Request Demo

Hachi

The employee who answers your WhatsApp at 3 in the morning

Hachi answers WhatsApp, Instagram and Messenger around the clock, checks your real calendar and books the appointment. Then it reminds people, so they turn up. Not a button menu: it understands what people write, in text or voice notes, and escalates to a human when something falls outside the script.

From €149/month · 7-day free trial, no card · GDPR compliant

In production today

24/7
Serving real clinics
without interruption
63
Critical rules enforced in
code, not in the prompt
3-5
Working days from
signing to going live
0
Flows to maintain.
It learns from your documents

We do not display logos of companies that are not clients. If you want to speak to someone already using Hachi, ask during the demo and we will put you in touch.

Powered by

Claude AI
OpenAI
DeepSeek
Twilio
Meta Business
LinkedIn

Seamless Integrations

Google Calendar
Zapier
Excel
Slack
GitHub
PostgreSQL
Stripe
AWS S3

Cognitive Agents with Dynamic Workflows

Unlike rigid automation tools like n8n or traditional LangChain agents, our LangGraph cognitive agents execute dynamic workflows that adapt to achieve objectives. They don't need pre-defined flows for each scenario—they reason, retry, and self-correct until they succeed.

Agent Framework Comparison

Feature LangGraph LangChain Agents n8n
Dynamic Flow Execution
Runtime path adaptation
ReAct loop only
Pre-defined flows
State Management
First-class with TypedDict
Agent scratchpad
None native
Self-Correction & Retries
Native cycles & conditionals
Limited by max iterations
No cyclic support
Memory Persistence
Checkpoints + Long-term
Conversation buffer
Workflow variables only
Multi-Agent Orchestration
Supervisor + handoffs
Custom implementation
Sequential nodes only
Human-in-the-Loop
Interrupt & approve
Manual callbacks
Wait for webhook
Real-time Streaming
Token + event streaming
Token streaming
Batch responses
Parallel Execution
Native fan-out/fan-in
Parallel tool calls
Split/merge nodes
Tool Scalability
100+ tools per agent
~10-20 optimal
400+ integrations

Full support Partial/Limited Not supported

WhatsApp

Instagram

Messenger

Email

Web Chat

Specialized Agents

Under the hood there is not one bot but several specialists that hand the conversation between them as needed. You see a single conversation; this is what happens behind it.

Emergency Agent

Response < 3 min

Urgency specialist that automatically detects critical situations and activates immediate escalation protocols.

  • Automatic detection of emergency keywords
  • Immediate escalation to a real person
  • Automatic escalation to medical staff
  • Empathetic but urgent and professional tone
  • 24/7 availability without interruptions

Sales Agent

Hybrid RAG

Commercial advisor with hybrid search (BM25 + semantic) that finds precise information from your catalog.

  • Hybrid search with cross-encoder reranking
  • Updated prices, promotions, and packages
  • Responses adapted to your brand tone
  • Automatic purchase intent detection
  • Intelligent handoff to appointment agent

Scheduling Agent

Google Calendar

24/7 scheduling natively integrated with Google Calendar via OAuth 2.0.

  • Native Google Calendar integration (OAuth)
  • Automatic event creation with reminders
  • Real-time bidirectional synchronization
  • Automatic confirmations via message
  • Modification and cancellation without intervention

Availability Agent

Temporal Awareness

Consultant with temporal awareness that understands "tomorrow", "next week" and verifies schedules in real time.

  • Intelligent natural language date parsing
  • Real-time verification with Google Calendar
  • Automatic buffer times between appointments
  • Alternative time slot suggestions
  • Timezone-aware for international clients

Support Agent

Chatwoot + RAG

Resolves frequently asked questions with RAG and automatically escalates to human agents in Chatwoot when needed.

  • Knowledge base with RAG for FAQs
  • Escalation detection by sentiment
  • Smooth transfer to Chatwoot
  • Complete conversation history
  • Support ticket tracking

Email Marketing

Multi-Provider

Automated campaigns and follow-ups with fallback between providers (SMTP, SendGrid, Mailgun).

  • Automatic post-conversation follow-ups
  • Customizable HTML templates
  • Multi-provider with automatic fallback
  • Retry with exponential backoff
  • Attachment support

WhatsApp Campaigns

10K msgs/day

Massive automated campaigns microservice that sends up to 10,000 WhatsApp template messages per day without human intervention.

  • Up to 10,000 template messages per day
  • Approved WhatsApp Business templates
  • Automated scheduling and queuing
  • Delivery tracking and analytics
  • Segmented audience targeting

Why Choose Hachi?

Key differentiators that set us apart from traditional automation tools

Dynamic Workflows vs Rigid Flows

Unlike n8n or LangChain agents that follow pre-defined rigid workflows, our cognitive agents adapt dynamically to achieve objectives, retrying and self-correcting without manual intervention.

Instant Knowledge Updates

Upload well-structured documents and agents learn automatically via RAG. Change promotions or services instantly—no specialized support needed. Reduce maintenance time and costs dramatically.

Scale to Hundreds of Tools

Our tested backend architecture is ready to rapidly scale to hundreds of agents and integrations. Customer service agents are just the beginning—the platform supports any workflow type.

30-Message Conversation Memory

Agents remember context from the last 30 messages per client: names, services asked, previous promotions sent. Personalized interactions that feel human and build trust.

Customizable Agent Prompts

Sub-prompts are fully configurable and stored in PostgreSQL per user. Customize agent personality, tone, and behavior to match your brand without touching code.

Smart Message Queuing

Celery workers with per-chat locks prevent simultaneous processing of messages from the same conversation, ensuring coherent responses that never lose context.

Cutting-Edge Technology

Enterprise architecture designed for maximum performance, reliability, and scalability

Hybrid LangGraph Orchestration

Rule Engine for fast decisions + LLM for complex scenarios. 50+ nodes with conditional routing.

RAG with Hybrid Search

BM25 + semantic with adaptive alpha, cross-encoder reranking, and Reciprocal Rank Fusion (RRF).

Native Multi-Tenant

Complete isolation per company: Redis prefixes, separate vector namespaces, independent configs.

Redis Shared State

SharedStateStore with typed dataclasses for pricing, scheduling, handoffs, and audit trail.

OAuth + Fernet Encryption

Encrypted credentials in PostgreSQL, automatic token refresh, multi-provider.

Celery + Redis Queue

Asynchronous webhook processing, retry with exponential backoff, no message loss.

What changes in your day

40-60% Fewer no-shows, thanks to reminders
24/7 Answering, including nights and holidays
Seconds To reply, instead of the next morning
0 Flows to redraw when your prices change

Transformative Benefits

Revolutionize your customer service with technology that actually works

Rapid Implementation

System ready to operate in 48 hours. Complete integration with your existing CRM without operational interruptions.

Immediate ROI

Reduce operational costs by up to 70% while increasing customer satisfaction and sales conversions.

Superior Experience

Instant responses, automatic scheduling, and personalized attention that exceeds expectations.

Infinite Scalability

Handle thousands of simultaneous conversations without losing quality or increasing operational costs.

Minimal Maintenance

Self-managed system with automatic updates and proactive performance monitoring.

Advanced Analytics

Detailed performance metrics, usage patterns, and continuous optimization opportunities.

Multichannel CRM with Chatwoot

Human agent panel for supervision + Embedded frontend for bot management

Input Channels

WhatsApp, Instagram, Messenger arrive at Chatwoot

AI Processing

Hachi responds automatically with specialized agents

Escalation

Human agent takes control when needed

Chatwoot CRM

Supervision panel, unified history, tags, and contacts

Bot Panel

Embedded frontend to configure prompts, RAG, and behavior

Google Calendar

Native OAuth for real-time scheduling and availability

Why quotes range from €29 to €900 for "the same thing"

If you are collecting quotes, you will see wildly different numbers described identically: "an AI assistant that answers WhatsApp and books appointments." They are not the same. They are three different technologies.

The question that separates them Tier 1
Drawn flows
Tier 2
Assistants that talk
⭐ Tier 3
Talk AND execute
Price per month €29 – €199 €150 – €500
Implementation €0 – €300 €0 – €1,000
Does it understand free text? Only if you press the right button Yes, it converses well
Does it check your real calendar before offering a slot? ❌ No ❌ No
Does it write the booking into your calendar? It sends a link It pings you to do it
Can it confirm a slot that is already taken? Yes — it cannot see your calendar Yes — it can hallucinate one
Who maintains it You, redrawing flows every time something changes You, rewriting instructions

Hachi is tier 3, and it costs less than its own tier: our most complete plan is €990/month where the market reaches €1,840, and our highest implementation fee is €1,690 where that range starts at €2,000.

When you compare €99 against €390, the question is not "why is it more expensive?" It is: what does it cost you when the €99 one confirms a slot that was already booked?

Plans and Pricing

Prices in euros, VAT not included. No lock-in. Nothing is charged until the 7-day trial ends and you decide to continue.

Solo

You work on your own

€149/mo

+ €290 implementation (one-off)

One calendar, one number
No team behind you

  • ✅ WhatsApp assistant, 24/7
  • ✅ Answers prices, services, questions and location
  • Books into your real calendar, checking availability first
  • ✅ Cancellations and rescheduling
  • ✅ Automatic appointment reminders
  • ✅ Up to 250 conversations/month
  • ✅ Control panel
  • ❌ Voice calls
  • ❌ Campaigns and proactive follow-up
Start 7-day free trial

Essential

You have a team

€390/mo

+ €690 implementation (one-off)

Everything in Solo, plus:

  • ✅ Up to 750 conversations/month
  • Multiple calendars or practitioners, each with their own hours
  • ✅ Full panel with metrics
  • ✅ Edit answers and behaviour from the panel
  • ✅ Your own knowledge base: upload your PDFs and it learns
  • ❌ Voice calls
  • ❌ Campaigns and proactive follow-up
Start 7-day free trial

Professional

Plus the phone line

€690/mo

+ €1,190 implementation (one-off)

Everything in Essential, plus:

  • AI voice reception that books during the call itself
  • ✅ Up to 1,500 conversations/month
  • ✅ 400 call minutes included
  • ✅ Proactive follow-up on cold quotes
  • ❌ Campaigns and outbound calls
Start 7-day free trial

Multi-site / White label

Groups and resellers

from €1,690/mo

Implementation quoted per case

Sell it under your own brand

  • ✅ Multiple sites or companies in one account
  • ✅ Your own branding in the panel
  • ✅ You onboard your clients and set your own prices
  • ✅ Your margin is yours
  • ✅ Priority support and training
  • ✅ Volume and minutes tailored to you
Talk about reselling

When you pay what, with no small print

MomentWhat you pay
Demo video call€0
Setting up your assistant€0
The 7-day trial€0 · no card required
If you decide to continueFirst month + implementation
If you decide not to€0

Pay a quarter up front and the implementation fee is waived.
Conversations beyond your plan: €0.25 each. Extra call minutes: €0.20. Service is never cut off.

🔒 GDPR compliant — Data processing agreement signed, data hosted in the EU.
Live in 3-5 working days — And no visual flows to redraw every month.
🚪 No lock-in — You stay because it works, not because you signed.

When does it pay for itself?

The most honest arithmetic we can show you: how many saved appointments per month cover the fee.

Plan Monthly fee Saved appointments/month
at a €200 average ticket
Solo€149
Essential€390
Professional€690
Complete€990

At a €400 average ticket, halve every figure.

📅 No-shows

Automatic reminders cut no-shows by 40-60%. Every slot that does not sit empty is revenue you had already lost.

⏱️ The 11pm enquiry

Someone who writes at 23:40 and hears nothing until 10:00 has already messaged three competitors. Replying in seconds is not convenience — it is the sale.

👻 The ones who vanish

They asked the price and never wrote again. Proactive follow-up picks them back up on its own, without anyone having to remember.

🧾 The honest comparison

A receptionist in Spain costs €25,000-€35,000 a year fully loaded, and takes days off. Hachi does not replace your team: it takes off their plate what they should not be doing.

You do not need to be a clinic

Hachi grew up serving clinics, but what it solves is not a medical problem: it is the problem of any appointment-based business.

👩‍⚕️ You work alone

Psychology, physiotherapy, nutrition, podiatry, therapies. One calendar, one number, and a phone buzzing while you are with someone.

🏥 Practice or clinic

Aesthetics, dental, spa, beauty, veterinary. Several calendars, several rooms, one overwhelmed front desk.

✂️ Outside healthcare

Hair, barbers, tattoo studios, photography, consultancies, academies, personal trainers. If people book a time, it fits.

🧾 You do not need a company

Sole trader, your own tax ID, no legal entity. The Solo plan exists exactly for that; there is no minimum below which we turn you away.

Data protection, taken seriously

You handle personal data and, in healthcare, special-category data. This is not a checkbox.

🤐 Hachi never messages first

The assistant does not start conversations on its own. Proactive follow-up only acts on conversations that person opened themselves. Nobody gets a message without having written first.

📣 The one exception, said out loud

Campaigns. You supply the list, and with it the responsibility for holding consent. We neither buy nor provide contact databases.

📄 Paperwork in order

You are the data controller; we are the processor. We sign the Article 28 GDPR agreement before touching a single record.

🏥 Health data

Treated as special category (Art. 9), with the safeguards that requires. And you can exercise erasure for a specific person when they ask.

Why it cannot invent an appointment

This is the point that separates Hachi from almost everything else, and it deserves an honest explanation.

A language model is persuasive even when it is wrong. If you let it decide on its own whether Thursday 17:00 is free, one day it will say yes when it is not — and the person who deals with that is your client, at your front desk.

The AI decides

It works out what the person wants, even in a voice note, half-finished, or with three requests in one message. That it does well, and that is what it is for.

The code enforces

Checking availability, writing to the calendar, not double-booking, not dropping a message: that runs on verified code. If the slot is not free, there is no booking, whatever the conversation says.

63

critical rules enforced in code, not entrusted to the model's instructions.

Each one answers the same question: if the model gets it wrong right here, what stops it? It is slow, unglamorous work, and it is exactly the difference between an assistant that dazzles in the demo and one that survives six months without you checking what it says.

The WhatsApp API is not WhatsApp Business

Almost nobody explains this before you sign, and it drives the most important decision of all: your number.

WhatsApp Business appWhatsApp API
Where you use itOn the phone
Who answersOne person
Can it be automated? Quick replies only
Anything to install?Yes, the app

Path A · New SIM

A new number for the assistant. Your usual WhatsApp stays untouched on the phone. Fastest route, nothing is lost.

Path B · Migrate your number

Clients keep writing to the number they know. In exchange, the history and contacts stored in the app stop being there. Meta does not allow the same number on the app and the API at once.

That history can be rescued before migrating. It is not automation: it is database work, and we quote it separately. We say so now, not once there is no way back.

Frequently asked questions

The ones we get most, answered without hedging.

Is the demo free? Do you ask for a card?

Free, and no card. First a video call where we show it working, then 7 days of trial with your assistant already configured. If you do not continue, you pay nothing.

Will it message my patients without permission?

No. Hachi does not start conversations. Follow-up only acts on conversations that person opened themselves. The exception is campaigns, where you supply the list and are responsible for holding consent.

Can it confirm an appointment that does not exist?

No, because the booking is not decided by the language model. Availability checks and calendar writes run on verified code. If the slot is not free, there is no appointment.

Can I keep my usual number?

Yes, but decide it with the facts in front of you. Meta does not allow the same number on the WhatsApp Business app and the API at the same time. Either you use a new SIM, or you migrate your usual one accepting that the history stored in the app stops being accessible. It can be rescued beforehand, quoted separately.

How long until it is running?

Three to five working days once we have your details and the number question settled. We do the setup; you build nothing.

What if I exceed my plan's conversations?

Service is not cut off. Extra conversations bill at €0.25 each and extra call minutes at €0.20. If the overage is constant we suggest moving plan, because it works out cheaper for you.

Is there a lock-in period?

No. You can leave whenever you want. Implementation is charged once on signing, and is waived if you pay a quarter up front.

Does it replace my receptionist?

No, and anyone who says otherwise is selling you smoke. It takes the repetitive part off their plate — opening hours, prices, directions, moving an appointment — so their time goes where a person is actually needed. And it covers nights and weekends, when there is nobody.

For readers who came for the architecture

If you got this far looking for engineering rather than pricing, this part is for you.

🧩 Neuro-symbolic architecture

Graph nodes emit typed signals that a router with no LLM in the loop turns into flow decisions. The model proposes; the state machine disposes. Check-Signal-Act in every node.

🛡️ Guarded invariants

63 properties the system guarantees in code, with an explicit cut-off rule: if Python guarantees the outcome it is an invariant; if only the prompt asks for it, it is a suggestion.

🏢 Real multi-tenancy

Per-tenant isolation down to the conversation checkpointer key. Every query is parameterised and scoped by tenant: one client's state cannot leak into another's.

🔀 Agents that build themselves

The graph can be compiled from the database: a new agent is defined with typed extraction fields and its own tools, with no code deploy.

♻️ Idempotency and compensation

Safe retry across the whole external surface. A duplicated webhook does not create two appointments; a retried campaign does not send twice.

🔌 Multi-provider inference

The inference layer is decoupled: provider and model are selected per tenant. No dependency on a single vendor or a single model family.

What that means in money

The variable cost of serving one client — messaging, inference and telephony — is measured in tens of euros per month, against fees of €390 to €990. Margin does not depend on scaling headcount, because maintaining the assistant is autonomous: there are no flows to redraw when a business changes its prices or its hours.

And the moat is not the model, which anyone can rent. It is the slow work of turning 63 critical behaviours into verifiable guarantees. That does not get replicated in a weekend with a flow builder.

Investing, or building things like this? Write to ceo@hachi.live with "technical" or "investment" in the subject and I will answer personally.