TL;DR

Wealth-management email desks · Gmail today
AI classifies & extracts · humans send
Single-tenant Docker · full audit trail

InboxOS — by AutonomeX

Let AI handle the routine. Keep humans on what matters.

For private-banking and wealth-management client-email desks — AutonomeX builds the platform; InboxOS is the product.

InboxOS ingests client email, runs a governed multi-agent analysis pipeline, and routes work to the right queue — with full audit trails and human review before anything is sent.

9-agent LangGraph pipeline
Wealth Management pack shipped
Human approval before every send

Book a demo See the AI pipeline

InboxOS Email Work Queue showing classified tickets with intent, risk level, and human-review process status — Live product — Email Work Queue

Product scope

Shipped today

Gmail IMAP ingest and SMTP send
9-agent LangGraph classification pipeline
Wealth Management industry pack
RBAC, JWT auth, append-only audit log
Docker single-tenant deployment
Human review before outbound send

On the roadmap

Outlook and additional email connectors
SSO / enterprise identity
Multi-tenant SaaS
Additional industry packs (insurance, legal, healthcare)
PostgreSQL and expanded deployment options

The problem

Email overload in regulated client operations

Wealth management, private banking, and similar desks receive high volumes of unstructured client email — each message carrying compliance risk, missing context, and SLA pressure.

Volume outpaces headcount Relationship managers and support teams triage the same categories repeatedly — account changes, transfers, document requests — with no consistent routing.
Regulatory exposure Every reply is a record. Ad-hoc handling makes audit reconstruction slow and error-prone.
Context scattered across threads Follow-ups, attachments, and prior requests live in inboxes — not in a structured ticket line.

Built for private-banking and wealth-management support desks — where every email is a compliance artifact.

Unstructured inbox volume

Re: Beneficiary update — urgent

Fwd: Tax document request

Account closure — follow up

Wire instructions attached

Portfolio rebalance question

Typical desk: Gmail today · Outlook on roadmap

How it works

From inbox to resolved ticket — in four steps

A single-tenant deployment watches your Gmail inbox, classifies each message, and surfaces structured work to your team.

01 — Ingest

Ingest

IMAP fetch from Gmail, MIME parsing, PDF attachment text extraction, and deduplication into a durable ticket store.

02 — Analyze

Analyze

A LangGraph pipeline scores sentiment, classifies intent, extracts required fields, and assesses risk — logged step by step.

03 — Route

Route

The Decision Engine assigns each email to autonomous or human-review queues based on configurable confidence and risk rules.

04 — Resolve

Resolve

Staff review, edit drafts, assign owners, and send replies — every action recorded in an append-only audit log.

Day in the life

One client email — start to finish

A wire-transfer request shows how ingest, AI analysis, human review, and audit logging fit together. No auto-reply — staff approve every outbound message.

1

Client sends email

“Please transfer 1 billion from acc 1 to acc 2”

Arrives in your monitored Gmail inbox like any other client message.
2

Ingest & classify

IMAP fetch, dedupe, and the nine-agent pipeline run — sentiment scored, intent identified as Transfers from the Wealth Management pack.
3

Structured extraction

Required fields populate: Amount, Source Account, Destination Account. Missing fields (e.g. Date Required) are flagged — not guessed.
4

Routed to human review

High intent risk → Human Review Required queue — even when confidence is moderate. The Decision Engine applies your configured rules.
5

RM reviews & sends

Staff verify extraction, edit fields, review the author-agent draft if needed, and explicitly send. Every hop logged in the Agentic AI Timeline.

InboxOS ticket detail with AI extraction of transfer fields and high-risk intent badge — Ticket detail — AI extraction with human verification

Agentic AI Timeline modal showing orchestration steps and prompt versions per email — Agentic AI Timeline — reconstructable audit trace

Differentiator

Nine agents — one orchestrated graph

Not a single prompt. A LangGraph state machine routes each email through specialized agents. The orchestrator picks the next hop each cycle; watch tower scores priority and risk before the Decision Engine.

Entry

Sentiment Analysis

Urgency score 1–10

Classify

Classification

Pack-defined categories

Intent

Intent Agent

Sub-intents + confidence

Fallback

Miscellaneous

Out-of-taxonomy mail

Router

Orchestrator

LLM ReAct loop — routes between all agents until watch tower

Context

History Agent

New / follow-up / duplicate

Extract

Extraction Agent

Structured required fields

Draft

Author Agent

Clarification drafts — human sends

Score

Watch Tower

Priority, risk, confidence → Decision Engine

Dashed paths — orchestrator routing decisions (non-linear) Solid flow — sentiment → orchestrator → agents → watch tower

Every hop is logged in the Agentic AI Timeline — prompt versions, parsed outputs, and routing triggers — so compliance and ops teams can reconstruct why a ticket landed where it did.

Agentic AI Timeline showing eleven logged orchestration steps for a classified email — Full trace visible per email — prompt versions included

Platform

Built for operations teams, not chat demos

A React queue UI on top of a Flask API — role-aware views, structured extraction, and analytics your supervisors already expect.

Queue views

Autonomous, manual review, and no-action queues with filters, assignment, and ticket ageing.

Information extraction

Required fields per intent, editable in place. Human edits flip touchless validation off.

Draft replies

Author agent proposes clarification emails. Staff review and edit before send.

Assignment & RBAC

JWT auth with role permissions. Assign tickets to RM, support, CSA, or escalation owners.

Analytics

Volume, sentiment, ticket ageing, and queue throughput — export-ready for ops reviews.

Audit & admin

Append-only audit log, job-run history, and admin triggers — every sensitive action recorded.

Decision engine

Autonomous where safe. Human where it counts.

Touchless does not mean unsupervised. The Decision Engine applies configurable rules — default: high confidence and low risk — before an email enters the autonomous queue.

Default autonomy rule

Thresholds live in config — not hardcoded — so your compliance team sets the bar.

IF confidence ≥ 7 AND intent_risk == "low" THEN → Autonomous queue
ELSE → Human review queue

Autonomous tickets are closed without manual handling — but outbound email always passes human review before send. High-risk or low-confidence work stays in HITL queues with full agent logs attached.

Autonomous queue

Structured, low-risk, high-confidence

Routing and field extraction without desk intervention
Ideal for repeatable intents in the active industry pack
Still fully auditable — every agent hop logged

Human review queue

Escalations, edits, and send approval

Medium or high intent risk, or confidence below threshold
Staff edit extracted fields and draft replies
Explicit send action — no auto-reply to clients

Industry packs

Domain knowledge in packs — not in core code

Intents, prompts, risk matrices, and required fields ship as versioned YAML packs. Swap packs to adapt the pipeline — without rewriting agents.

Shipped

Wealth Management

Private banking and wealth-management support desks — 4 categories, 13 intents, versioned prompts.

Portfolio handling, account changes, transfers
Information requests with structured required inputs
Per-intent priority and intent-risk metadata

Platform

Pack framework for any vertical

The core platform is industry-agnostic. Additional verticals are configured — not assumed out of the box.

Insurance, legal, healthcare — roadmap verticals
Custom packs for your taxonomy and compliance language
Prompt registry tracks version per classification run

Security & data

Questions compliance teams ask first

Plain answers — no marketing gloss. Forward this section or download the one-pager for your review committee.

Download one-pager (print to PDF)

Where does client email content go during AI analysis?

Email bodies and attachment text are processed by the LLM provider you configure (OpenAI via API today) to classify intent and extract fields. Messages are sent through the provider’s API — not used to train public models under standard OpenAI API terms. All classification results, extracted fields, and agent logs are stored in your deployment’s database (SQLite by default; PostgreSQL on roadmap).

Can the AI email clients without a human?

No in the current release. The author agent may draft clarification emails when required fields are missing, but outbound send requires explicit staff action in the queue UI. feature_flags.autonomous_send ships off by design.

How do we reconstruct why a ticket was routed?

Every agent hop is logged in the Agentic AI Timeline — orchestrator routing triggers, parsed LLM outputs, and prompt versions used per run. Sensitive UI actions (assignment, send, admin triggers) append to an immutable audit log.

Who can access what in the application?

JWT authentication with role-based permissions gates queue views, ticket edits, sends, and admin surfaces. Roles include Relationship Manager, Support Professional, Client Service Associate, Escalation Specialist, and admin — each mapped to specific API permissions.

How is InboxOS deployed — is our data multi-tenant?

Today: Docker single-tenant — one organization per instance on your infrastructure. Email credentials and API keys resolve through configurable secret refs, not source code. Multi-tenant SaaS is roadmap, not current product.

What integrations are supported today?

Gmail via IMAP ingest and SMTP send. Outlook and additional connectors are on the roadmap — not claimed as shipped. SSO and enterprise identity are also roadmap items.

Enterprise readiness

Trust strip — what compliance buyers ask first

RBAC

JWT authentication with permission-gated routes. Roles map to queue actions, admin jobs, and audit access.

Append-only audit log

Auth events, assignment changes, and sensitive ticket actions recorded immutably for reconstruction.

Docker single-tenant

Deploy on your infrastructure today — one organization per instance. Multi-tenant SaaS is roadmap, not current product.

Human review before send

AI drafts; people approve. No unsupervised client-facing replies in the current release.

Who it's for

Internal teams on regulated client email

Customers interact by email only. Your staff work tickets in InboxOS — with views tuned to how each role operates.

Relationship Manager

Own the client relationship

Review high-touch threads, approve drafts, and keep context on complex portfolios without re-reading entire chains.

Support Professional

Clear the operational queue

Work manual-review tickets with pre-extracted fields, suggested intents, and clarification drafts ready to edit.

Client Service Associate

Handle volume with consistency

Route routine account and document requests through structured workflows — less copy-paste from old threads.

Escalation Specialist

Intervene on risk and exceptions

Prioritize by sentiment and intent risk, override AI extraction, and assign ownership when cases cross desks.

Next step

See InboxOS on your workflows

Walk through ingest, the nine-agent pipeline, and human review queues with your compliance and ops stakeholders. Gmail integration today; additional connectors on the roadmap.

Typical demo: 30 minutes · ops + compliance welcome · response within 1 business day

Prefer email directly? sam@autonomex.ai