Skip to content

Blog · Published · Updated

AI in accounting: a missing documents list for the client

Short answer

AI helps accountants prepare a draft list of questions to a client about documents: a missing purchase description, an ambiguous case number or an attachment mentioned in correspondence. The accountant sets the rules for the check, and the model orders the material. It decides neither the accounting treatment nor the tax treatment.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Accounting and AI: statistics 2026

2.5 mo.

payback of €3,000 at 600 documents a month: €1,745 of work today, €528 with checking and the model. Scenario.

Figures checked: 22 October 2026

A missing documents list ready to send
  • Each question points to a specific document
  • Completeness kept apart from correctness
  • Check rules set by the accountant
  • The list approved before it goes to the client

A question should lead to a specific document

In a fictional example, the firm received an invoice for a service, but the information on which project it concerned is missing. A note saying „please complete the documents” makes the client search again. The list should point to the document and name the missing information exactly.

Do not assume that a purchase concerns the same project as the previous invoice from that supplier. A repeat supplier does not confirm what a cost was for. If the client has already answered in another thread, link that answer to the right case and check that it is still current.

Keep completeness apart from correctness

A filled-in field does not prove that the description is right. The status „information received” can come before the accountant's assessment. Keep both stages, so the draft list does not suggest that a case is closed after every reply from the client.

With stable identifiers, part of the work can be done with rules. Power Query can merge tables on one or more columns; you need to agree the keys and the data types. AI can be limited to reading free-text descriptions. Microsoft documentation, checked on 9 October 2026.

How do you check the list before using it?

In the proposed trial, include a complete document, a document with no description and an answer that concerns a different number. The system should not ask again about information already in the materials, and it should not close a gap on the strength of an answer about something else.

Also check a second upload of the same file and a later correction. The process owner decides which event updates the case. The list for the client should contain only material that this recipient has access to.

We have not run a trial on client documents here. Before you use real material, agree the tool cleared for use and how the material is passed on. Fictional examples are enough to judge whether the proposed view is clear.

Is the current document workflow system enough?

If your software already keeps comments and assigns answers to a document, check its configuration and how the team works. A separate integration makes sense when the accountant regularly links email, files and tasks by hand.

If your accounting software has e-invoicing (in Poland, KSeF) and OCR features, compare them with an extra workflow, so you can separate the work the software does from collecting explanations from the client.

Syntalith can discuss an automation with you. The scope can end with a list for approval; sending messages and writing to the accounting software need separate agreements. If the need is better checking of AI drafts, see team training for accountants. The service price levels are on the Syntalith pricing page.

Start the conversation with the question that most often goes back to clients and the place where you record the answer today. You do not need to send invoices for the first meeting.

What it costs

Scenario: 600 documents a month
Today
600 documents × 5 min = 50 h (€1,745)
With the system, a person checks the result in 30% of the time
€524
Model, 1 call per case, Claude Sonnet 5.5
€5
Cost of one case
€2.91 today, €0.88 with the system
Saving
€1,217 a month

Payback of €3,000

2.5 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 3,000 input tokens and 300 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

What we measure in the trial
  • The time from receiving a case to the result, before and after the change
  • Cases the application passed to a person
  • Corrections by the person checking
  • The cost of the model and maintenance at the target volume

Where to start

In the free review we choose one process and count the volume and the team's working time, and within 2 working days you receive a written summary with a price. We build the automation as part of AI automations, from €3,000 net.

Worked example · Scenario

How we count the payback: missing documents

We run the same count for your firm in the free review.

€2,094

a month for preparing 20 reports

Payback: 1.7 mo.

3 hours to collect the data and prepare a report and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: checking the commentary in our reporting system (about €0.0002) plus compiling the data (Claude Sonnet 5.5, about 30,000 + 2,000 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

Start with the process that takes the most time each week.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 21, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI implementation

Start with the process that takes the most time each week.

The engineer chooses one process with you and calculates how much it costs today. Then we build a free prototype on 20-100 cases that your team has already handled. We write down the goal and the fixed price in the contract.

See AI implementation →
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

Questions

  • How does AI help an accounting firm with missing documents?

    It prepares a list of questions to the client, each pointing to a specific document and gap. The accountant approves the list before it is sent.

  • Does AI decide how a document is booked?

    No. It checks completeness against the accountant's rules, and the accountant judges whether the content and the tax treatment are correct.

  • How much does it cost?

    At Syntalith, AI apps, automations and agents start from €3,000 net. At 600 documents a month and 5 minutes each, the payback is 2.5 months.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.