AI use case

AI for inbound correspondence triage and routing

AI that sorts inbound correspondence before anyone answers it: it takes every inbound letter, email, upload and secure message into one intake, identifies what it is, extracts the key fields, links it to the right customer and account, sets priority and routes it to the right team or workflow, replacing the manual sorting desk.

By Len Debets · Last verified 27 September 2026 · 6 public deployments

91%
Reported accuracy
Travelers, vendor claim.
99%
Reported automation rate
Encova Insurance, organization claim.
USD 500,000 to USD 2.7 million
Indicative value per year
A bank or insurer that receives 1 million inbound letters and emails a year. Worked example, see how it is calculated.

What problem does it solve?

Banks, insurers and public bodies still receive a large share of their work as unstructured correspondence: scanned letters, emails with attachments, portal uploads and secure messages. Someone has to open each item, decide what it is (a complaint, a power of attorney, a bereavement notice, a change of address, a payment instruction), find the customer and send it to the right queue. That sorting step adds delay before anyone starts the real work.

Manual sorting is also where risk hides. A complaint filed as a general enquiry can miss its regulatory deadline, a bereavement letter can sit in the wrong queue, and a fraud warning can be read days late. Rule based keyword routing helps with obvious cases but struggles with free text and mixed documents.

How does it work?

  1. One intake. Post is scanned; emails, uploads and secure messages land in the same queue with their attachments.
  2. Classify. The AI identifies the document or request type, the language and any urgency signal (complaint, vulnerability, fraud, legal deadline), with a confidence score.
  3. Extract and link. It extracts the key fields (names, account numbers, dates, amounts, reference numbers) and matches the item to the customer and account in the core systems.
  4. Route or trigger. It sets the priority and service level, routes the item to the right team, or starts the downstream workflow directly (for example an address change or a bereavement case), with a short summary for the receiving officer.
  5. Fall back to people. Low confidence items, unmatched customers and anything sensitive go to a human review queue, and every correction becomes training data.
Audience
Back office
Autonomy
Supervised agent
Adoption
Mainstream
Channels
Email, Internal tools, API and system to system

What is it worth?

Benchmarks are computed from the public deployments below: one data point per organization per KPI, with who made each claim.

Value benchmarks for AI for inbound correspondence triage and routing
KPIMedianReported rangeData pointsClaimed by
Interactions handledNot pooled
25,000 to 100,000
21 organization, 1 vendor
AccuracyToo few to pool
91%
11 vendor
Automation rateToo few to pool
99%
11 organization

Value drivers: Lower cost to serve, Speed and cycle time, Compliance quality, Employee productivity.

Indicative value

A bank or insurer that receives 1 million inbound letters and emails a year

USD 500,000 to USD 2.7 million

Manual sorting effort avoided per year

How this is calculated

Formula: items * minutesPerItem / 60 * automatedShare * costPerHour. The low scenario uses every low input, the high scenario every high input.

InputLowHighBasis
Inbound items per year items, items per year1,000,0001,000,000The reference organization. Replace with your own mailroom and mailbox volume.
Minutes to read, classify, index and route one item manually minutesPerItem, minutes per item24Editorial assumption, replace with your own time study.
Share of items routed without human touch automatedShare, fraction of items0.50.8Editorial assumption, replace with your own. None of the evidence on this page reports a share of correspondence routed with no human touch; measure it on your own labelled sample before relying on it.
Fully loaded cost per hour of intake staff costPerHour, USD per hour3050Editorial assumption, replace with your own.

What it leaves out: Sorting labour only. It leaves out the value of faster downstream handling, fewer missed complaint deadlines and the cost of scanning, the platform and integration.

Who already uses it?

6 public deployments, strongest evidence first. Grades: A regulator or audit, B the organization itself, C vendor case study, D anonymous or estimate.

U.S. Department of Veterans Affairs

United States · Government and public sector · 2020

ScaledGrade B

The Veterans Benefits Administration runs Mail Automation Services, an intake platform for claims material and other submissions from veterans and their representatives, mostly arriving through the Centralized Mail Portal. It combines form recognition, OCR, handwriting recognition and natural language processing to extract an average of 95 fields from more than 1,500 form layouts and to establish the claim and send each submission to the right business line. The agency reports that it ingests 25,000 to 40,000 packets a day; it has been in operation since 2020.

  • Interactions handled: at least 25,000, packets per day (25,000 to 40,000)
    "The platform ingests and reviews 25k to 40k packets of information per day, primarily derived from the Centralized Mail Portal."
    Claimed by: organization

Loadsure

United Kingdom · Insurance · 2024

ProductionGrade C

Loadsure, a London based insurtech for freight insurance, automated the intake of claim documents such as bills of lading, invoices and shipping documents with Google Cloud Document AI. Each incoming document is first classified and then sent to an extractor built for its type, which feeds the claims verification process; Gemini was later used for a similar extraction workflow elsewhere in the business. The blog post, written by Google Cloud and Loadsure staff, says work that took 30 to 60 minutes per claim now happens in near real time.

No outcome disclosed.

Encova Insurance

United States · Insurance · 2023

ScaledGrade C

Encova Insurance, a US mutual insurer, replaced traditional OCR with UiPath Document Understanding in its claims invoice process, so incoming invoices are read, their data extracted and passed to automated processing, with exceptions fixed by staff in UiPath Action Center. Its solution architect says that traditional OCR got 40% of documents through without issues and that the new process has a 99% success rate, documents processed through without issues, which the vendor headline separately calls 99% accuracy. The vendor also reports that manual data entry time in the wider policy intake automation programme was cut by over 99% over the year.

  • Automation rate: 99%, document understanding success rate on claims invoices, processed through without issues
    "With this new [UiPath] process, the success rate is 99%."
    Claimed by: organization

The Master Trust Bank of Japan

Japan · Banking · 2023

ScaledGrade C

The Master Trust Bank of Japan, a trust bank specialising in asset servicing, uses Rossum's intelligent document processing to read inbound Japanese financial documents such as trade instructions, dividend notices and tax returns, and pass the extracted data to its own robotic process automation. The deployment grew to more than 90 document types used by 10 to 15 departments and 100,000 documents a year. The vendor reports that manual workload fell by 75% and that full processing now takes under 10 minutes instead of up to 1.5 hours per document.

  • Productivity gain: 75%, manual data capture workload
    "The Rossum IDP platform has reduced the manual workload by 75% and improved the time spent verifying and validating documents."
    Claimed by: vendor
  • Interactions handled: 100,000, documents per year
    "To date, Rossum has scaled to handle 100,000 documents per year for MTBJ."
    Claimed by: vendor

Travelers

United States · Insurance · 2023

AnnouncedGrade C

Travelers receives millions of emails a year from agents and customers asking for policy service. With AWS it built a classifier that reads each email and its attachments (Amazon Textract turns PDF attachments into text) and assigns one of 13 service categories with a prompted foundation model (Anthropic's Claude) on Amazon Bedrock; the post says the classifier powers an automation system for these requests but does not confirm that it runs in production. Initial testing without prompt engineering gave 68% accuracy; prompt engineering, condensed categories and better instructions raised it to 91%. The ground truth set held over 4,000 labelled emails.

  • Accuracy: 91%, evaluation accuracy after prompt engineering (testing, not production)
    "After using a variety of techniques with Anthropic’s Claude v2, such as prompt engineering, condensing categories, adjusting document processing process, and improving instructions, accuracy increased to 91%."
    Claimed by: vendor

Ecclesia Group

Germany · Insurance · 2022

ProductionGrade C

Ecclesia Group, a German insurance broker, uses ABBYY to process incoming claims correspondence. The platform extracts key data such as case numbers and licence plates from scanned documents, matches each document to the right record in the customer database and routes it to the responsible claims manager, replacing manual sorting. No outcome figures could be verified.

No outcome disclosed.

How do you implement it?

A model agnostic playbook: what to prepare, the order to build in, and what goes wrong.

Data you need

  • A labelled sample of historical correspondence per request type
  • An agreed taxonomy of request types with owner teams and service levels
  • Customer and account data reachable for matching

Systems to integrate

  • Scanning and mailroom capture
  • Shared mailboxes and secure messaging
  • Core banking or policy administration for customer matching
  • Case management and workflow tools for routing
  • Complaint management system

Complexity: Medium

Classification and extraction are mature. The effort is in the taxonomy of request types, the customer matching against core data and the connections to every downstream queue.

  1. 1

    Build the request taxonomy with the receiving teams

    List the request types, their owner team, priority and service level. Keep it short at first; a catch all class routed to people is better than twenty rare classes.

  2. 2

    Label a real sample

    Label a few thousand recent items, including the messy ones (handwritten, multi topic, forwarded chains), and use them as the test set for every model change.

  3. 3

    Start with classification and summaries only

    Let the AI propose the class and a summary while people still route. Measure accuracy per class before switching routing on.

  4. 4

    Route automatically per class above a confidence threshold

    Switch on automatic routing class by class, with a review queue below the threshold and mandatory human review for complaints, vulnerability and legal documents.

  5. 5

    Trigger downstream workflows

    For simple requests, start the fulfilment workflow directly from the extracted fields instead of dropping a task in a queue.

Guardrails

  • Complaints, vulnerability signals and fraud warnings are always flagged and never auto closed
  • Items below the confidence threshold go to a human review queue
  • Customer matching requires at least two strong identifiers before an item is linked
  • Personal data in documents is masked in logs and model prompts

KPIs to instrument

  • Classification accuracy per class on a weekly sample
  • Share of items routed without human touch
  • Time from receipt to arrival in the right queue
  • Misrouted items reported by receiving teams
  • Complaints identified at intake versus later

Human in the loop

People review low confidence items and every item flagged as a complaint, vulnerability or legal matter. A quality team samples automatically routed items weekly and feeds corrections back into the labelled set.

Common failure modes

A complaint routed as an enquiry
The regulatory clock runs while the item sits in the wrong queue. Treat complaint detection as its own high recall check.
Linked to the wrong customer
A document attached to the wrong account is a data breach. Require strong identifiers and route ambiguous matches to people.
Taxonomy drift
New products and campaigns create request types the model never saw. Review the catch all class monthly.

What are the risks and rules?

EU AI Act

Depends on design

It depends on where the system runs. Classifying and routing a bank's or insurer's correspondence is not a use listed in Annex III, so it is minimal risk: the AI literacy duty of Article 4 applies, and the Article 50 duty to tell people they are dealing with AI does not, because the system does not interact with the sender. Used by or for a public authority in a benefits process covered by Annex III point 5(a), the provider can treat it as not high risk only while it performs a narrow procedural or preparatory task under Article 6(3); the provider must then document that assessment before it goes live (Article 6(4)) and register the system in the EU database (Article 49(2)). If the system evaluates eligibility for benefits or profiles the people who write in, it is high risk, so those judgements stay with people.

Guidance

  • DISP 1.6 Complaints time limit rules (Financial Conduct Authority, Europe). The response deadlines (eight weeks for most complaints, 15 business days for payment services and electronic money complaints) run from the firm's receipt of the complaint, so intake must recognise complaints wherever they arrive.

Controls to put in place

  • Misclassification rate tracked as a model health metric, per class
  • Log of every classification, extracted field and routing decision
  • Separate high recall check for complaints and vulnerability
  • Retention and access controls on scanned documents in line with the records policy

Frequently asked questions

How accurate is AI at classifying inbound correspondence?
Good enough to route most items, not all. In a post written by AWS and Travelers staff, the Travelers policy service email classifier reached 68% accuracy in initial testing and 91% after prompt engineering and condensed categories; the ground truth set had over 4,000 labelled emails in 13 classes. These are test results, not production figures, which is why the design keeps a human review queue below a confidence threshold.
Does this work for scanned paper as well as email?
Yes, once the capture step has turned the scan into text. The US Department of Veterans Affairs reports that its Mail Automation Services platform combines OCR, handwriting recognition and language processing, ingests 25,000 to 40,000 packets a day, mostly from its Centralized Mail Portal, and sends each submission to the right business line.
What should never be routed automatically?
Complaints, signs of customer vulnerability, fraud warnings and legal documents such as court orders and powers of attorney should always be flagged for a person, even when the classifier is confident.

How to cite this page

Blits.ai AI Use Case Library, "AI for inbound correspondence triage and routing", last verified 27 September 2026, https://www.blits.ai/ai-use-cases/correspondence-triage-and-routing. Licensed under CC BY 4.0. Method: how we verify use cases.

Changelog
  • 27 September 2026: First published

Related use cases

Cross industryGovernment and public sector

AI reply drafting for customer email and support tickets

A copilot for asynchronous service work that drafts the reply to an incoming customer email, message or ticket once it has reached an agent: it summarizes the request, pulls the relevant customer data and approved knowledge, and drafts a reply in the organization's tone and the customer's language for the agent to check, edit and send. Live calls and chats, and the sorting of the inbox itself, are separate use cases.

Deployments
6 public, best grade B
Reported cycle time reduction
about 50%
HYPE, vendor claim
Cross industryGovernment and public sector

AI document intelligence for unstructured forms and documents

AI that takes documents in any format, such as scanned forms, PDFs, photos, emails and handwritten notes, splits and classifies them, extracts the required fields with a confidence score, validates them against business rules and source systems, and sends only the uncertain cases to a person before the data enters the downstream process.

Deployments
5 public, best grade B
Reported accuracy
at least 90%
Ancine, vendor claim
Cross industryBanking

AI agent for complaints recognition, investigation and response

An AI agent that recognizes when a customer interaction is a complaint, logs it against the regulatory definition, classifies its root cause and severity, gathers the evidence, drafts the acknowledgement and the response for a human handler to approve, and tracks every statutory deadline until the case is closed.

Deployments
2 public, best grade B
Reported time saved per task
about 5 minutes
Lloyds Banking Group, organization claim
BankingInsurance

AI for back office account servicing execution

AI that executes the servicing requests that land in operations queues, such as address and mandate changes, standing instructions, beneficiary updates, reissues, payoff and reference letters and loan maintenance, by reading the request, checking it against policy and entitlements, and preparing or making the change in core systems under dual control.

Deployments
2 public, best grade C
Reported cycle time reduction
95%
SS&C Technologies, vendor claim
Cross industryBanking

AI for drafting customer letters and outbound notices

AI that drafts the letters and notices operations must send at scale, such as arrears notices, decline letters, complaint responses, servicing confirmations and product change notices, from case data and approved templates and clauses, in the customer's language, for a person to approve where the notice is regulated.

Deployments
5 public, best grade B
Reported cycle time reduction
25%
SS&C GIDS and RS, vendor claim
BankingPayments and cards

AI for payment investigations and exceptions

AI that works the payments that fall out of straight through processing: it reads the failure, repairs or enriches the message, drafts the ISO 20022 or SWIFT investigation, chases the counterparty bank and proposes a return, recall or correction, while an operator approves anything that moves money.

Deployments
2 public, best grade B
Reported automation rate
at least 10%
BNY, organization claim