
• Access questions. Who may see which files, and who must decide before anything is shared.
• HAND-BACK SUMMARY. Files saved, sources used, MISSING lines, checks missed and one suggested next step.

How the work is checked

• Every fact, date, version and owner traces to a source, or is marked MISSING:.
• No file without approved status appears in the reviewer handover.
• No private contents, password or private link appears.
• Nothing says the set is complete in the legal sense.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Source note summariser. Reads each document and records its purpose, date, version, owner and the requests it answers, without copying private contents. Builds the index and the request coverage map, and flags what is missing, old or in conflict. Hands step 2 the index and the open requests. Check before moving on, each row matches a real file.
• Handover note writer. Writes the reviewer handover from step 1's index, your request list and your disclosure rules. It lists approved file locations, owner contacts, limits on disclosure and unresolved requests. It never includes a password or grants access. Check before sharing, every file it points to has been approved.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id prepare-a-due-diligence-document-index only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/prepare-a-due-diligence-document-index/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The documents you may share, as files or a list with where each is stored
• The reviewer's request list, with request numbers if they have them
• Who owns each document, by name or role
• Your rules on what may be shown and to whom, such as "draft contracts are internal"
• Dates and versions you already know, such as signed or draft (optional)

Helpful context (optional)

• The reviewer's request list, as they sent it.
• A folder export or file list with dates.

Tools and access

• A chat AI that reads many files: It can read each document and build the index in one pass. In plain chat, paste each file's title, date and a few lines.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.
• Any good chat AI: A one-message note works in any strong chat AI.

Functions and deliverables

• Due diligence document indexer: Share approved files, versions and reviewer requests. Get a document index, request coverage map and access questions.
  • A document index with name, owner, date, version, location, what it covers and its disclosure status
  • A request coverage map showing which files answer each request and which requests have none
  • Flags for missing, old and conflicting versions
  • A reviewer handover with file locations, owner contacts, limits on disclosure and open requests
  • Questions about access that someone must answer before sharing
• Source note summariser: Paste an article, talk or chapter into this source note summariser. You get each claim, how well it is backed, the gaps and three quotes to keep.
  • Every claim with a quote and location, and the evidence behind each rated
  • The gaps and assumptions
  • What it adds to your question, three quotes to keep, and an 80-word summary
• Handover note writer: Turn a brain dump into a handover note. The person covering your work sees what breaks first and what is due, and can act on day one.
  • Time bombs first, each with a date and an action
  • What is due, live work with next steps, and where things live
  • The people and how to deal with them, what to leave alone, how to reach you
• India deal due diligence planner: Plan due diligence for an Indian deal. Get workstream requests, owners, status tracking and a separate list of red flags.
  • Checklists by workstream
  • Status tracking columns
  • Red flag notes
  • Priority items for your main concerns
  Source: nighomni123.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• A buyer, investor or lender has sent a long request list and you must answer it.
• Your team keeps two or three versions of the same contract and nobody knows which is final.
• You are building a data room and need a clean list before you upload anything.
• A reviewer asks "who owns this?" and nobody can say.

Limits to check before starting

• You need a lawyer to say the document set is complete: this lists what you hold. It cannot say what is legally required. Ask your counsel.
• You are not sure you may share the files: get approval first. This works only on the set you are allowed to disclose.
• Your data room tool already keeps an index: use that. Run this only to compare it with the request list.
• You want the contents of one contract checked: use the Contract clause and ownership reviewer workflow.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the workflow pack and add it to Claude, ChatGPT or Gemini, in a chat that accepts files.
• Attach the documents you may share, or paste the file list. Paste the request list and your rules on what may be shown.
• Tell your AI to follow the pack and save each step's file.
• After step 1, check the index against your folders. A file missing from the index, or two versions of one file, needs fixing before the handover.
• After step 2, have the person who owns disclosure approve every file the handover points to. Then give it to the reviewer.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-due-diligence-document-index for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.