Skip to content

Blog · Published · Updated

Purchase approvals: what was approved before the change?

Short answer

A shared view of purchase approvals shows the approved request next to a later change, for example of supplier, and sends the change back for approval. First check whether your current ordering system keeps the approved version. Your own screen makes sense when chat, a form and the ordering system lose the link between an approval and its content.

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 application, fixed price before contract
from €3,000
from signing the contract to acceptance
4–10 weeks
free prototype on your documents
€0

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

Author: Syntalith · 5 min read

Example: the morning request inbox
Agent · ready

Statistics

Purchasing and AI: statistics 2026

1.8 mo.

payback of €3,000 at 500 purchase requests a month: €2,327 of work today, €702 with checking and the model. Scenario.

Figures checked: 22 October 2026

A purchase request after a change
  • The approved version kept with the date and the person
  • The supplier change shown next to the approved version
  • Re-approval for a significant change
  • The order created from the approved version

The approval covers the purchase the manager saw

Say maintenance needs a specific part. The request names supplier A, and the manager approves the purchase. Later it turns out that A cannot deliver the part. The buyer changes the supplier to B. At this company, such a change needs approval again, under its own rules.

If the buyer just overwrites the name in the form, the earlier “approved” may stay next to the new supplier. The next person then has to work out whether the manager has already seen the proposal to buy from B. The date of the last edit alone does not explain what the decision covered.

In the proposed solution, the original request stays available with the manager's approval. The buyer prepares the changed version, and the manager gets a short explanation:

Supplier changed from A to B. Supplier A cannot deliver the part. The earlier approval covered buying from A; buying from B is waiting for re-approval.

With this note, the manager opens the new version and can compare it with the previous one. They do not have to search the correspondence for why the matter came back. Once they decide, the record of the decision stays with the version they just reviewed. The buyer and finance see both the earlier agreement and the answer on the change.

Why the team keeps rebuilding the same story

Chat is good for a short question, a form for collecting data and an ordering system for running the order. The trouble starts when an approval in one place does not clearly point to the content recorded in another. The buyer remembers the change, the manager remembers the original purchase, and the person preparing the order sees only the current form.

Joining this information up should let an employee open the approved request from wherever they do the next piece of work. Next to the current proposal they need to see what changed and whether someone has already approved that change. Handing the matter to a colleague then needs no separate story of every step.

Preparing material before a decision is covered separately by the offer for AI in procurement: comparing terms and collecting questions for suppliers. The company sets which changes have to go back to the manager. In the example it is a change of supplier; your process may have other rules. The supplier builds these arrangements into the app. Keeping the version and the approval together can be solved with ordinary software, with no AI in the decision.

First check what your current ordering system can do

Ordering systems can send requisitions for review as whole documents or as single lines, and create a purchase order after approval. How a later change of supplier is handled has to be checked in the solution you use and its configuration.

Ask the person responsible for the ordering system to walk through the case above with the buyer. If the system keeps the approved request, shows the change and lets you send it back to the right person, configuring the current flow may be enough. Then consider whether the extra form and separate approvals in chat are still needed.

An integration makes sense when the tools in use handle their own parts of the work well, but lose the link between the request and the decision. Your own app is worth considering when the team needs a shared view of changes and approvals that the current tools cannot provide comfortably. You can limit the project to that part and leave orders and accounting records in the ordering and finance systems.

Moving to the new purchase approval flow without losing earlier agreements

At launch, you have to decide what happens to requests already in progress. Some can finish the flow in the old tool, and selected matters can be moved with their attachments and decision history. Importing the current form content alone will not show what the manager approved before the change. The person responsible for purchasing should confirm that the earlier decision still points to the right version of the request.

The offer should cover later support for the connection to the ordering system: who deals with an approved request that does not appear where the work continues, and how to report a problem. Also settle access to the code and documentation, and exporting requests with their decisions and attachments. These arrangements matter when you change supplier.

When replacing the tool for collecting documents from suppliers, the guide to a custom supplier portal in place of SaaS will also help.

What you can order from Syntalith

Syntalith builds custom software and integrations. For this problem we propose linking the register of requests to the place where purchasing carries on the work, plus a view showing the approved version and later changes. The first scope can be limited to one type of purchase.

Your team brings the rules for re-approval and knowledge of the current flow. In the conversation we will settle whether you need configuration of the ordering system, a connection between existing tools, or also your own screen for comparing requests. Tell us about the last change where you had to find the earlier approval, and show where the request and the decision were recorded. Syntalith's apps start from €3,000 net, and we set the scope after a free process review (pricing).

When the difficulty already starts with comparing offers, look at the possible AI rollouts for purchasing. They help separate work on documents from the purchase approval flow.

What a purchase approval system costs and when it pays back

Scenario: 500 purchase requests a month
Today
500 purchase requests × 8 min = 66.7 h × €34.90 = €2,327
With the system, a person checks the output in 30% of the time
€698
Model, 1 call per case, Claude Sonnet 5.5
€4
Cost of one case
€4.65 today, €1.40 with the system
Saving
€1,625 a month

Payback of €3,000

1.8 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, converted at the ECB rate of 1.1205 USD per euro.

What we measure in the trial
  • Time from receiving a case to the result, before and after the change
  • Cases the app passed to a person
  • Corrections by the person checking
  • Model and maintenance cost at the target volume

Where to start

In the free process review we choose one process and count the team's volume and working time, and within 2 working days you get a written summary with a price. We build as part of AI apps, and we price maintenance separately.

Worked example · Scenario

How we count the payback: purchase approvals

We run the same count for your purchasing team 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 ↗

When an off-the-shelf tool does not fit, we build your own.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 →

Custom AI apps

When an off-the-shelf tool does not fit, we build your own.

We build an application with a language model for the work of your team: searching the company's knowledge, case panel or portal. We check the validity of your documents before launch, and the code stays with you.

See AI applications →
net per application, fixed price before contract
from €3,000
from signing the contract to acceptance
4–10 weeks
free prototype on your documents
€0

Questions

  • How do you run purchase approvals without chat and emails?

    In a view that keeps the approved request, shows later changes and sends them back for approval. Ordering and booking stay in the ordering system.

  • What should happen when the supplier changes after approval?

    The change goes back to the approver with a comparison of versions. The earlier approval stays with the version the approver saw.

  • How much does it cost?

    At Syntalith apps, automations and AI agents start from €3,000 net. At 500 purchase requests a month of 8 minutes each, the payback is 1.8 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
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.