Skip to content

Blog · Published · Updated

A voicebot for a staffing agency: almost an hour saved per applicant

Short answer

For a staffing agency we built a system in which a voicebot holds the first conversation with each applicant, and the agency's CRM updates after every call. According to the client, the team saves almost an hour of work on every applicant. We build such apps from €3,000 net, and with 300 applicants a month the payback in our scenario is 0.3 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 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 · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Recruitment and voicebots: statistics 2026

almost 1 h

of work saved per applicant, according to a staffing agency that is a Syntalith client under NDA. The voicebot runs prescreening, and a consultant calls the people after it.

Figures checked: 22 October 2026

What the agency team gained

A staffing agency receives applications from people looking for work. Each one needs a call, the same screening questions, the answers saved in the CRM and the case passed to a consultant who closes the recruitment.

The result of the rollout
  • Team time

    almost 1 h

    Less work on every applicant, according to the agency.

  • Screening calls

    the voicebot

    Consultants call the people after prescreening, and still run some prescreening calls themselves.

  • CRM

    the same one

    The system works on the CRM the agency already uses.

The client is under an NDA. The screenshots show the deployed app with synthetic data. Calls and the CRM in the presentation are simulated, and names, numbers and scores do not come from the client's work.

From an application to a call with a consultant

The path of one applicant
  1. 01Applicationthe system creates a record in the agency's CRM
  2. 02Prescreeningthe voicebot calls, asks the screening questions and completes the record
  3. 03Consultantcalls from the contact card and sees what was established earlier
  4. 04Transcriptthe time of every utterance, confirmed information and the proposed step
  5. 05Resultthe consultant picks the result, the date and the note, and the record goes to the CRM
The call card with findings above the transcript
Findings above the transcript: confirmed information and the proposed next step. Synthetic data.
The call result panel with the result Call back
The result „Call back” with a time and a note goes to the task queue. Synthetic data.

What the manager sees

The manager sees who is on the line, who they are talking to and for how long, and moves from that view to the call they want to check. Each call carries the criteria from the script: did the consultant state the purpose of the call, confirm availability and agree the next step. The manager sets a score from 0 to 100 and saves it with the contact. Daily and weekly reports gather the scores of the whole team.

Call quality assessment by the team's criteria
Quality assessment by the team's criteria. Sample values.
The rules the system enforces
  • Supervision actions go to a log that cannot be edited
  • Outgoing calls only on working days from 9:00 to 19:00
  • Recordings and transcripts are tied to the call, so every score has a source
  • The consultant approves the result, the contact date and the note

What a staffing agency voicebot costs and when it pays back

Scenario: 300 applicants a month
Work saved
300 people × 50 min = 250 h × €34.90 = €8,725
App with a voicebot and a panel
from €3,000 net

Payback of €3,000

0.3 months, before telephony and model costs

The client speaks of almost an hour saved per person; the scenario counts 50 minutes. The number of applicants is an assumption. We price telephony, the model and maintenance after the review. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat.

Who this makes sense for

When to use a voicebot for the first call
  • Many applications with the same screening questions

    a prescreening voicebot and a team panel

    from €3,000

  • Incoming calls from customers

    a voicebot that answers calls, the odbierze.ai brand

    priced after the review

  • A few applications a week

    a call script and a form in the CRM

    no build

The system helps staffing agencies and teams that call back many applicants with the same questions: in recruitment, booking appointments and telephone sales. It gives the most where a person still calls after the screening call. We roll out voicebots for incoming calls under the odbierze.ai brand. The seven steps of work in the panel are shown in the case description. For the free process review, 30 minutes with an engineer about your team's work is enough, and within 2 working days you get in writing what to move to a voicebot first and from what price.

Worked example · Scenario

How we count the payback: recruitment

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

€2,327

a month for handling 800 candidate and employee documents by hand

Payback: 1.5 mo.

5 minutes to receive and check a document 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: reading a document in our case file system (about €0.0002) plus a description of what is missing (Claude Sonnet 5.5, about 2,000 + 300 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 ↗

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 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 →

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, voicebot 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

  • What does a voicebot do in a staffing agency?

    It calls the people who left an application, asks the screening questions and updates the record in the agency's CRM. A consultant then calls the people after prescreening and sees the contact history.

  • How much time does a prescreening voicebot save?

    In our staffing agency rollout, according to the client, almost an hour of work on every applicant. The result concerns this process and this agency.

  • How much does a voicebot with a team panel cost?

    At Syntalith we build AI apps from €3,000 net, usually in 4 to 10 weeks. We price the connection to the CRM and telephony after the review. In a scenario with 300 applicants a month and 50 minutes saved per person, the payback is 0.3 months.

  • Who approves the result of a call?

    The consultant. The findings and the proposed next step are material to check, and a person approves the result, the contact date and the note.

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.