Skip to content

Blog · Published · Updated

AI agents for preparing procurement waiver requests

Short answer

An AI agent prepares a request for a waiver from the purchasing rules for decision: it sets the reason and the deadline against the attachments and asks the requester what is missing, for example which alternatives were checked. The procurement manager receives a complete case, and the decision stays with them. The agent costs from €3,000 net at Syntalith and, with 120 waiver requests a month at 30 minutes each, pays back in 2.1 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

2.1 mo.

payback of a €3,000 agent with 120 waiver requests a month: €2,094 of work today, €633 with checking and the model. Scenario.

Figures checked: 22 October 2026

Delivery on Thursday explains only part of the request

A private company's policy lets the procurement manager consider a waiver if the request gives the reason, the required date and an explanation of which alternatives were checked. An employee needs materials for maintenance work on Friday, writes that the preferred supplier will deliver them on Thursday and attaches the confirmation. They do not say whether they contacted other suppliers.

The agent finds the confirmation and sets it beside the description of the need, and the manager sees where the urgency comes from. One specific question for the requester remains:

The request mentions maintenance work on Friday, and the attachment confirms delivery on Thursday from the preferred supplier. Which alternative offers were checked, and with what result?

A procurement employee checks the draft and sends the question. The agent attaches the reply to the same case.

A waiver request
  1. 01Requestreason, date and the note „urgent”
  2. 02Attachmentsthe delivery confirmation beside the description of the need
  3. 03Gapsa question about the specific missing information
  4. 04Replyattached to the same case
  5. 05Decisionthe procurement manager, with the complete material
What the agent does not decide
  • Whether the waiver is justified
  • Exceptions where the rules are unclear
  • The choice of supplier
  • Changes to the purchasing policy

What it costs and when it pays back

Scenario: 120 waiver requests a month
Today
120 waiver requests × 30 min = 60 h (€2,094)
With the system, a person checks the output in 30% of the time
€628
Model, 3 calls per case, Claude Sonnet 5.5
€5
Cost of one case
€17.45 today, €5.28 with the system
Saving
€1,461 a month

Payback of €3,000

2.1 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: 5,000 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.

Links to the attachments stay next to the summary, because the manager may want to read the exact wording of the supplier's confirmation. A short description makes it easy to get your bearings, and the source lets you check the detail.

When a form and the current workflow are enough

If requests keep missing the same field, fix the form: the question about checked alternatives can appear when the request is submitted. Ready-made tools handle passing a request on for decision: Power Automate routes approval requests to people and collects the replies. The agent has more to do when the reasons are scattered across the text of the request, an attachment and a later email. The article on a purchase approval system covers versions of an approved purchase after a change of supplier.

A form, a workflow or an agent
  • The same field is always missing

    a corrected request form

    configuration

  • Requests are complete, nothing passes them on

    an approval workflow in your current tools

    configuration

  • The reasons sit in many places

    an agent that completes the request for decision

    from €3,000

Where to start

The first scope covers one type of waiver in the current workflow. On a finished case we check whether the proposed question would have produced the explanation the manager had to go back for. AI in procurement describes other starting points. 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: the procurement team

We run the same count for your requests 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 with procurement waivers?

    It sets the reasons in the request against the attachments, points out missing information the policy requires and prepares a question for the requester. The manager receives a complete case for decision.

  • Can the agent approve a waiver?

    It cannot. The person named in the purchasing policy decides. The agent prepares the material and the questions.

  • How much does such an agent cost?

    At Syntalith from €3,000 net. With 120 waiver requests a month at 30 minutes each, the payback is 2.1 months. We agree integrations and maintenance before the quote, and the model costs €5 a month.

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.