AI operations layer for hospitality

Are you managing — or just watching?

Your dashboard says conversion dropped. Pragma says why — and what to do about it now. An AI operations layer for hotels, resorts and restaurant groups: it turns events into signals, signals into human-confirmed actions, and actions into a result measured in money.

E · S · A · I — Events → Signals → Actions → Intelligence: from raw events to governed action and learning.

Does not replace your PMS, POS, CRM, or ERP — sits above them as an AI action-control layer. Already running in production on a working resort's live data.

We accept only 3 properties for pilot through end of 2026. Pilot is 30–45 days, partially free.

Morning screen

What Pragma shows the manager every morning

One screen instead of scattered reports from PMS, POS, and messengers. Concrete signals, money at stake, and action buttons — not five tabs and a fifth cup of coffee.

Illustrative signals from the first pilot. Real figures are published only with client consent.

E / S / A / I four pillars of the loop

The letters are not decoration — they describe what enters the loop, what matters, what happens, and what we learn.

E
E — Events

Events from PMS, POS, CRM, ERP, tasks, messengers, reviews, guest calls and dialogues, appeals, and operational processes.

S
S — Signals

Variance, risk, overdue work, complaints, revenue dips, blockers.

A
A — Actions

Tasks, notifications, escalations, recommendations, promos, checks.

I
I — Intelligence

Outcome measurement, learning loop, better decisions next time.

Watching is numbers without an answer. Managing is an action with a proven effect. Pragma turns an event into a signal, a signal into a decision, a decision into a human-confirmed action, and an action into a measurable outcome.

Product loop

How Pragma runs operational reality

The chain we anchor on a pilot: Event → Signal → Decision → Action → Outcome → Learning.

1 · Event
Event

A guest checks in, a task slips, revenue dips, a complaint lands, a policy step is missed.

2 · Signal
Signal

The system decides the event matters — risk, loss, blocker, or growth opportunity.

3 · Decision
Decision

Decisioning and agents pick a safe action using rules, context, and past outcomes.

4 · Action
Action

Pragma creates tasks, sends notifications, escalates, proposes upsell, or prepares a management decision.

5 · Outcome
Outcome

We measure what changed: SLA, revenue, complaints, occupancy, discipline, repeat issues.

6 · Learning
Learning

Strong plays are reinforced; weak playbooks are revised. The loop gets sharper.

Pilot vignette

Reservations call

1 · Event

A guest called asking for a room on the weekend.

2 · Signal

AI detected booking intent, but no alternative dates were offered.

3 · Decision

Pragma scored lost-booking risk and potential revenue.

4 · Action

The system created a manager task and drafted follow-up.

5 · Outcome

The manager re-contacted the guest; the outcome was recorded.

6 · Learning

Pragma updated refusal reasons and recommendations for reservations.

Decision Card

Decision Card how AI reaches the manager's screen

When a signal calls for a decision on guests, money, or staff, AI does nothing on its own. It surfaces a card with source, loss estimate, recommendation, and a clear set of buttons. One interface — for calls, complaints, SLA breaches, penalties, HR signals.

What happens after a click The action gets an Impact ID, lands in the executor's app, and is recorded in the history. At 30 / 60 / 90 days, impact is compared to the baseline in the Impact Report.

The same card type — for a call, a complaint, a penalty, a task escalation, an HR signal. Managers learn one interface, not five.

Ask Pragma

Pragma brings decisions to you. And you can ask it directly.

The morning screen and the Decision Card work one way: the system spots a risk and brings it to your screen. But a manager also needs the reverse — to ask. So there is a second mode: a line where you ask a question in plain words across all connected data at once — PMS, POS, CRM, Yandex.Direct, finance, tasks, calls.

The answer arrives not as a chat message, but as a decision card: a number or chart, the data sources, a confidence score, and an action button — the same grade as the signals Pragma surfaces on its own.

Decisions, not a conversation

An answer is a stream of decisions with sources and a confidence score, not a conversation. If the data isn't there, Pragma says “no data” honestly rather than inventing a figure.

Across every integration at once

One question runs across PMS, POS, CRM, Yandex.Direct, finance, tasks, and calls — where before you had to open five systems and reconcile them by hand.

AI proposes — humans decide

Any action from an answer — a task, a follow-up, a change — goes through your confirmation and gets an Impact ID. The same safeguards as when the system surfaces a signal itself.

Data in your perimeter

Questions run over your data inside your own infrastructure, with guest personal data protected. Nothing leaves for third parties.

Free-form questions across all your data are a capability of the Pragma operations layer that we are rolling out on the assistant now. On the pilot we show it on your data and an agreed set of sources.

Sources

Operational signal sources

Pragma does not require one system of record. Every channel feeds events that become signals and actions.

PMS POS CRM ERP / 1C Tasks Messengers Reviews Appeals Guest calls Guest conversations Kitchen Storage Checklists IoT sensors Photo evidence Sanitary standards

Guest calls become another signal source: Pragma shows where a booking was lost, why a guest declined, and what action to take next.

Kitchen, storage and sanitary standards become another source of operational signals: Pragma detects temperature deviations, overdue checklists, write-off risks, missing evidence and recurring violations — and turns them into tasks, escalations and Impact IDs.

Module

Conversation Intelligence: the cause is where it happens — inside the guest conversation

Pragma analyses guest calls and dialogues to surface lost bookings, refusal reasons, unhandled complaints, and cases that need follow-up. AI does not replace the manager: it shows the signal, proposes an action, and routes it for human confirmation.

First pilot · measured on real data

We reviewed 627 recorded reservation calls. Here is what the analysis found — and what becomes your baseline metric on the pilot:

28%

of callers never got through — and no one reached back within 24 hours: 1,057 enquiries lost before a conversation even started

This is one property's baseline, not an industry benchmark. Your numbers will be your own — Pragma measures them on your recordings, and the “after” becomes a pilot metric.

Lost bookings

AI flags calls where the guest was ready to book but left without a next step.

Refusal reasons

Price, no dates, no alternative offered, weak terms explanation, no follow-up.

Follow-up tasks

Pragma creates a manager task and suggests message copy or a re-contact playbook.

Missed revenue

The system estimates potential loss and highlights guests worth re-engaging.

Operator prompter

From a call debrief — to a prompt in the moment

The conversation is where the booking is won or lost. Pragma works right inside it: today through a post-call debrief, next through a live prompt to the operator during the call. We don't promise what isn't there — we've already validated the path to a live prompter technically.

Today · in production

A line-by-line prompter debrief: which move worked, where the booking slipped, and which phrase to use next time instead of the one that didn't land. Not “conversion dropped,” but a specific move — AI proposes, the manager confirms.

Next frontier · roadmap

A live in-call prompt: the guest card, open dates and rates on the operator's screen in the moment. Feasibility is already validated technically; publicly we promise only what works in the pilot.

Roadmap The same speech analytics and prompter — not only for the sales desk but for internal communications too (employee ↔ support): dialogue debriefs, procedure prompts, and escalation of anything left unanswered. A direction of development — the internal-comms phase; publicly we promise only what already works in the pilot.

Call recording and analysis happen on your telephony stack, on the basis of guest consent and your data-processing policy. Pragma does not record calls on its own and does not store audio outside your property's infrastructure.

Get the same breakdown of your reservation desk

Send a period's call recordings and we'll return a breakdown of lost bookings, “let me think” reasons, and missed revenue in money. No rollout, no new system for the team.

Request a call audit →

The analysis runs on your recordings, under your consent and data-processing policy. Pragma shows the signal and proposes a follow-up — your manager confirms.

Module

Reputation Ops: the negative review that never gets written — and never comes back

Pragma already collects reviews from the map and review platforms your property lives on into a single event feed. The next step is a closed loop: unhappy guests are noticed while still in-house, public negatives are answered on time, and a complaint can only be closed by fixing its root cause — with evidence. AI prepares the analysis and a draft reply; your manager decides and publishes.

Verified on live data · July 2026

We audited 2,166 public reviews of an operating resort hotel and checked every negative one for a reply. The team works fast — and still:

84%

of negative reviews had a public reply, median response time — 1 day. Solid manual work — and also its ceiling

51

negative reviews were left unanswered — including two fresh public refund complaints that every prospective guest reads in high season

6 of 6

noise complaints within a single month went unaddressed: individual replies exist, but no one saw the systemic pattern

Most telling: not one of the 325 complaints can be shown to have its root cause fixed and not recurring — the industry simply has no such mechanism. That is exactly what Pragma adds. We can measure your property the same way — from public data, before any integration.

Interception before publication

A short survey on day two of the stay and on departure day. An unhappy guest gets the problem solved before check-out — instead of posting a 1-star review when it is too late.

No negative review gets lost

Every negative review carries a response deadline and an owner. Overdue items escalate to the GM and the owner automatically. A complaint cannot be closed for show: only a fix with photo evidence, or an explicit reasoned decision.

A reply with facts, not boilerplate

AI drafts a reply in your brand voice and inserts the fact from the closed task: “resolved on 12 July, work accepted by the GM”. A human always publishes — auto-publishing does not exist.

Verified resolution

After 4–8 weeks the system re-measures whether the same complaint returned and issues an honest verdict: resolved / recurred / insufficient data. This metric cannot be gamed by deleting reviews.

Today · in production

Review collection from the major map and review platforms into a single feed is already live. Plus a reputation audit snapshot from public data: reply coverage, response speed, systemic gaps — like the example above.

Roadmap · pilot

Pre-publication interception, the SLA and escalation loop, quality-guarded draft replies and resolution verdicts are rolled out on a pilot property. We only promise publicly what already works on a pilot.

Pragma does not inflate ratings, does not remove or commission reviews, and never auto-publishes replies. We do not promise rating growth: pilot metrics are response speed and coverage, the share of negativity intercepted before publication, and verified root-cause fixes. Brand replies are published only by your staff.

Get a reputation audit snapshot of your property

Send a link to your property's public listing — we will return an audit built from public data: how many negatives are unanswered, how fast your team responds, and which complaints recur systemically. No integration and no access to your systems required.

Request a reputation audit →

The audit uses only your property's public reviews. Pragma shows the gaps and suggests an action plan — the decisions remain yours.

Module

Pragma Hygiene Intelligence: kitchen and storage as a source of operational risks

Not a standalone HACCP log — a sanitary risk layer inside Pragma Command Center.

Pragma Hygiene Intelligence connects POS, 1C/storage, checklists, photo evidence and IoT sensors into a unified kitchen and storage control loop. It doesn't just record temperatures or cleaning. It identifies the risk, suggests a corrective action, assigns responsibility, requires proof of completion and saves the result to Impact ID.

Cold chain

Temperature deviations, prolonged door openings, manual probe verification, write-off risk and a task for the responsible person.

Sanitary checklists

Shift opening and closing, zone cleaning, disinfection, labelling, product placement, photo confirmations.

Shelf life & storage

Batches, stock levels, expiry dates, write-off risk, link to sales and procurement.

Audit Pack

Temperature logs, checklists, incidents, corrective actions and evidence for internal or external audits.

Roadmap · pilot loop for restaurants, kitchens, sanatoria and SPA hotels.

Module

Pragma Risk Intelligence: where the business loses money — before the report shows it

Not a security add-on — a money-control layer inside Pragma Command Center.

Pragma Risk Intelligence looks for financial, operational and managerial anomalies across PMS, POS, CRM and 1C data, turns them into signals with a rouble loss estimate, explains the cause and surfaces a Decision Card with evidence to the manager. The AI never hunts for fraud on its own and never acts by itself: it shows the anomaly, gathers the evidence and hands the decision to a human.

Plan-vs-actual anomalies

Sharp revenue deviations, rising food and labour cost, falling RevPAR, occupancy that doesn't match revenue — on your existing plan-vs-actual thresholds.

Suspicious procurement

Prices above the median, payments split under the approval limit, repeating amounts, procurement growing without revenue, purchases bypassing policy.

Counterparties & 1C

Supplier risk dossier, repeating tax IDs and bank details, hidden links, suspicious detail changes, new counterparties with fast-growing turnover.

Operational abuse

Unjustified discounts, refunds and order cancellations, manual cheque adjustments, write-offs, night-shift operations and out-of-norm actions.

AI document auditor

OCR of contracts, invoices and acts, detail extraction, contract-invoice-act reconciliation, mismatch detection and risk explained with quotes from the documents themselves.

Every risk signal passes through rules and human approval — never straight into a fine. The loop expands as your sources connect: 1C, POS, documents.

Module

Pragma Academy: standards live in shift clearance, not in a binder

Not a standalone LMS — a training and clearance loop built into your live policies and tasks.

Academy extends the live policy-and-testing loop into a full cycle: a new hire gets a role-based onboarding plan, takes courses assembled from your policies, proves skills in practice and earns clearance to work shifts. Managers see each person's readiness — instead of discovering it at peak hour.

Role-based onboarding

A day-one / week-one / month-one adaptation plan starts automatically on hire. A mentor signs off on practice; HR tracks every newcomer's progress.

Courses built from policies

A course is assembled from live policies: update the document and the training follows. Reading and test results are recorded.

Exams that test doing

Beyond recall: situational cases from real hotel practice and tasks with in-app photo evidence. AI drafts questions from the policy — the author approves every one.

Clearance and knowledge checks

Periodic micro-checks against knowledge decay. Shift-clearance status is visible before the shift; certificates verify by QR inside and outside the company.

In development · the core loop — policies with mandatory knowledge testing — is already live in the product.

Where control slips

Your property is already digital. Management is still manual.

  • 🏨Reservations — in the PMS
  • 💳Revenue — in the POS
  • 📋Leads — in the CRM
  • 📊Finances — in the ERP
  • 💬Tasks and assignments — in messengers
  • ⚠️Guest complaints — in conversations
  • 🧠Control — in the manager's head
  • 🌡️Sanitary logs, kitchen and storage — in paper, Excel or messengers

The data exists. But a dashboard shows the temperature, not the diagnosis: “conversion is down” is a result, while the cause lives inside a specific conversation, shift, or process. “Let’s tighten up” is not an action. What’s missing is the layer that turns the number into a confirmed action and a measurable result. Managers learn about a problem no earlier than the guest does.

When temperatures, cleaning, labelling, expiry dates and write-offs exist separately from POS, 1C and tasks, managers see violations too late. Pragma turns these events into signals and actions within the unified operational loop.

Pragma does not replace your stack. It makes it behave as one loop.

Shelter, R-Keeper, amoCRM, 1C, and other tools hold data in their lanes. Pragma ties them to tasks, regulations, people, and management actions — so owners see signals and actions, not only disconnected reports. We reviewed some forty solutions built for this industry: AI appears in each of them in one spot — pricing here, calls there, cameras elsewhere. Pragma assembles those signals into a single management loop.

PMS shows reservations — Pragma surfaces revenue-at-risk.
POS shows checks — Pragma spots average-check drops and write-offs.
CRM shows leads — Pragma highlights missed follow-ups.
1C shows finance — Pragma highlights deviations and cash-flow risks.
Tasks show execution — Pragma surfaces blockers, delays, and repeat failures.
Telephony and messengers hold conversations — Pragma surfaces lost bookings, refusal reasons, and weak follow-up.
Capability ERP / accounting BI CRM Pragma
Cross-system operational loop
Tasks and escalations from signalsPartial
Accountability tracePartial
Works between systems
No PMS/POS/CRM replacement
Agents and action playbooksPartial
Audit and approvalsPartial
Example: room turnover
ERP: checkout recorded
BI: summary arrives tomorrow
Pragma: housekeeping task → SLA control → next guest without friction
Boundaries

What Pragma is not

Pragma is not your PMS, POS, CRM, ERP, telephony stack, or contact centre. It sits above them and turns their events into management actions.

Conversation Intelligence does not replace telephony and is not a call centre product. It is a Pragma module that treats calls and dialogues as operational signals: lost bookings, refusal reasons, complaints, and follow-up tasks.

The reputation module does not “manage ratings” and is not an SERM agency: it does not inflate scores, remove reviews, or publish anything on the hotel's behalf without a human. It is the Pragma loop that turns guest reviews and surveys into signals, tasks, and verified root-cause fixes.

Rollout

Where implementation starts

Operations Control

Tasks, blockers, delays, escalations, and execution discipline.

Guest Experience

Complaints, guest requests, response speed, service paths, repeats.

Revenue & Occupancy

Occupancy, upsell, lost leads, marketing signals, revenue per guest.

HRM & Regulations

Shifts, workload, policies, knowledge checks, execution compliance.

Food Safety & Loss Prevention

Temperature deviations, sanitary checklists, expiry dates, write-off risk, photo evidence, Audit Pack.

From our ad audits

In our ad-audit work, a sizeable share of paid budget — often a third or more — leaks into irrelevant traffic and competitor-brand poaching with near-zero return. The Revenue & Occupancy loop surfaces it as a signal — instead of you finding it at quarter's end.

Five examples: event to action.

The same loop in F&B, rooms, HR, and reservations — without turning the page into a technical manual.

EEvent: margin signal from POS reporting
SSignal: category crosses an agreed threshold
AAction: task to head chef — review purchasing and write-offs
IOutcome: signal closed; root cause logged for the next loop
EEvent: guest checkout in PMS
SSignal: housekeeping window under pressure
AAction: room task plus escalation timer
IOutcome: next guest on time against SLA
EEvent: new hire enters the system
SSignal: open policies and knowledge checks
AAction: training and clearance chain
IOutcome: clear readiness for shifts
EEvent: guest called asking for a weekend room
SSignal: booking intent, but no alternative dates offered
AAction: manager task plus drafted follow-up
IOutcome: guest contact logged; refusal reasons updated for reservations
ERefrigerator sensor records a temperature deviation; shift-closing checklist not confirmed
SPragma identifies write-off and sanitary violation risk, checks shift context, stock levels and problem recurrence
ACreates a task for the sous-chef, requires manual probe verification and photo, triggers escalation on overdue
IRecords the corrective action, links it to the batch, shift and Impact ID; repeat problems enter Risk Memory

Three focus zones for owners and directors

Restaurant complex
COO
Floor variance is noticed late — POS and management tasks are not tied
Fewer blind spots in the operating day
Without the loop
Responses to variance are fragmented
With Pragma
Signals become owned tasks
Spa hotel
Owner / GM
Issues surface in chat before they exist as work items
Faster routing to owners
Without the loop
Guest history is not tied to tasks
With Pragma
One response chain with SLA control
Multi-site group
Commercial director
Leads and marketing sit apart from occupancy and revenue per guest
Fewer lost follow-ups
Without the loop
No single signal across funnel and occupancy
With Pragma
Signals and actions in one loop
Agents

Pragma agent layer First wave

The product core already holds tasks, signals, and execution control. Below, honestly: which of the specialised loops run in the first release — and which turn on during the pilot as integrations land.

Live in the first loop
Operations Agent
Turns signals from systems, tasks, and communications into clear actions for the team.
First wave: supported by tasks and escalations.
Signal Analyzer Agent
Reviews SLA, variance, and operational signals; helps separate noise from risk.
Expands as sources connect.
Guest Experience Agent
Sees complaints, appeals, reviews, and guest dialogues — helps create tasks faster and close issues before a negative review.
First wave: messenger ↔ tasks; richer text analysis on the roadmap.
Revenue Agent
Finds lost leads, weak follow-up, missed upsell, and revenue potential across bookings, CRM, and guest calls.
Recommendations require approval — no autonomous financial moves.
Expanding on the pilot · roadmap
Occupancy Agent
Reacts to occupancy, revenue, and marketing variance with safe, approvable actions.
Designed with hoteliers; playbooks agreed on the pilot.
Hygiene Risk Agent
Monitors kitchen, storage, checklist and IoT signals: temperature deviations, overdue checks, write-off risk and missing evidence. Suggests corrective actions but does not write off products or apply sanctions without human confirmation.
Pilot loop for restaurants, kitchens, sanatoria and SPA hotels.
Pilot

Pragma must prove impact — not only run

We baseline sites before go-live, then measure change at 30, 60, and 90 days. No promised “auto-growth”; a transparent method instead.

Tasks inside SLA
Share closed on time
Incident response time
Signal to first action
Leads without reply
Queue and return-to-work
Upsell per guest
Offers tied to actual sales
Repeat complaints
Themes and breakpoints
Write-offs and returns
Signals from POS and kitchen
Occupancy & RevPAR
Aligned with marketing signals
Policy execution
Tests, clearances, violations
Temperature deviations
Frequency and resolution time
Sanitary checklists
Completion rate on time
Recurring violations by zone
Zones with systemic failures
Write-off risk
Prevented losses vs actual

Each action gets an Impact ID: recommendation → approval → execution → outcome.

Concrete deltas come from your pilot data; we do not publish borrowed case figures or guaranteed percentages.

How the loop is built in brief

Sources
PMS · POS · CRM · ERP · tasks · messengers · reviews · calls & dialogues → APIs, webhooks, exports (phased)
Event layer
Normalisation, idempotency (the same signal won't double-count), inbound signal journal
Pragma Core
Signals → policies → tasks and notifications → audit
Interfaces
Web app · mobile surface · API · dashboards
Infrastructure
Customer-controlled deployment; stack details agreed per pilot
Customer VPS
Typical pilot start. Data stays inside your own infrastructure.
Managed cloud
Optional. Lighter operations.
Private / on-prem
For enterprise constraints — dedicated footprint.
Human-in-the-loop Action audit trail Data sovereignty No PMS/POS replacement

Impact sizing on the pilot

The dashes in the table are deliberate: we take potential figures from your data, we don't invent them. Here is what it looks like in practice — the first reservation-desk pilot already showed:

28%never got through and got no callback within 24h — lost before a conversation

This is one property's baseline, not an industry benchmark. Your numbers will be your own — Pragma measures them on your data, and the “after” becomes a pilot metric.

Illustrative upside Payback horizon
Small footprint Based on your baseline Case by case
Mid-size group Based on your baseline Case by case
Holding Based on your baseline Case by case
Less operational chaos
Leadership time returned
Lower incident cost
Policy discipline
Method
1Baseline: agree the metric set and capture current values
2Go-live: tasks and signals on selected sites
3Checkpoints at 30 / 60 / 90 days vs baseline
4Pilot report with decisions on scaling

We do not promise guaranteed revenue uplift — we agree measurable metrics up front and compare honestly afterwards.

Control

AI proposes. Humans confirm. Pragma records the outcome.

On the pilot, Pragma does not run critical actions autonomously. AI forms the signal and recommendation; the manager confirms, edits, or rejects it; the system keeps the decision history and result.

Human-in-the-loop

Decisions on guests, money, and people require human approval.

Audit trail

Every action is logged: who saw it, who approved it, who executed it.

Privacy-by-design

Recordings and transcripts follow your access, retention, and consent rules.

Control

Pragma does not act without a human

At pilot start, Pragma operates in observation mode only. Active actions only after your manager confirms.

  • Pragma does not change prices or rates without manager approval
  • Pragma does not charge money or apply penalties automatically
  • Pragma does not make HR decisions without a human
  • Every recommendation appears on the manager's screen with an explanation
  • Any type of recommendation can be disabled at any time
  • Your data stays in your infrastructure (self-hosted)
Product screens

See where revenue leaks — and why the number is trustworthy

Not another dashboard your staff will abandon. A live scenario: a signal from the floor → your decision → a documented result. Step through it yourself.

The screen a manager opens first: not a list of all the data, but the one thing that is costing money right now and waiting for a single decision.

Step 1 · A signal arrives. Pragma captured the complaint with its source, estimated the loss, and proposed what to do.

  • Over one shift this catches losses that would otherwise slip away unnoticed
  • A decision in 40 seconds — no meetings, no message threads
  • Every action stays in history — who decided, and why
Is it clear what this screen does?

The on-shift staff screen: exactly what to do now, and a button to confirm with a photo — in two taps.

Step 1 · A task for the shift. No five different apps — just what to do now and by when.

  • Proof is a fresh in-app photo, not an old one from the gallery
  • Two taps for staff — no training on a new system
  • The manager sees confirmed work, not a vague "think it's done"
Is it clear what this screen does?

Your screen: where revenue leaks across every property — and why the number is trustworthy. The data underneath is logged by the shift, not by you by hand.

Step 1 · Where revenue leaks. The number is trustworthy: the shift logged it, the manager confirmed it — Pragma only compiled it. Next, one action.

  • Every property on one screen — no manual report-gathering
  • An anomaly is visible right away, not at month-end
  • The task goes out with a deadline and stays in the history — you see whether it was done
Is it clear what this screen does?

These are three screens from the product. The rest is easier to show on your data than to describe.

Personal demo of the real product
Traceability

Pragma doesn't just recommend. It proves impact.

1
Detected a signal
2
Proposed an action with explanation
3
Manager confirmed
4
Action completed — with evidence
5
Result measured: ΔRevenue / ΔSLA / ΔReviews
Impact ID #UA-00421 — saved in history
Full trail · Impact ID #UA-00421
  • 13:42 · 📞 Guest call (PMS event 9821)
  • 13:43 · ⚠️ Signal “lost booking intent”, confidence 0.87
  • 13:44 · 🤖 Recommendation: follow-up + 3 alternative dates
  • 13:51 · 👤 Alexey M. approved, chose “follow-up”
  • 14:30 · ✅ Guest contacted, booked 2 nights
  • 15:00 · 💰 ΔRevenue +21,000 ₽ credited to the property

Every Pragma action gets a unique identifier. You always see: what the system proposed, who confirmed it, what was done, and what the measurable outcome is.

AI proposes. Humans decide. Results — in money, time, and service quality.

Proof framework

How Pragma proves impact

Pragma is not a pitch deck. It is a four-step framework that ends not with an interface, but with a report — a measurable delta on the metrics you agreed up front.

1
Baseline
3–5 days

We agree the metric set and capture current values for your property: tasks-in-SLA, time-to-first-action, lost follow-ups, policy execution, RevPAR, etc. Without this snapshot, every later step is meaningless.

2
Shadow Mode
7–10 days

Pragma watches and emits signals — but takes no actions. We compare what AI saw against what staff saw. This is when we calibrate confidence and cut out noise.

3
Recommendation Mode
14–20 days

AI proposes actions. The manager confirms, edits, or rejects each one. Every decision gets an Impact ID. Override rate becomes a metric of its own: how often a human disagrees with AI.

4
Impact Report
30 / 60 / 90 days

Roll-up of baseline metric changes. Not opinion, but a quantitative gap, broken down by signal, with the chain recommendation → approval → action → outcome.

Override rate is a discipline metric for the AI itself. Too low — managers rubber-stamp everything; too high — recommendations miss reality. A mature pilot settles into a meaningful corridor, and that's the signal that both sides of the loop are working.

We do not promise guaranteed growth. We promise a measurable before/after on the metrics you agreed — and we commit to showing it within 90 days.

First pilot

A spa hotel in Anapa — Pragma's first reference

Active pilot, 2026. We will name the client only after they agree — for now we share the format and context anonymously. Measurements are published after the pilot, and only what the client approves. We do not promise guaranteed percentages — every property is different.

Before Pragma
Housekeeping tasks lived in WhatsApp, penalties in Excel, guest complaints reached managers after the fact through reception. Regulations existed, but knowledge was checked verbally once every six months. Managers couldn't see SLA breaches until the shift was over.
What we did
Connected manual event entry plus a Shelter API connector (bookings, check-in/out). Rolled out the decision-card flow for task approvals and cascading appeals. Launched regulations with mandatory testing. The first 7–10 days ran in Shadow Mode — no active actions.
What we measure
Time-to-first-action on guest complaints · share of tasks closed with evidence · percent of staff passing regulation tests · SLA variance by shift. Slices at 30 / 60 / 90 days against the pilot baseline.
Status: active pilot, 2026 · now — Baseline and Shadow Mode (data collection and observation) · PMS stack — Shelter
Where the pilot is now
  1. nowBaseline — we capture the starting point on agreed metrics
  2. nowShadow Mode — Pragma observes and collects data, no active actions
  3. Recommendation Mode — AI proposes, a human confirms
  4. Impact Report — a measurable delta vs baseline at day 30 / 60 / 90

The rollout has only just begun — data collection and observation are underway. That is why there are no “growth percentages” here: the first measurable cuts will come after Shadow and Recommendation Mode. We will show only what is confirmed on the property’s data and approved by the client.

Full client name, logo, and specific numbers — only with written consent. This page shows format and context without revealing sensitive data.

Materials

Pragma documents

A short overview for a first look, plus the full product presentation. Grab them before we talk — the conversation gets sharper.

We accept only 3 properties for pilot through end of 2026. One slot taken. 2 remain.

Stop watching.
Start managing.

01
Diagnostic
3–5 days
02
Setup
3–5 days
03
Shadow Mode
7–10 days
04
First actions
14–20 days

Audit 50 calls for lost bookings

Tell us about your property and your goal — we reply within one business day. No sales scripts.

Email us at info@anapaerp.ru →

No obligation Reply within one business day No sales scripts Data in your perimeter
FAQ

Before the pilot

Missing a question? Email info@anapaerp.ru

No. Pragma sits above Shelter, R-Keeper, amoCRM, 1C, and other systems. It collects events, finds signals, and triggers management actions.
No. Conversation Intelligence is a Pragma module that treats calls and dialogues as signal sources: lost bookings, refusal reasons, complaints, and follow-up.
Yes. The first audit can run on call exports or manually uploaded audio. The pilot connects one telephony provider.
Not on the pilot. AI prepares follow-up; the manager confirms, edits, or rejects the action.
Every action leaves a measurable trail: event, signal, recommendation, human confirmation, execution, and outcome.
One property, an accountable GM, access to a subset of data, sample calls or one telephony provider, and agreed data-processing rules.
Both. Pragma surfaces signals to your screen, and you can ask it a question in plain words across all connected data — PMS, POS, CRM, Direct, finance, tasks, calls. The answer comes as a card with sources, a confidence score, and an action under your confirmation — not as a chat thread. Free-form questions across all data are being rolled out on the assistant now and shown on the pilot using your data.
Discuss pilot