Skip to content

Blog · Published · Updated

AI Agent for Purchase Order Exceptions

Short answer

When a confirmed purchase order changes, an AI agent sets the supplier's old and new dates beside the linked production order and the date promised to the customer in correspondence, points out gaps and passes the case to the buyer for decision. The buyer decides. The agent costs from €3,000 net at Syntalith and, with 150 purchase order changes a month at 25 minutes each, pays back in 2.0 months.

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
net per agent for one process, build paid once
from €3,000
from signing the contract to acceptance
6–16 weeks
free prototype on your cases
€0

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

Procurement and AI: statistics 2026

2.0 mo.

payback of a €3,000 agent with 150 purchase order changes a month: €2,181 of work today, €663 with checking and the model. Scenario.

Figures checked: 22 October 2026

What the decision-maker should receive

A supplier moves the date of one line on a confirmed purchase order. In the system, the planner has a production order that depends on this delivery and, according to the record, needs the part only after the new date. Looking only at the system, the change seems harmless. The thread with the customer, however, shows that the salesperson promised earlier shipment of the finished product, and that date never reached the system.

The agent shows the supplier's old and new promise, the linked order line, the production order, the date for the customer found in the correspondence, and the items that need confirming. The buyer decides whether to negotiate with the supplier or warn the salesperson. Sending the same confirmation again does not create a second case, and a later version from the supplier replaces the earlier assessment.

A test before you buy
  • A change the agent has not seen before
  • A deliberately incomplete set of evidence, for example without the customer thread
  • The same confirmation sent again
  • A later version of the confirmation from the supplier

If the agent misses a known record, assigns a message to the wrong line or merges two versions, the rollout waits until we establish the cause.

What it costs and when it pays back

Scenario: 150 purchase order changes a month
Today
150 purchase order changes × 25 min = 62.5 h (€2,181)
With the system, a person checks the output in 30% of the time
€654
Model, 3 calls per case, Claude Sonnet 5.5
€9
Cost of one case
€14.54 today, €4.42 with the system
Saving
€1,518 a month

Payback of €3,000

2.0 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: 8,000 input and 600 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

The count covers the work around a case: searching, reading, writing and passing things on. What remains is the time to check the output, 30% of today's work in the scenario. Before the quote we measure both times on 20 to 100 cases the team has already handled, in a €0 test that takes 5 working days.

A bigger cost than the buyer's hours is a change nobody assessed. A late part moves production, and the customer learns about the delay on the planned shipping day. So the trial also counts the changes where the agent found a promise to the customer that the system did not show.

First check your current purchasing system

Some systems have their own workflow for changes after an order is confirmed, which groups the changes for approval. If the system shows the changed confirmation, the dependent requirement and the next approval step, its workflow or a rule is enough. An agent makes sense when assessing a change needs information from outside the system: a date promised to the customer in an email, or arrangements with the supplier in a thread.

What to choose for which changes
  • The system shows the change and the dependent requirement

    the change workflow in the purchasing system

    configuration

  • A few changes a month

    the buyer checks by hand

    no build

  • Dozens of changes, customer dates in correspondence

    an agent that sets changes against the plan and the inbox

    from €3,000

Where to start

For the first call, prepare an anonymised confirmation before and after the change, the linked requirement record and an example of correspondence about the customer's date. We build this as part of AI agents. For the free process review, a description of one case from recent weeks and the tools it ran through is enough. You do not need to send confidential documents, and you get a written plan within 2 working days.

Worked example · Scenario

How we count the payback: AI in procurement

We run the same count for your orders in the free process review.

€2,792

a month for checking 800 supplier invoices by hand

Payback: 1.3 mo.

6 minutes to compare an invoice with the order and the goods receipt 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: €0.0040 per invoice, measured in our invoice coding system (0.004514 USD), 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 ↗

See the agent on your own cases before you commit.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 25, 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 agents

See the agent on your own cases before you commit.

The agent takes the case through the next steps in your systems, and the actions take effect until the consent of the indicated person is obtained. A prototype for 20-100 cases that your team has already handled costs €0. We write down the purpose and test set in the contract.

See AI agents →
net per agent for one process, build paid once
from €3,000
from signing the contract to acceptance
6–16 weeks
free prototype on your cases
€0

Questions

  • How does an AI agent help when a purchase order changes?

    It sets the supplier's old and new dates beside the production plan and the date promised to the customer in correspondence, points out gaps and passes the case to the buyer.

  • Does the agent accept the supplier's new date?

    No. The buyer and the planner decide whether to accept, negotiate or change the plan. The agent prepares the full picture of the case.

  • How much does such an agent cost?

    At Syntalith from €3,000 net. With 150 purchase order changes a month at 25 minutes each, the payback is 2.0 months. We agree integrations and maintenance before the quote, and the model costs €9 a month.

  • When is the change workflow in your system enough?

    When the system shows the change, the dependent requirement and the approval step. An agent makes sense when the assessment needs information from correspondence.

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
When we roll out ChatGPT, Claude or Copilot, you buy the licences directly from OpenAI, Anthropic or Microsoft and they invoice you. We add nothing to the licence.
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.