Skip to app details
Back to app library
APPNEURAL APP FAMILYWorkspace

Assistant

Answers from your work, with the sources shown

Ask questions about your own workspace and files, get answers with citations, and turn them into drafts.

01 / OVERVIEW

See where it fits in your day.

Conversations are private to the person (a team member's email, or the domain's owner for the owner and deployment passcodes); owners and the admin get a 404 for anyone else's conversations, files and drafts. Each question picks its sources: everything the person may see (a Workspace Search query as that person, the best 8 with full text), up to six chosen items re-read on every question, or PDFs up to 10 MB, text and Markdown files and pasted text for that conversation (R2). Claude (claude-opus-5-5) answers from search-result and document blocks with citations turned on, streamed to the page; every citation opens the item or the file with the quoted passage, and when the sources do not cover the question the answer says 'I could not find this in your sources.' (with no sources found, Claude is not called at all). Quick actions summarise, list decisions and action items, compare two items, draft a reply and show what changed this week. Drafts (email, document, note) come from an answer or are written by hand; they are edited and copied, opened in the person's email app through mailto (nothing is sent), or saved to Writer (POST /api/v1/documents) and Notes (POST /api/v1/notes) as private items with the sources listed. 30 questions or AI drafts an hour per person, and each person's monthly questions and tokens shown to owners. Without an Anthropic key the app says what it needs, and drafts still work by hand. No public pages, no feed of its own and no webhooks.

A LOOK INSIDEExample layout · sample content
Assistant
# Conversations# Drafts# Usage
CONVERSATION PREVIEW
A
What did we decide on pricing?
N
Summarise the launch notes
T
Draft a reply to the client
02 / CAPABILITIES

Built around the work you do.

What Assistant does for you.

01

Sources you choose

Everything you may see through Workspace Search, chosen items, or PDFs, text files and pasted text for one conversation.

02

Cited answers

Each answer cites its sources; when they do not cover the question, it says it could not find it instead of guessing.

03

Drafts

Email, document and note drafts you edit, copy, open in your email app, or save to Writer and Notes.

03 / GETTING STARTED

Start small. Build from there.

A suggested path for Assistant. What you can do depends on your access in the app.

01

Pick the sources

Everything I can see, chosen items, or files for this conversation.

02

Ask

Type a question, or use a quick action such as Summarise or Decisions and action items.

03

Draft

Turn the answer into an email, a document or a note, and edit it before you use it.

YOUR NEXT MOVE

Make Assistant part of your workflow.

The app opens in a new tab, so your ecosystem stays close.

Open app
05 / CATALOG DETAILS

The registry record.

Live host, inventory, governance, health checks, verification, dependencies and history.

Catalog surfaceDEPLOYEDHEALTHY
InventoryACTIVE1 items
P2VERIFIEDPUBLISHED
Overview

Purpose and boundaries

Conversations are private to the person (a team member's email, or the domain's owner for the owner and deployment passcodes); owners and the admin get a 404 for anyone else's conversations, files and drafts. Each question picks its sources: everything the person may see (a Workspace Search query as that person, the best 8 with full text), up to six chosen items re-read on every question, or PDFs up to 10 MB, text and Markdown files and pasted text for that conversation (R2). Claude (claude-opus-5-5) answers from search-result and document blocks with citations turned on, streamed to the page; every citation opens the item or the file with the quoted passage, and when the sources do not cover the question the answer says 'I could not find this in your sources.' (with no sources found, Claude is not called at all). Quick actions summarise, list decisions and action items, compare two items, draft a reply and show what changed this week. Drafts (email, document, note) come from an answer or are written by hand; they are edited and copied, opened in the person's email app through mailto (nothing is sent), or saved to Writer (POST /api/v1/documents) and Notes (POST /api/v1/notes) as private items with the sources listed. 30 questions or AI drafts an hour per person, and each person's monthly questions and tokens shown to owners. Without an Anthropic key the app says what it needs, and drafts still work by hand. No public pages, no feed of its own and no webhooks.

Answers and drafts from a person's own workspace: questions answered only from permitted workspace items or the files given to a conversation, with citations, and email, document and note drafts saved to Writer and Notes.

Finding items belongs to Workspace Search; source notebooks and research briefs belong to Research; the website chatbot for visitors belongs to Chatbot.

Priority
P2
Portfolio
Workspace
Capability
Workspace
Technical owner
Not configured
Runtime
Cloudflare Workers / OpenNext
Last verified
2026-11-18 14:03:13
Semantic inventory

Every number says what it counts

1Catalog itemstrackedEntityCount · catalog-api:live
Production-ready gate

Governance evidence required

5 of 18 required controls are configured. Catalog deployment and inventory maturity remain independent until every required control is present.

MissingBusiness owner
MissingProduct owner
MissingTechnical owner
MissingMaintaining team
MissingGitHub repository
ConfiguredProduction URL
ConfiguredHealth endpoint
MissingDocumentation
MissingArchitecture document
MissingCurrent security review
ConfiguredData classification
MissingDependencies
MissingConsumers
MissingSLA / SLO
MissingOn-call
MissingLast release
ConfiguredLast verification
ConfiguredDeprecation status
Catalog details

assistant schema v1

Catalog-specific metadata is not configured.
Live host

Where it runs

assistant.appneurox.com DEPLOYED

assistant.appneurox.com

Worker
assistant-catalog
Health
HEALTHY
Last deployment
2026-11-18 14:03:13
DNS & routing

Confirmed infrastructure only

Provider inspection appears after Cloudflare credentials are configured. Mutations require dry run, idempotency and explicit confirmation.
Repository & architecture

Technical context

APPNEURAL-Catalogs/assistant-catalogLOCAL · NOT CONFIGURED

Documentation

Documentation and architecture evidence are not configured.
Dependencies

Registered relationships

No dependency edges are registered. Nothing has been inferred.
Operations

Checks and verification

No health checks have been recorded.
Security

Review posture

Security review not configured. This does not mean the catalog is secure or insecure.
Automatic reconciliation

GitHub · Cloudflare · DNS · catalog APIs

No synchronization run has completed yet. The scheduled Worker records missing credentials as Not configured, never as success.

Drift findings

No drift has been recorded.
Evidence & history

Trust record

Verification is verified. Run verification to store check-level evidence, confidence, expiry and remediation.

AI workspace

Human-reviewed drafts

AI outputs are saved as drafts with evidence references. They never replace verified catalog fields automatically.

App libraryOpen app