AI implementation in Israel
An AI agent answers your customers on WhatsApp in Hebrew, English or Russian and works inside monday, Fireberry or Priority. Prices start at $1,400 (about ₪4,400), with a working pilot 2–4 weeks after we get access
WhatsApp · customer
11:20Hi! We need 12 Ergo Pro chairs for our new office by the end of the month. Can you make it? Any discount for the volume?
AI
Reads and acts
Hebrew or English, and the ask
- 12 × Ergo Pro
- due: end of month
- discount question
ERP · Stock and delivery
Stock and delivery
CRM · Customer record
Customer record
Access and rules
Reply to the customer
11:20Hi! Ergo Pro is in stock, and we can deliver 12 chairs in 3 business days. A manager approves volume discounts: Oliver will message you today by 5 pm.
Bitrix24 · Deal and summary for sales
- Deal:
- 12 × Ergo Pro, by month end
- Task:
- approve the discount
We connect your systems
-
Quality tested before launch
Criteria agreed before we start
-
Hebrew and English
Tested on your own conversations
-
A decision after each stage
Every stage is paid for separately
Which business processes to hand to AI first
Four common scenarios, and the kind of solution that fits each one
Customers and candidates write on WhatsApp and Telegram, managers answer the same questions and fall behind
- Staff dig through policies, PDFs and chats, or just ask their manager because it is faster. Document search: An assistant answers from internal documents with a source link and respects who can see which documents.
- Data from chats, calls and emails is retyped into the CRM or 1C, reports are assembled by hand. AI inside CRM and 1C: AI works inside your systems: parses requests, drafts emails and reports, fills in fields.
- The process lives in spreadsheets and messengers, and managers cannot see statuses, errors or workload. Internal tool: A workspace or panel for one process with AI inside: task queue, statuses, disputed cases, reports.
AI implementation case studies
Facts and numbers from published projects
Scenario transcript
Application
- Under the hood: New application. HR system, Vacancy «Cook», Vacancy: Cook. Applied for “Cook”
- Agent: Good afternoon, Daniyar! I’m a recruiter at Magnum. You applied for the cook vacancy. Are you still looking for work?
Interview
- Customer: Yes, I am
- Agent: Thank you! May I ask how old you are?
- Customer: 23
- Under the hood: Screening rules. Candidate’s answers: meet them. Meets the screening rules
- Agent: Tell me an address or district where you’d like to work, and I’ll find a store nearby.
Nearby stores
- Customer: Saina Shalyapin
- Under the hood: Stores with the vacancy. Yandex Geocoder, Almaty, Saina × Shalyapin, Priority: 0.7 km, Nearest: 1.8 km, Nearest: 3.4 km. Priority store first
- Agent: There is an open cook vacancy near the Saina and Shalyapin intersection: 1. Store, 0.7 km 2. Store, 1.8 km 3. Store, 3.4 km Which one suits you?
Trial shift
- Customer: The first one. I can come tomorrow
- Under the hood: Candidate’s answer. store 1, tomorrow. Store 1, tomorrow
- Under the hood: Trial shift booking. HR system, Status: Trial shift, When: tomorrow morning, Changed by: AI Bot. Status “Trial shift”
- Agent: You’re booked for a trial shift tomorrow morning. Please come to the store’s main entrance. Bring your ID; an electronic one from eGov or Kaspi is fine. Dress code: dark trousers or skirt, a plain top, closed shoes.
- System: Status written to Magnum’s HR system · after the shift the agent asks how the day went
AI agent · WhatsApp · MagnumMagnum: HR agent for store hiring
An application in Magnum’s internal HR system turns into a WhatsApp conversation. The agent runs the first screening interview, finds a store near the candidate’s address and books a trial shift. The status goes back to the HR system, so the recruiter sees the result.
- Offers priority stores first, then others nearby, each with the distance
- Sep 2026 the agent went live with Magnum’s store candidates, in Russian and Kazakh
- Understands Russian, Kazakh and mixed speech
- Screen recording from the live botDocument search · Magnum
Magnum: Olzhas knowledge base for staff
An employee asks in their own words: how to request leave, who takes the sick note, where to get an employment certificate. The assistant finds the answer in approved documents and shows which document it came from.
- 150+ checks built from real employee questions in Russian and Kazakh, run against every update
- Understands Russian, Kazakh and a mix of both
- Magnum’s new documents go live after the eval set has been run
Scenario transcript
Request
- Customer: Hello! I’d like to become a supplier
- Under the hood: Site from the QR code. Compass, QR · Compass site, City: Almaty, Site: Compass station. Almaty, Compass station
- Agent: Hello! You’re at a Compass site in Almaty. What is your company called, and what is its BIN?
BIN check
- Customer: Dala Snab LLP, BIN 1809•••••12
- Under the hood: BIN check. Company registry, BIN 1809•••••12, Company: Dala Snab LLP, Status: active. BIN is active
- Agent: BIN verified. What do you supply?
Category
- Customer: Household goods and cleaning supplies
- Under the hood: Supplier category. household goods, cleaning supplies. Household goods
- Agent: Category: household goods. Please send your price list: PDF, Excel or a photo.
Bitrix24 card
- Customer: price_list_2026.xlsx (XLSX · 38 KB)
- Under the hood: Supplier card. Bitrix24, Company details: Dala Snab LLP, Category: household goods, Price list: price_list_2026.xlsx. Card created
- System: Bitrix24 card · company details, category, price list
AI agent · WhatsApp and Bitrix24 · CompassCompass: supplier onboarding into Bitrix24
A supplier scans a QR code at a Compass station and lands in WhatsApp. The agent collects company details, validates the tax ID, picks the category, accepts a price list in any format and creates a card in Bitrix24.
- A QR code at every station, so the agent knows the city and site
- Russian and Kazakh, language detected automatically
- The supplier card goes straight to Bitrix24
Scenario transcript
Question
- Customer: Hello! I’d like to sign up for the marathon
- Under the hood: Race calendar. Knowledge base, races 2026, Almaty Marathon 2026: registration, Astana Half Marathon 2026: registration, Tau Jarys 2026: registration. Three races on the calendar
- Agent: Good afternoon! I’m the Almaty Marathon assistant. Which race would you like to know about? The calendar now has Almaty Marathon 2026, Astana Half Marathon 2026 and Tau Jarys 2026.
Race kit
- Customer: Almaty Marathon. Where do I pick up my race kit?
- Under the hood: Race kit pickup. Knowledge base, Almaty Marathon · race kit, Where: pickup point, How: QR code from the email. Pickup point, QR code
- Agent: Race kits are handed out at the pickup point before the race. Show the QR code from your registration email.
Refund to a manager
- Customer: And if I can’t run, will I get my money back?
- Under the hood: Agent permissions. Refunds: manager. A person decides on refunds
- Under the hood: Handoff to a manager. WhatsApp, To: manager, Summary: race, kit, refund. The manager has the summary
- System: Refund → manager · chat summary attached
- Agent: I’ve passed your question to a manager. They’ll reply right here.
Support · WhatsApp, Instagram · Almaty MarathonAlmaty Marathon: runner support agent
The agent answers participants on rules, schedule, registration and race packs. Refunds, complaints and VIP requests go to a manager with a summary of the chat.
- 9 in 10 conversations resolved without an operator
- ~2,130 conversations with race participants
- WhatsApp and Instagram around the clock
A working version in 2–4 weeks
Five stages. After each one you decide whether to go on. Each stage is paid separately
Pick one process
2–3 working daysWe find where the team loses hours and pick one process with an owner on your side and a result that can be counted.
A short memo: the process, the type of solution, what success means, and what stays out of the first stage.
Process, metric and owner are agreed.
Timelines start once access is granted: without chat exports and a test API the audit cannot start. WhatsApp number verification with Meta takes from a few days to three weeks, so we start it on day one. Projects with several processes or heavy integrations with 1C and custom systems take 3–4 months, but even there a working version ships in the first month.
What AI implementation costs
The cost of implementing artificial intelligence depends on the process and the integrations. These are starting prices, and we name the exact figure after the audit, once we have seen your data and systems
- Timeline: 1–2 weeks
What we build: AI in a CRM or 1C
Price: from $1,400What is included: One feature inside the system: request parsing, draft replies, document sorting
- Timeline: 2–4 weeks
What we build: AI agent
Price: from $2,000What is included: A scenario, answers from your materials, handoff to a manager
- Timeline: 3–5 weeks
What we build: Document search
Price: from $3,000What is included: An assistant over your policies and knowledge base, answers with a source link, role-based access, a test set
- Timeline: 3–6 weeks
What we build: Internal tool
Price: from $4,000What is included: A staff workspace with AI features: summaries, document checks, reports
Model usage (OpenAI, Anthropic and others) and the WhatsApp API are billed separately at the providers’ rates.
Get an estimate for your case
Send the task for an estimateAI quality testing before launch
We agree the threshold before we start and measure it separately in Hebrew and every other language, on your own questions
- A set built from your questions
- 100–200 real requests with reference answers from your staff. Hebrew questions, mixed Hebrew and English, and replies to customers of either gender are always included.
- A different model grades
- A separate judge model, not the one that answered, scores the answers. We check its scores against your staff’s own grades.
- Every miss gets reviewed
- An overall score can hide individual errors, so every answer below the threshold is reviewed on its own and fixed before launch.
- Acceptance on new questions
- We sign off on questions the system never saw during tuning, so the result can’t be fitted to familiar ones.
- RU Где мой заказ 4187? 0.93
- KZ Тапсырысым қашан келеді? 0.86
- RU Можно счёт на ТОО? correctly handed to accounting 0.90
- KZ Тауарды қалай қайтарамын? judge: right answer, but in Russian 0.72
- KZ+RU Сәлем, доставка Астанаға қанша тұрады? 0.88
- RU Позовите менеджера handed to a person right away 0.97
- KZ Жеңілдік бар ма? judge: promised a discount outside the rules 0.64
- RU Как поменять адрес доставки? 0.84
- KZ+RU Заказты отменить етуге бола ма? 0.81
- KZ Кепілдік мерзімі қанша? 0.85
Illustration of the mechanics with sample data. The real set is built from your requests during the audit.
What AI implementation in Israel has to handle
We check all of this during the audit, before building. Companies operating elsewhere can start from our general AI implementation page
Hebrew, English and Russian in one agent
The agent replies in the customer’s language and addresses them in the right grammatical gender. Templates, PDFs and emails are checked in right-to-left layout. Hebrew is a well-resourced language for frontier models, but we only promise quality after testing on your conversations.
מתי תגיע ההזמנה 4187?
-
WhatsApp
Official Business API only. Since 1 October 2026 Meta charges for service messages above 1,000 a month per number, and we put that cost in the estimate. Marketing messages go only to people who gave written consent.
Business API · opt-in list
-
Shabbat and holidays
On Shabbat and holidays the agent keeps answering customers but pauses broadcasts. The quiet window follows sunset and the Hebrew calendar, not a fixed clock. Queued messages do not go out in one burst after Havdalah.
Sun–Thu week · sunset pause
-
monday, Fireberry, Priority
The agent creates leads and deals in monday or Fireberry and marks them as its own. It reads orders and stock from Priority ERP. Writes go only through a confirmed route.
lead · deal · stock
-
Invoice allocation numbers
Since 1 June 2026 input VAT on an invoice above ₪5,000 before VAT is deductible only with an allocation number from the Tax Authority. AI checks incoming supplier invoices against the Tax Authority service and flags those without a number.
מספר הקצאה · Morning · iCount
-
Payments in the chat
The agent sends a payment link through Cardcom or Tranzila, where the customer pays by card or with Bit. Morning or iCount issues the invoice once the payment lands. Refunds and disputed payments stay with a person.
Cardcom · Tranzila · Bit
-
Amendment 13 and data transfers
The bot says it is a bot from the first message. OpenAI or Anthropic keys belong to your company, with training on your data switched off. Customer data stays in the EU or with your provider, not in Kazakhstan, and the transfer abroad is covered by a contract under Israeli rules.
bot discloses itself · your API keys
Guides for your industry
Each guide covers what to hand to AI first, what stays with people and how to run the pilot
Frequently asked questions
With the process. In the first meeting we look at where the team loses time: customer chats, searching through policies, retyping data, or the lack of a shared picture. That decides the type of solution. If there are several processes, we pick one with a clear owner and a result that can be counted.
AI in a CRM starts at $1,400 (about ₪4,400), an AI agent at $2,000 (about ₪6,200), document search at $3,000 (about ₪9,300), an internal tool at $4,000 (about ₪12,400). A full launch with an audit, testing in Hebrew and English and integrations usually costs $8–12K, and support $200–1,000 a month. The contract and invoice are in US dollars; shekel figures are a guide at the 29.10.2026 rate. The exact figure comes after the audit.
A ready-made bot follows the platform’s template. We build the logic around your process, connect your CRM, invoicing and payments, and test the answers on your own Hebrew and English conversations before launch. Israeli agencies list a WhatsApp agent at around ₪10,000 and up; ours sits below that. If a standard flow such as bookings and common questions is all you need, a subscription is cheaper, and we will say so.
AI in a CRM or 1C takes 1–2 weeks, an AI agent 2–4, document search 3–5, an internal tool 3–6 weeks. The full path with process selection, an audit and a pilot gets you a working version in 2–4 weeks after access is granted. Projects with several processes and heavy integrations take 3–4 months.
A process owner who makes decisions, 30–100 real requests, conversations, or documents, a list of systems with access to their test APIs, handoff rules, and examples of good team answers. The knowledge base does not have to be perfect: we build the test set together.
Hebrew is a well-resourced language for frontier models, but we found no public comparison of GPT, Claude and Gemini in Hebrew. So we test on your conversations: the test set covers Hebrew, English, Russian and mixed messages, and the threshold is measured per language. A separate rule sets how the agent addresses each customer, since second-person verbs in Hebrew are gendered. WhatsApp templates, PDFs and emails are checked in right-to-left layout, and Hebrew voice gets its own test during the pilot.
ChatGPT and similar tools help an individual employee write and search. Implementation connects a model to a company process: customer chats, the CRM, 1C and documents, with access rights respected. The system answers by your rules, writes results into your systems and hands difficult cases to a person. Quality is checked with a test set before launch and after every change.
Yes, under a few conditions. Amendment 13 to the Privacy Protection Law has been in force since 14 August 2025, and data may leave Israel only for a country with equivalent protection or under an exception, for example when the recipient undertakes by contract to follow Israeli rules. So the bot discloses that it is a bot, and your privacy policy says an AI provider abroad processes the conversations. OpenAI or Anthropic keys belong to your company, with training switched off. Customer data stays in the EU or with your provider, not in Kazakhstan. Medical and financial data need a separate review, and the final setup is worth showing to your lawyer.
You sign with our company in Kazakhstan, priced in US dollars without Israeli VAT. We work fully remotely and never travel to Israel for the project, and banks usually transfer payment for services rendered entirely abroad without withholding tax. Israel and Kazakhstan have no tax treaty yet, so if your bank asks for a Tax Authority approval, it is requested on form 2513/1. You self-assess the 18% VAT and deduct it at once. Please confirm the details with your accountant. Almaty is two to three hours ahead of Israel, so our working days overlap Monday to Thursday.
Yes, but only to people who gave written consent: the anti-spam law requires it, and a recipient can claim up to ₪1,000 per message sent without consent. The agent keeps the opt-in list, pauses broadcasts on Shabbat and holidays, and does not release a backlog in one burst after Havdalah. Keep the cost in mind too: since 1 October 2026 Meta charges for service messages above 1,000 a month per number.
We agree on the success criterion before the start. Usually it is the share of requests handled without an operator, accuracy per language and response time. After the pilot there are three options: launch, rework or stop. Each stage is paid separately, and the next one only if you continue. When the AI is unsure, a person decides the disputed case.
The code, the knowledge base, the test set with reference answers, and documentation. Model keys and accounts are in your company’s name, so the system can keep evolving with us or without us.
Read before the call
- AI pilot in 30 days A day-by-day plan and the three decisions a pilot ends with
- AI business process automation Where workflow rules are enough, where AI earns its place, and how to do the ROI math
- What to prepare before implementing AI A company checklist and the minimum package for a vendor
Let’s talk
Describe the process you want AI to take over, the languages your customers write in and the systems that hold the data. Attach a couple of real conversations if you have them. We will tell you which solution fits and where to start.
I read every request myself.