Back to all use cases

Use case • Accounting & Professional Services

AI inbox copilot for a small accountancy firm

Monitors a shared Outlook inbox, classifies every incoming client email, decides if a reply or follow-up action is needed, and drafts or sends responses grounded in the firm's knowledge. The team went from manually triaging >50 client emails a day to reviewing high-quality drafts, one-click approvals and focusing on edge cases.

1,500-2,400
Emails triaged / month
~50h
Time saved / month
≈70%
Replies auto-drafted
-40% vs naive
LLM calls avoided
~50h / agent / month saved

What this agent does for the team

Built for a growing accountancy startup handling dozens of client emails every day across tax, payroll, and general queries.

Inbox classification & routing
Every incoming email is classified by topic, client, sentiment and context, then moved into the right folder or queue inside Outlook.
Priority & action detection
The agent scores priority (low / medium / high) and detects whether the sender expects a reply or follow-up action from the firm.
Autodraft & optional autoreply
For eligible emails, the agent drafts a professional, human-like reply grounded in the firm’s knowledge base and tone. Depending on configuration, it can send automatically or save as a draft for review.
Knowledge-aware responses
The reply generator uses a vector knowledge base (Qdrant + OpenAI embeddings) to pull relevant policies, product docs and previous answers. Retraining is a deliberate step, so you stay in control of when new or updated documents affect replies.
High-priority alerts
High-priority emails (for example, regulatory deadlines or angry clients) trigger notifications for the relevant accountant or team channel.
Full logging & evaluation
Decisions and outcomes are logged to private Google Sheets for auditing, refinement and regular evaluation against a curated dataset.

Before vs after

Before

One support/admin staff member manually triaged >50 emails / day: categorising, forwarding to accountants, responding to routine questions, and chasing missing information.

After

The inbox is auto-classified and prioritised. Routine queries arrive pre-drafted or already sent; complex cases land in the right folder with clear labels, so the team spends most of their time on approvals and edge cases instead of inbox triage.

Inbox coverage
All inbound email
Languages
Currently English & Romanian; extendable to additional languages

How the inbox copilot works

A chain of specialised AI decisions orchestrated in n8n, backed by a vector knowledge base and logging in Google Sheets.

1. Listen to the shared inbox

An n8n workflow monitors a shared Microsoft Outlook inbox. Each new email triggers the agent with message body, headers, thread context and basic metadata.

Microsoft Outlook • n8n trigger
Step 1

2. Multi-dimensional classification

The first AI step classifies the email into labels (e.g., tax return, payroll, onboarding), priority (low / medium / high), whether a reply is expected, and whether further action is required.

Intent & topic • Priority scoring • Reply / action expectation
Step 2

3. Move & organise the inbox

Based on the classification, the email is labelled and moved into the right folder in Outlook, keeping the primary Inbox clean and organised for the team.

Label & folder routing
Step 3

4. Search the knowledge base

If a reply may be needed, the agent queries a vector database in Qdrant using OpenAI embeddings to find relevant documents: policies, FAQs, historic answers or templates.

Qdrant vector search • OpenAI embeddings
Step 4

5. Draft or send a reply

Using the classification, KB snippets and email thread, the agent drafts a human-like reply. Depending on the `agent.enable_autoreply` flag, it either sends directly (marking the email as read) or saves a draft for a human to review and send.

Grounded generation • Draft or autorespond
Step 5

6. Notify on high-priority emails

For high-priority or sensitive topics, the workflow sends a notification so someone can review quickly — even if an initial draft was prepared automatically.

Priority alerts
Step 6

7. Log & evaluate decisions

Key decisions (classification, priority, reply/no-reply, actions) are logged to private Google Sheets for monitoring. A separate evaluation sheet holds test cases and metrics to validate changes before rollout.

Runtime logger sheet • Evaluation sheet
Step 7

Tech stack for this agent

n8n
Main orchestrator for triggers, branching logic and external integrations.
Microsoft Outlook
Shared inbox for incoming client emails, folder management and draft storage.
OpenAI
Classification, prioritisation and reply generation models.
Qdrant
Vector store powering semantic search over the firm’s knowledge base.
Knowledge base
Curated policies, docs and previous answers ingested into embeddings.
Google Drive & Sheets
Private logging (runtime) and evaluation datasets with metrics.
Other inboxes & helpdesks
Pattern can be adapted to Gmail, shared mailboxes or ticketing tools like Zendesk/Help Scout.
Logging & evaluation

Every classification, priority decision and reply action is logged to private Google Sheets: one for runtime logging, and one for evaluation scenarios and metrics. When prompts or logic change, we re-run evaluations before pushing to production, so you can see accuracy and behaviour improve over time instead of “trusting the model”.

Private logger in Google Sheets
Evaluation dataset & metrics

Safety, control & human oversight

Designed so the firm can start with review-only drafts, then selectively enable full autoresponding where it’s safe.

Human-in-the-loop by default

The firm started with `agent.enable_autoreply = false`, so all messages were drafted but not sent. Staff reviewed, edited and sent replies while building trust in the system.

Scoped knowledge & access

The agent is restricted to a vetted knowledge base and specific mailboxes. It cannot invent new policies or send messages outside the authorised accounts.

Tested on edge cases

A separate evaluation workflow runs the agent against tricky scenarios (ambiguous emails, partial data, sensitive topics) and logs metrics before any major change is deployed.

Want a similar automation for your team?

We adapt this pattern to your stack, compliance requirements and tone of voice — whether you’re in accounting, legal, consulting or another professional service.