Skip to content

Blog · Published · Updated

Project change portals: what did the client approve?

Short answer

A project change portal records the client's approval against a specific drawing version and change description, so the project manager does not search emails for which version the client saw. First check the approval flow in your current tool, and build your own view when the client needs access the tool does not give.

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

Projects and AI: statistics 2026

2.5 mo.

payback of €3,000 at 150 project changes a month: €1,745 of work today, €525 with checking and the model. Scenario.

Figures checked: 22 October 2026

A project change with approval
  1. 01Changea description and a new drawing version
  2. 02Clientsees the version and replies
  3. 03Approvalrecorded against that version
  4. 04Next changea new version, a new approval
  5. 05Teamgets work from the approved version

Approval to move the reception desk

Say a team is designing an office interior. At the client's request, the designer moves the reception desk and sends drawing version B. The client approves this proposal. Later, version C appears, in which the designer also moves a cupboard. The client's reply still concerns version B and moving the reception. The new idea for the cupboard needs presenting separately.

The proposed portal shows the client the drawing with a short description of what they are asked to assess. Their reply stays with that version. The project manager sees the approved proposal for the reception and, next to it, the later change waiting for a reply. They can rebuild the conversation without comparing email dates with file dates.

Before sending version C, the designer describes the extra change and points to the new drawing. The client can go back to the earlier agreement, see what was added and reply on the new proposal. The earlier approval stays in the history. The project manager passes on the resulting work in line with the company's agreed way of authorising execution. On the task, the team opens the drawing covered by the agreement, even when a newer sketch has already appeared in the folder.

First check your current approval flow for project change requests

A ready tool may handle much of this work. Jira Service Management lets you add an approval to a request's workflow. The named people get a notification and can approve or decline the request, for example in the help centre or by email (approvals in Jira Service Management).

If you already use a similar system, check whether the client's reply stays linked to the drawing and description presented for approval, even after a new attachment is added. An “approved” field on its own may be too general when versions pile up in a request. The administrator should explain how to keep the earlier agreement and present a new proposal. Configuration and tidying the attachments may be enough.

When the client needs a view of their own

An extension may be enough if the internal flow works well, and the client struggles to find the proposal among comments and attachments. A simple view would show the drawing, the change description and a place to reply. On the team's side, the matter would still go to the current task system. Such a connection must also carry which version the reply refers to.

Your own portal is worth considering when the project manager keeps assembling agreements from email, the drawing library and the work-planning program. The first scope can cover one type of change presented to clients. You do not need to replace the designers' tool or all project management. What matters is that, after getting a reply, the project manager can pass the work on without rebuilding the context again.

The team has to name who on the client's side replies to a proposal and who at the office sends it for execution. The client should see the materials of their project, and the designers' internal notes stay in their working flow. That lets you prepare a clear view for the conversation with the client, without moving the office's whole back room into it.

Ordinary software is enough for this basic flow; summarising long correspondence with AI can be assessed separately.

If the difficulty appears only after the work is accepted, when a signed document has to reach the person handling invoicing, the article on the flow of acceptance certificates will help.

Keeping agreements when you change tools

When moving open matters, keep the proposal, the drawing and the client's reply together. A list of requests with a final status alone will not let the project manager explain what was agreed. Older projects can stay in an accessible archive, if these links can be found there. Also agree on exporting them later from the new portal.

After launch, someone has to look after client access and changes to the office's way of working. Agree with the supplier who clears up a case where a reply reached the portal but did not appear on the team's task. The terms of upkeep for the connections, ownership of the code and data and access for a later supplier are part of the comparison with a ready product.

Have the client's reply linked to the team's work

As part of custom apps, Syntalith can prepare a portal that links the change proposal, the drawing version and the client's reply to a task in the system you use. The project manager gets a basis for passing on the agreed work, and the client one place to view proposals and reply. A working approval flow can stay part of the solution.

Tell us about the last change where you had to work out what the client had actually approved. Show where you keep the drawings and where the project manager assigns tasks. The conversation will help settle whether you need these tools connected, or a separate client view as well. Syntalith's apps start from €3,000 net, and we set the scope after a free process review (pricing).

What a project change portal costs and when it pays back

Scenario: 150 project changes a month
Today
150 project changes × 20 min = 50 h × €34.90 = €1,745
With the system, a person checks the output in 30% of the time
€524
Model, 1 call per case, Claude Sonnet 5.5
€1
Cost of one case
€11.63 today, €3.50 with the system
Saving
€1,220 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, 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: project changes

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

€4,363

a month for handling 1,500 job emails

Payback: 0.8 mo.

5 minutes to read an email and reply 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: Claude Sonnet 5.5, about 3,000 + 600 tokens per message with a draft reply, 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 record the client's approval of a project change?

    Against a specific drawing version and change description, with the date and the person approving. The next change creates a new version, and the earlier approval stays with the old one.

  • Can your current project tool handle it?

    Often, yes: ticket and project tools have approvals. Your own view makes sense when the client needs simple access to the versions and their own reply.

  • How much does it cost?

    At Syntalith apps, automations and AI agents start from €3,000 net. At 150 project changes a month of 20 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
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.