I INSIS
Internal preview concept.ins.is May 2026

This is not a CRM.
It's the operating system
for our entire team.

INSIS — Inside Information System. One tool where the editorial team produces content, sales replies to clients, SEO ships landing pages, and analytics shows what actually generates revenue. No more twenty tabs, no more screenshots in chats, no more "where is that file again."

"Idea → published"
cycle 5× shorter
60%
Auto-mode handles
60–70% of WhatsApp
−60%
North Star:
Cost per Lead in 12 mo
app.ins.is/brain/bundles/db-2412
Editorial Brain Bundles DB-2412
Damac Bay launch
Inside Realty · EN + RU + AR · 10 artefacts
in review
Bundle progress 8 / 10 artefacts
Damac Bay walkthrough 4:32
primary asset · transcript ✓
📍 Business Bay
Cavalli-branded tower
4 facts you need
to know
TG carousel · 8 slides
other artefacts
LinkedIn · 3 posts EN · RU · AR ready
Instagram stories · 3 9:16 vertical ready
Longread (in.ae) 1,480 words rendering…
FAQ block (for KB) 7 Q&A pairs draft
Editorial Brain· AI Sales Agent· Knowledge Base· Dual-brand SEO· WhatsApp auto-mode· Narrative Bundles· Multi-tenant· EN · RU · AR·
§ 1 · what it is

It's your team,
amplified.

INSIS is a closed multi-tenant platform for the Insidex group. Not a public SaaS. Not a CRM. Not a Bitrix replacement. It's the layer on top of every tool you already use, gathering them into one interface and automating 70–85% of the routine work.

Editorial Brain

From narrative to publication — in one tool. Idea → brief → artefacts (TG carousel, LinkedIn post, stories, longread, FAQ, landing page) → distribution across channels. One narrative is automatically packaged for every brand, format, and language.

AI Sales Agent on WhatsApp

30 numbers, 3 languages (RU/EN/AR from day one), 60–70% of inbound messages handled by auto-mode. Operators see suggested replies for the rest and send them with one click. With a kill switch, escalation for sensitive topics (price, legal, VIP, customer frustration), and output sanitization. No hallucinations.

Knowledge Base

The company's single source of knowledge — style guides, FAQ, sales scripts, legal references, market analysis. AI agents use it for retrieval, operators search it directly, new brokers onboard with it. Built on top of AFFiNE with hybrid search (vector + BM25) and Cohere reranking.

Web Operations · Dual-brand SEO

1,500+ landing pages on two independent sites (insiderealty.ae + in.ae) — generated automatically from UnitPilot master data. The SEO team shrinks from 7 people to 1–2 system operators. Unique content per brand, schema markup, internal linking, A/B tests — all automated.

Analytics — from impression to deal

End-to-end attribution: the full path from a Telegram post → landing click → WhatsApp message → Bitrix lead → closed deal. ROAS, CPL, conversion funnels — in one dashboard. Editorial Brain learns: which narratives → which formats → which results.

Serving 5 brands in the group
Inside Realty
Real estate agency
insiderealty.ae
Inside Media
Internal · production-side
analytical observer
In.ae
Independent media portal
in.ae
UnitPilot
B2B SaaS for brokers
unitpilot.ai
Insidex
B2C AI valuation · in dev
insidex.ae
§ 2 · why

Right now 15 people live in 30 tabs.
It works — but we've hit the ceiling.

This isn't criticism of the team. The team is excellent. It's criticism of the tools — they were never designed for each other. Notion + Google Drive + Airtable + Creatium + Wazzap + six different SMM services + Bitrix24 — each one is fine in isolation. Together, they create a thousand small operational frictions that quietly drain hours every day.

Media department · 15 people

Today
  • Editor-in-chief + 2 copywriters + 3 designers produce content manually across dozens of disconnected tools
  • Style guides live in Notion, brand assets in Drive, briefs in chats
  • Brief takes 2–3 hours to write; "idea → post" cycle is 2–3 days
  • 7 SEO specialists semi-manually build in.ae landing pages via Creatium + Airtable
  • 2 SMM managers juggle 5 different services to publish to channels
  • 3 video producers work in isolation from the rest of the editorial team
With INSIS
  • + "Narrative → published" cycle in hours, not days
  • + One narrative becomes TG + LinkedIn + Stories + Longread + FAQ automatically
  • + Style guides live in the system; agents follow them automatically
  • + SEO team: 7 → 1–2 system operators
  • + 25–30 publications per day instead of 5–7

Sales team

Today
  • 30 WhatsApp numbers via Wazzap (vendor lock-in, expensive)
  • Brokers answer the same client questions a hundred times
  • Market knowledge is scattered — a new broker spends a month onboarding
  • No automation: every message is manual work
  • Attribution is weak — we don't know which posts drive deals
With INSIS
  • + Auto-mode answers 60–70% of inbound automatically
  • + Operators see suggested replies for the remaining 30–40% and send them in one click
  • + Knowledge Base is searchable Q&A for every broker
  • + Response time: 30+ minutes → under 2 minutes
  • + 3× more conversations per operator at the same quality
  • + Full path from impression to deal in Bitrix24

Analytics

Today
  • GA4 on websites, Wazzap separately, every social network on its own
  • No unified view of "post → click → WhatsApp → lead → deal"
  • Decisions are made on intuition, not data
  • Traffic manager can't see ROAS across all channels at once
With INSIS
  • + One dashboard: impression to deal
  • + Editorial Brain learns: narrative → format → conversion
  • + Traffic manager sees ROAS across all channels in one place
  • + Per-narrative tracking — which narratives actually convert, which just create noise
North Star Metric

Cost per Qualified Lead
down 60% in 12 months

Not "number of publications." Not "response time." Not "open rate." The only metric that matters: how much money it takes to get a qualified lead into Bitrix24. Everything else is a proxy.

Editorial velocity
25–30/day
vs 5–7 today
Auto-reply coverage
60–70%
WhatsApp inbound
SEO uniqueness
95%+
no duplicate
Both sites top-10
70%+
target keywords
§ 3 · modules

One deployment,
nine modules,
clean boundaries.

INSIS is built as a modular monolith in TypeScript. Not microservices (we're a small team — we don't need them). Not spaghetti (modules talk only through events and public APIs, exactly like microservice boundaries). Each module owns its own database tables. No direct SQL into other modules' tables. Ready to extract any module into a service when the time comes, but we don't do it "just in case."

packages/brain

1 · Editorial Brain

Content production from narrative to publication-ready artefact. Topics DB + News Scout, Format Strategist (AI), Brief Generator (AI), Production Skills for each format, three approval gates (Topic → Format → Final), brand context per (brand, locale).

TopicsFormat StrategistBrief GeneratorNarrative BundlesVoice Guides
packages/posting

2 · Posting

Publishing artefacts to distribution channels via Postiz + native publishers (Telegram, custom integrations). Schedule Optimizer picks timing from best-time data. A bundle is published as a coordinated content drop: video → description → series of posts → stories → longread → FAQ, in the right order.

PostizNative TelegramSchedule OptimizerContent Plan
packages/comm

3 · Communications · AI Sales Agent

30 WhatsApp numbers (4 WABA + 5 grey + 21 broker phones). Baileys + Meta Cloud API. Conversation Engine + AI Sales Agent with auto-mode and suggestion-mode. Operator inbox UI, Bitrix24 sync. Confidence scoring, kill switch, output sanitization. 8 escalation triggers for sensitive topics.

WhatsApp · 30 numbersAuto-modeOperator InboxBitrix24 syncKill switch
packages/knowledge

4 · Knowledge Base · RAG

AFFiNE as primary KB storage (Notion-like editor for the team). Custom RAG layer on top — semantic chunking, Voyage AI embeddings in pgvector, hybrid search (vector + BM25), Cohere reranking. Multi-language retrieval (RU/EN/AR). Workspaces per area: Editorial, Sales, Legal, Shared, Internal.

AFFiNEpgvectorVoyage AICohere Rerank5 workspaces
packages/analytics

5 · Analytics

ClickHouse warehouse + native collectors (IG, LinkedIn, TG, YouTube, Plausible × 4). Bitrix24 webhooks. Metabase dashboards. Editorial Brain feedback loop: which narratives → which formats → what converts. Per-bundle attribution. LLM cost tracking (model, tokens, USD, latency, outcome).

ClickHousePlausible × 4Bitrix attributionCost eventsMetabase
packages/market

6 · Market

UI for browsing market references through UnitPilot DB (read-only). Districts, projects, developers, prices, units. UnitPilot stays the source of truth — INSIS reads via CDC + webhooks. No data duplication.

UnitPilot DB readDistrictsProjectsUnits
packages/web-builder

7 · Web Builder · Dual-stack

Landing generator for two independent sites. Inside Realty → Next.js 15 on Vercel. In.ae → Astro on Cloudflare Pages. Different stacks, different hosting, different content per brand — all so Google can see them as independent (ADR-005). Schema markup, sitemap, internal linking, A/B testing — automated.

Next.js · VercelAstro · CloudflareSchema.orgA/B tests
packages/asset-layer

8 · Asset Layer

Domain-aware layer over Immich. Auto-tagging via Claude Vision, asset usage tracking, mood tags, brand affinity. MCP server for agents: "find photos with Business Bay skyline for the Damac Bay landing" — agent goes to Asset Layer itself and finds them. Immich on VectorChord for optimal performance.

ImmichVectorChordClaude VisionMCP server
n8n self-hosted

9 · Workflow Engine

n8n for visual workflows. Head of Media builds custom automations without code: "new sales signal → create topic → ping me on Telegram", "8 am daily → gather tomorrow's approved bundles → send me the digest." Custom INSIS nodes connect to our API. n8n doesn't own data — it orchestrates API calls.

n8nCustom INSIS nodesTemplates libraryNo-code for Head of Media
§ 4 · scenarios

Three stories
about how it all works.

Better to see one end-to-end scenario than read ten architecture diagrams. Here are three "days in the life" of the team with INSIS.

01
Scenario
Video → Narrative Bundle

The video team filmed a Damac Bay walkthrough — 4 minutes, floor plans, unit breakdown. Before: editor watches the video, writes the YouTube description, copywriters draft a post series by hand, SEO specialist separately produces an article. Cycle: one week.

With INSIS: the video gets uploaded to Immich with tag editorial-source. Asset Layer triggers the video-published source handler. Whisper transcribes. Format Strategist proposes the default bundle mix. Brief Generator writes briefs for each artefact in parallel. Production Skills generate them. 30 minutes later — the full bundle lands on Head of Media's desk.

Asset LayerWhisperFormat StrategistBrief GeneratorProduction Skills
1
Video uploaded to Immich
tag: editorial-source · duration 4:32 · YouTube + storage
2
Whisper transcription (RU)
confidence 0.94 · 2 minutes · text stored in editorial.assets.metadata
3
Topic created with primary_asset_id = video
source_type: video_published · suggested_brand: inside-realty
4
Format Strategist proposes a bundle mix
1× video description · 1× TG carousel · 3× LinkedIn · 3× IG stories · 1× longread · 1× FAQ
5
10 artefacts generated in parallel · 23 minutes
brand voice · forbidden phrases filter · cross-brand check
6
Bundle in review · Head of Media notified
one approval button for the whole pack, or per-artefact tweaks
7
Approved → Posting distributes across plan
Day 0: video + announce post · Days 1–3: posts · Days 2–4: stories · Day 5: longread · Day 7: FAQ → KB
02
Scenario
Client messages WhatsApp

Sunday, 23:45. A client writes to our brand-line WhatsApp: "Hi, I'm looking at a 2-bed in Business Bay under 5M." Brokers are offline, but the client doesn't drift to a competitor — auto-mode is awake.

The AI Sales Agent detects the language, queries the Knowledge Module for relevant context (units, projects, prices), checks all 8 safety gates. Confidence 0.91 — auto-mode is cleared. Before sending, the output sanitizer scans: no forbidden phrases, no In.ae mention, no internal IDs leaked. 12 seconds later the client gets a meaningful, brand-correct reply.

Auto-mode 0.91RAG retrieval8 safety gatesOutput sanitizationBitrix24 sync
A
Aida Mansoor
online · sun 23:45
Sunday, 23:45
A
Hi! Looking at a 2-bed in Business Bay under 5M. What's available? Thanks.
23:45
AI typing…
Hi Aida! For a 2-bed in Business Bay under 5M we have options across Damac Bay by Cavalli and Aykon City — ready units from AED 3.9M to 4.8M, 86–112 m². Want me to send a comparison with floor plans? Also: ready or off-plan?
23:45
Auto-mode decision
ai_decisions · 12s · 23:45
Confidence 0.91
threshold 0.85 ✓
Safety gates · 8/8 passed
Kill switch enabled
No price commitment
No legal advice
Not VIP
No assigned broker
Operator offline
No sensitive topic
No frustration detected
Output sanitizer
forbidden phrasesclean
cross-brand mentionsclean
PII leakageclean
B24
Bitrix24 lead created
UTM: tg-damac-launch
audit.events ✓
action: auto_reply.sent
cost_events logged
$0.012 · sonnet-4-7
03
Scenario
New project → 2 landings

Sales adds a new project to UnitPilot. INSIS gets a webhook via CDC. Web Builder creates two paired landings: one for Inside Realty, one for In.ae. Two websites, two brands, two independent versions — each with its own tone, structure, schema markup, typography, photo selection.

This is the dual-brand SEO strategy (ADR-005): both sites in Google's top-10 for the same queries, looking independent. Same project, fully different prose, no cross-references. Google sees different ASNs, different stacks, different analytics owners, different author profiles.

UnitPilot CDCNext.js · VercelAstro · CloudflareADR-005
insiderealty.ae/damac-bay
Inside Realty
ListingsProjectsAbout
Damac Bay by Cavalli — Premium Tower in Business Bay
From AED 3.9M · 60/40 plan · Q3 2027
Speak to a senior broker
MA
Mahmoud A. · 12 yrs in Dubai market
schema
RealEstateAgent
author
Mahmoud A.
analytics
Plausible #1
in.ae/projects/damac-bay
In.ae
DistrictsReportsNews
Project review
Damac Bay Business Bay residences — independent project review
in In.ae Editorial · 8 min read
Photo: Damac Properties
Contents
1. Developer track record
2. Comparable projects
3. Payment plan analysis
Q: Is off-plan safe?+
Q: 60/40 vs 50/50?+
schema
Article + FAQ
author
In.ae Editorial
analytics
Plausible #2
Independence check passed
ADR-005 · auto
Cross-links
0
Shared accts
0
Dup score
12%
Schema drift
none
§ 5 · roles

What each person gets
in their workday.

One platform, different interfaces. Every role sees only what it needs — no noise. Capabilities are pinned in the system, RBAC on every endpoint, RLS on every table. No accidental leakage between roles or brands.

HM
Head of Media
editor-in-chief · 1 person

8 AM — Morning Briefing: 12 ranked topics in the Telegram bot. Approve top-3 with one tap. By 9:30 the desk has 3 Narrative Bundles in review (one bundle per click, not a thousand scattered posts). Per-bundle approval: video + 10 artefacts on one screen, approve all / approve except X.

User story

"I want to see the entire content pack for one narrative on a single screen — video, posts, stories, article — and approve or send back with one click. I don't want to check each post separately in five different interfaces."

CW
Editor / Copywriter
2 people

AI writes the first draft. The copywriter polishes it, adds the human voice. Voice guide hints in-line, forbidden phrases highlighted in red. Side-by-side: original narrative and its adaptation per (brand × format × language).

User story

"I want AI to give me a strong first draft in our voice — not generic chat-gpt text. I want to see which spots need my originality and where the template is fine."

DS
Designer
3 people

Doesn't do the routine. Creates templates in Penpot — for TG carousel, stories, landing, ads. Templates are parameterised (headline, photo, brand color). AI Production Skill fills the template with data for each artefact — sub-second. Designers focus on new formats, brand evolution, premium projects. Asset Layer auto-tagging finds the right photos in seconds.

User story

"I want to design, not crank out TG carousels every day. I want to build one strong template that adapts itself to any project and brand."

SM
SMM Manager
2 people

Doesn't juggle five different services. Opens the Content Plan calendar — sees bundles (not random posts) with suggested timing. Can adjust timing, add channel-specific tweaks. One click — publish. Schedule Optimizer suggests best-time from history. Postiz handles the cross-posting.

User story

"I want to see the full plan two weeks ahead, understand which narrative is playing on each channel, and know for certain nothing publishes without a brand-isolation check."

VP
Video Producer
3 people

Gets a black-box video brief from Editorial Brain: what to film, what narrative, what shots, what voice-over. Films, edits in Premiere/DaVinci (their domain), uploads to Immich with the editorial-source tag. INSIS handles the rest — transcript, description, derivative content. The video team doesn't write descriptions by hand.

User story

"I want to film and not spend time on the packaging — description, tags, posts, article. Let the system extract maximum value from my material."

SE
SEO Specialist
was 7 → becomes 1-2

Doesn't click through Creatium manually. Operates the system: checks dual-brand SEO health, indexation, rank position pairs. Adjusts SEO targets (keywords, schema), launches A/B tests. When something breaks — alert in Telegram pointing to the specific landing. No more babysitting 50 pages.

User story

"I want to operate the system, not Creatium. I want to see the dual-brand strategy working: both sites in top-10, no affiliation signals, content unique."

brokers favourite
SB
Sales Broker
~20 brokers

Full breakdown in the next section — an entire chapter on how brokers will work in INSIS. Short version: one inbox for all 30 numbers, AI suggestions for replies, unified listing builder, launch ads from the dashboard, mobile app for everything. No more "where's the project deck", "what's the latest price", "where did this client come from."

Jump to the "Brokers" section
SD
Sales Director
1 person

Sees every conversation, every lead, attribution from post to deal. Can fire /signal "push Damac Bay" from Telegram — Editorial Brain picks it up instantly. VIP clients auto-escalate from auto-mode to a specific broker. Sees when an operator is online — auto-mode deactivates on that number.

User story

"I want to manage the team, not babysit chats. If something's wrong — the system finds me; if a VIP writes — I know instantly; conversion is real-time visible."

TM
Traffic Manager
1 person

ROAS in one dashboard across all platforms (Meta, Google, TikTok, UAE-specific channels). Per-narrative cost: which narrative produced which leads and which deals. Per-brand budget caps, alerts on runaway spend. Brokers launch their "soft" ads from the mobile app — Traffic Manager approves.

User story

"I want to see the whole funnel in one place and instantly know which channel to scale today and which to cut."

NR
Native Reviewer
RU / AR · 2-3 people part-time

Final human QA for content in their native language. Especially critical for AR — RTL layout, cultural context, dialect. Sees only pending-on-review artefacts in their language. Approve / reject + concrete feedback → Editorial Brain learns from it.

User story

"I want to see only AR content that needs my review. I don't want to wade through RU/EN — not my area. I want a simple feedback mechanism so the system doesn't repeat the same mistakes."

OW
Owner / Founder
Dmitry · 1 person

Executive dashboard: high-level metrics across all modules for yesterday / this week / this month. Cost tracking — all spend (Hetzner, Anthropic, Voyage, Cohere, Postiz, fal.ai) on one screen, broken down by component. System Health — critical Grafana metrics without having to dig into Grafana. Audit log: who did what, when — especially AI agent actions (`actor_type='agent'`). When something breaks — Telegram alert with suggested action. No more sitting in logs.

User story

"I want to own the system, not operate it. I want to know INSIS is working, see business metrics, and spend my day on strategy — not on investigating why a post didn't go out."

§ 6 · brokers

If you're a broker —
this system is for you.

We watched how you work today. Eight tabs open: Wazzap for one client, Telegram for another, UnitPilot to check a unit, an Excel with prices, Drive with presentations, a chat with marketing asking "send me an image please", Bitrix to log the lead, Instagram for ads. And all of it — grey, slow, unable to remember where you stopped yesterday.

INSIS is one interface that does 80% of that hustle for you, leaving you with what genuinely needs you — personal contact with the client, negotiation, expertise.

01

One inbox for every client

All conversations — yours, plus from the shared pool (if rotation is enabled) — in one place. WhatsApp, Telegram, platform DMs unified. Full client history: what they viewed on the site, which posts they liked, which projects other brokers have shown them.

AI suggestions appear right in the chat. Don't like them — type your own. Like them — send with one click. If you're online, auto-mode disables itself on your conversations automatically.

AI suggestion with confidence score
Full client history (UTM, posts, past brokers)
Knowledge Base search right inside the chat
Send a listing in 2 clicks (no URL copy-pasting)
Inside Realty Inbox
MA
Inbox
23 · 7 unread
↑ priority
handled by AI
A
Aida Mansoor VIP 1
+971 50 ••• 8821 · EN · 4 visits
Context: tg-damac-launch Damac Bay × 4 +12 details
Today · 11:23
A
Looking at a 2-bed in Business Bay under 5M
11:23
AI suggestion
0.91

Hi Aida! For a 2-bed in Business Bay under 5M we have units across Damac Bay by Cavalli and Aykon CityAED 3.9M to 4.8M, 86–112 m². Want me to send a comparison with floor plans? Also: ready or off-plan?

KB chunks: 7 · units linked: 2 · 3 variants
Write a message…
Inside Realty Listings DB-2412
Available
1 / 18
Business Bay view · sea + skyline
+14
MA
RS
2 brokers working on this unit
Damac Bay by Cavalli
Business Bay · Tower 1, 32fl · unit 3204
Price
4.7M AED
per m²
42K AED
Bedrooms
2 BR
Area
112 m²
Handover
Q3 2027
Payment plan
60 / 40 no overpayment
My exclusive
until May 25
2h ago · UnitPilot · 23 views · 4 saved
02

A listing is a card with actions

Not an Excel sheet. Not a screenshot. Not a PDF. A live card that knows everything about the unit. All 30+ fields from UnitPilot flow in automatically — no manual copy-pasting.

"Send to client" generates a polished card with your name, contact, and brand styling. "Generate post" turns the listing into a ready TG/IG/LinkedIn post in your voice. "Edit listing" lets you customise the description, add your own photos, mark "I have an exclusive until X." "Boost (ads)" launches a Meta/Google ad on this unit straight from the app.

30+ fields auto-synced from UnitPilot
Quick actions: send / generate / edit / boost
See which colleagues already worked on this unit
Exclusives marked — others don't duplicate your post
03

Content in one click

"Post this unit to my Instagram" — tap. 8 seconds later: a finished post with photo, description, price, your contact, and brand-styled layout.

AI writes in the right language (RU/EN/AR), in your personal tone (brokers can configure their own voice). Forbidden phrases filter automatically. Cross-brand mentions blocked. PII checks. Reviewer signs off — published. Don't like the result — tap "another variant" or edit it yourself.

3 languages (RU/EN/AR) from day 1
Your personal voice (optional)
Photos picked by Asset Layer
Brand-styled layout automatically
MA
mahmoud.realty
Inside Realty · Dubai
1/8
347 likes

mahmoud.realty 🌊 Sea-view 2-bed in the Cavalli tower. 112 m², handover Q3 2027. 60/40 payment plan, no overpayment. DM for floor plans.

#dubai #realestate #damacbay #insiderealty

MA
Mahmoud Alami in
Senior Broker · Inside Realty
2h · 🌍
Видовая 2-bed в башне Cavalli — 112 м², 32 этаж, handover Q3 2027. Платёж 60/40. Открыт к viewings с серьёзными инвесторами.
👍 Sarah K. and 187 others
12 comments
MA
mahmoud.realty
Inside Realty · دبي
1/8
٢٤٣ إعجاب

mahmoud.realty 🌊 شقة بغرفتين بإطلالة بحرية في برج كافالي. ١١٢ م²، التسليم Q3 2027. خطة دفع 60/40 بدون فوائد.

#دبي #عقارات #داماك_باي

Listings DB-2412 Edit
Unsaved changes
Auto-save: 2s ago
Personal note (only you see this)
128 / 500
Owner has exclusive until May 25. Flexible to offers from 4.5M. Can show evenings or weekends.
Your photos (override defaults)
3 / 12 added
1
Featured for your audience
Master fields
from UnitPilot · read-only
Price4.7M AED
Area112 m²
HandoverQ3 2027
Payment plan60 / 40
Floor32
Need to change master data? UnitPilot → or ping the coordinator on Telegram.
Visibility
After save: 5 posts across channels will regenerate automatically
04

Edit what's yours

Master data (price, area, handover) comes from UnitPilot — that's the source of truth for the whole group. The coordinator updates it, not every broker individually (no desync).

But your stuff is yours: personal note, exclusive until X, additional photos, your position on negotiation, per-channel visibility. Saved — the system regenerates the posts with the new data, refreshes the card on the website, informs auto-mode about the new information.

Master vs Personal — clean separation
Exclusives visible to the whole team but not duplicated in posts
Per-channel visibility settings
05

Launch ads from here

Tap "Boost" on a listing — short form opens: budget (from $50), duration (from 3 days), target audience (presets: "UAE residents 30–50", "GCC investors", "Local expats").

AI generates the creative (video + text + copy), wires the UTM, ships it to Meta / Google. Traffic Manager approves (or auto-approves under the limit). After 24 hours of run-time — stats are already in your dashboard: impressions, clicks, conversations, leads.

You don't need to: open Meta Business Manager, hunt for campaigns, copy UTMs out of chat, fill targeting filters from scratch. You don't need to know how Meta works — you need to know your client.

Meta / Google / TikTok from one screen
Pre-set audience templates
Budget caps (mom-Sales-Director won't let you blow it)
UTM auto-tied to the listing — attribution works
Listings DB-2412 Boost campaign
draft
Budget
$350 / 7d
$50$500$1K$2K
≈ 1,280 AED · $50 / day average
Audience preset
Platforms
Projected reach · 7 days
based on history
Impr.
42K
Clicks
580
Convos
28
Leads
6–9
CPL projection: $38–58 vs avg $187
Creative AI-generated · v3
Damac Bay · 2-bed
4.7M AED · 60/40 plan
0:15
$350 · within your $500/mo limit
auto-approve · UTM tied to listing
My day Monday, May 12
MA
3 viewings 2 calls 1 meeting 1 signing +12% vs last Mon
09:00 60 min
Viewing · Damac Bay VIP
A
Aida M. · Business Bay, 32fl
11:00 30 min
Call · presentation
K
Khalid R. · Aykon City flat compare
12:30 AI
AI insight
Aida silent 2 days after viewing. Similar clients converted after soft follow-up — send a draft?
14:00 15 min
Team standup
M
K
L
+5 others
16:00 90 min
Offer signing DEAL
E
Elena K. · Aykon City · 3.2M AED
18:00
— free —
06

A calendar that knows context

Not just Google Calendar. It knows your conversations — reminds you when a client went silent, drafts a follow-up. Knows your deals — schedules the signing automatically. Knows your boost campaigns — alerts when something flatlines.

Morning brief in the Telegram bot: 3 top priorities, specific actions. End of day — a short wrap-up of what happened.

Smart reminders from conversation history
Morning brief + evening wrap-up
Sync with Google Calendar / Apple Calendar
The promise

No more "grey" interfaces.
No more ten tabs.

Every click is either contact with a client or real expertise. Everything else — routine, copy-pasting, searching, context-switching — that's the system's job. You do what you love and what you're paid for. Not what a computer should be doing.

§ 7 · the app

All of this —
in your pocket.

Brokers don't sit at a desk. They're on viewings, in cars, at meetings, at restaurants with clients. INSIS Mobile isn't "the smaller web version." It's a mobile-first app for iOS and Android, designed from spec.

Inbox in your pocket

Push notification on a new client message. Swipe → quick reply via AI suggestion. Voice messages get transcribed.

Camera → listing

Just shot photos at a viewing — the app recognises the unit (QR code or geo), attaches photos to the listing, optionally publishes to your Instagram with your signature.

Calendar and route

See today's viewings, the route on the map, Dubai traffic forecast. One tap on a viewing → client detail + full conversation history.

Boost ads on the go

Fresh video from a viewing → upload → one form (budget, audience) → launch the Meta campaign from the app. AI generates the creative, you give the final approval.

Personal analytics

How many conversations, viewings, deals this month. Which channel brings you the most clients. Where you stand on the team leaderboard (if that's your thing).

Knowledge Base offline

Before a client meeting — company search. "Which laws apply to a Golden Visa via real estate?" Accurate, up-to-date answer. Works offline (cached).

iOS · native Android · native Push notifications Biometric login EN · RU · AR
9:41
MA
Inside Realty
Inbox
Auto-mode on · 7 unread
A !
Aida M. 12s
Looking at 2-bed in Business…
VIP Damac Bay · tg-launch
K
Khalid R.
Thanks for the deck!
15 min · viewing scheduled
E
Elena K. 42m
Anything cheaper, a studio?
Y
Yusuf I. AUTO
AI · "sending floor plans"
9:41
Available
Damac Bay by Cavalli
Business Bay · 2-bed · 32fl
4.7M AED
42K/m²
Area
112m²
Plan
60/40
HO
Q3 27
9:41
Monday
May 12
today
3 viewings
09:00 VIP
Viewing · Damac Bay
A
Aida M.
11:00
Call · presentation
Khalid R.
AI insight · 12:30
Aida silent 2 days — send a follow-up?
14:00
Team standup
16:00
Offer signing
Aykon City · Elena K.
Phase 1 · MVP+
React Native, core features

Inbox + Listings + Calendar + Profile. Push notifications. Biometric login. EN/RU/AR. Offline KB cache.

Phase 2 · Mobile-first features
Camera, geolocation, voice

Camera→listing with unit recognition. Geolocation for viewing routes. Voice transcription for quick notes. Live offer dashboard.

Phase 3 · Power features
Ads, AR, personalisation

Boost campaigns from the app. AR unit preview (when there's a 3D model). Personal voice tuning for AI suggestions. Coaching tips.

§ 8 · AI safety

AI works
not in spite of people,
but with guardrails.

WhatsApp auto-mode is money. If AI says something stupid to a client — we lost a lead, or worse — got a legal problem. So the AI Sales Agent is built with multi-layered defence.

This isn't "looks fashionable" — it's a load-bearing requirement for a production system talking to real clients with real money at stake.

Global kill switch
features.ai_auto_mode_enabled

One flag disables all auto-mode instantly. UI toggle in Settings (with confirmation), CLI emergency command. Every toggle goes into `audit.events`.

8 escalation triggers · if any fires, the conversation goes to a human
01
Price commitments

Any concrete price or discount promise → escalate. Only verified data from UnitPilot.

02
Legal questions

Visa, tax, residency, ownership rules → escalate to a licensed advisor.

03
VIP customer

`vip_level >= 1` — always a live broker, never auto-mode.

04
Assigned broker

If the client already has an assigned broker — auto-mode doesn't interfere with an active dialog.

05
Operator online

A broker is active in the system — auto-mode on their numbers deactivates so we don't duplicate replies.

06
Sensitive topic

Classifier detects sensitive topics (politics, third-party personal data) → escalate.

07
Customer frustration

Sentiment + keyword classifier catches irritation, dissatisfaction → live broker immediately.

08
Confidence < 0.85

The model itself isn't sure → escalate. 0.85 is a high industry bar.

Output sanitization · last filter before the client
Forbidden phrases
Per brand × per locale. "Guaranteed return" / "risk-free" — blocked.
Cross-brand
Inside Realty doesn't mention In.ae and vice versa. ADR-005 hard rule.
PII leakage
Internal IDs, leadId, paths — never leak into outbound messages.
§ 9 · dual-brand SEO

Two sites.
One project.
No connection.

insiderealty.ae (our agency) and in.ae (an independent media portal) — they're not the same site under different names. Google shouldn't see any affiliation, or one of them drops out of the results.

That's why we build 8 layers of architectural independence. Not cosmetic — a load-bearing SEO requirement, encoded in ADR-005 and verified automatically on every deploy.

Inside Realty
Next.js 15
on Vercel
In.ae
Astro 5
on Cloudflare Pages
1. Different technology stacks
Next.js (RSC) vs Astro (static) · different DOM, different JS bundles, different fingerprints
enforced
2. Different hosting providers
Vercel vs Cloudflare · different ASN, different IPs, different CDN signatures
enforced
3. Different analytics ownership
Plausible × 4 — separate admin accounts, separate orgs · no shared GA4
enforced
4. Different content per project
One project, two completely different prose versions · uniqueness score >85%
enforced
5. Different internal linking
Never cross-link between sites · no references to each other
enforced
6. Different schema.org markup
Inside Realty: RealEstateAgent · In.ae: WebSite + Article + FAQPage
enforced
7. Different whois ownership
Different UAE entities · whois privacy enabled · different registrars
enforced
8. Different authoring patterns
Inside Realty: specific brokers with photos · In.ae: editorial team
enforced
SEO Health dashboard monitors this daily: cross-domain backlinks (target: 0), shared accounts (target: 0), schema drift, duplicate content score. Any violation — p1 Telegram alert.
§ 10 · how we're building this

A system that does work for the team,
is built by an autonomous pipeline.

INSIS is a big system. 9 modules, 5 brands, 3 languages, multi-tenant, AI safety, dual-brand SEO. Building this the traditional way means 10+ engineers for 12 months. We took a different approach: solo development with AI agents writing production-grade code from detailed specs.

Every day: task → pipeline runs overnight → PR up for review in the morning. 70–85% of tasks close automatically. 15–30% land in `blocked` with a specific reason (need a decision, missing API key, ambiguity in spec).

Not "trendy", not "vibe coding". Every line of code ships to production — no MVPs, no "rewrite later", no `any` in TypeScript. If a task is impossible without violating principles — it's flagged `blocked`, we discuss it, we don't ship a watered-down version.

This documentation (35+ files, ADRs, iterations, agent specs) is the executable contract. AI agents read it before every task. Any architecture change goes through a new ADR. No "I'll tell you how to do it later."

Planner

Breaks iter-NN into atomic tasks, writes acceptance criteria.

Designer

Writes UI spec for UI tasks: states, breakpoints, copy, accessibility.

Coder

Production-grade code end-to-end. Types, tests, audit, observability, RLS.

Tester

Runs UI flow in headless browser, AI eval suites, catches regressions.

Reviewer

Auto-reject triggers: missing tenant filter, cross-brand mentions, `any` types, raw SQL, missing tests, hardcoded model versions, missing escalation triggers. Nothing sloppy reaches production.

§ 11 · roadmap

10 iterations.
Each one production-grade.

We don't do MVP-first then V2-later. Every iteration is a finished, production-grade module (per ADR-002 "No MVP"). Phase numbers and execution order don't match — see the actual order below.

00
Phase −1.5
Infrastructure

Server provisioning · Authentik OIDC · Postgres 16 + pgvector · Redis · ClickHouse · AFFiNE · Penpot · Postiz · n8n · Immich migration to VectorChord · Observability stack · Plausible × 4 · PM2 · audit schema · Asset Layer foundation.

DockerCaddyBackups
01
Phase 0
Shell

Next.js 15 application layer · Authentik OIDC integration · Multi-tenant foundation · RBAC · Audit log · Health checks · Dark/light theme · Base nav and roles.

Multi-tenantSSORLS
02
Phase 1
Excalidraw integration

Whiteboard for the team — embedded in Shell. Used by planners and designers for architecture sketches and quick ideation.

ExcalidrawCollaboration
04a
Phase 1.9
Knowledge Base · Foundation

AFFiNE workspaces · pgvector schema · Voyage AI embeddings · Cohere reranking · Hybrid search · Retrieval API. Required before iter-03 because Editorial Brain consumes retrieval.

AFFiNERAGVoyage AI
03
Phase 2 + 3
Editorial Brain · Core

Topics + Topic Ranker · Format Strategist · Brief Generator · Production Skills · Approval Gates · Voice Guides per (brand × locale) · Eval suites · Source Registry + Narrative Bundles (ADR-006) · Video-published source.

TopicsNarrative BundlesVideo source
06
Phase 4
Posting

Postiz integration · Native Telegram publisher · Schedule Optimizer · Bundle distribution (coordinated content drops) · Best-time intelligence · Per-channel adapters.

PostizNative publishers
most critical
05
Phase 4.5
Communications + AI Sales Agent

Baileys + WABA · Conversation Engine · AI Sales Agent with auto-mode and suggestions · Inbox UI · Bitrix24 sync · Wazzap migration · 8 escalation triggers · Kill switch · Output sanitization. The most mission-critical iteration.

WhatsApp × 30Auto-modeSafety gates
04b
Phase 4.6
Knowledge Base · Expansion

Multi-language cross-lingual retrieval (RU/EN/AR) · Eval suite expansion · Observability dashboards · Auto-sync with UnitPilot DB via CDC · Knowledge UI in Shell. Runs in parallel with iter-03.

EN/RU/ARCDC sync
07
Phase 5 + 8
Analytics

ClickHouse warehouse · native collectors (IG, LinkedIn, TG, YouTube, Plausible × 4) · Bitrix webhooks · End-to-end attribution · Metabase dashboards · Per-bundle metrics rollups · LLM cost tracking · Editorial feedback loop · Ads management (ad_accounts, ad_campaigns, ad_metrics).

ClickHouseAttributionROAS
08
Phase 7
Web Builder · Dual-brand

Inside Realty site (Next.js on Vercel) + In.ae site (Astro on Cloudflare Pages) · Landing generator with UnitPilot integration · Schema markup · Sitemap · Internal linking · A/B testing · ADR-005 independence enforcement. 1,500+ landing pages, automated.

Dual stackSEOA/B tests
09
Phase 9
Market UI

UI for browsing market references (UnitPilot read-only): Districts, Projects, Developers, Units. Filters · search · cards · maps. UnitPilot is the source of truth; INSIS is the convenient viewer for brokers.

UnitPilotRead-only
📱
separate track
Mobile App · iOS + Android

React Native app with push notifications, biometric login, offline Knowledge Base cache, camera → listing, geolocation for viewings, boost campaigns. Phase 1 → MVP+ 8–10 weeks after iter-05.

iOSAndroidReact Native

Total time to full delivery across all 10 iterations + Mobile: 7–8 months with solo development and the autonomous AI pipeline. Full specs for each iteration (with acceptance criteria, schema, code samples, Definition of Done) live in docs/iterations/history/iter-NN-*.md in the repo.

§ 12 · vision

Where we're going.
End of 2026 and beyond.

This isn't a unicorn pitch. It's about concrete operational changes for the group, and a potential SaaS exit if it becomes clear other UAE agencies would want this tool.

End of 2026

Fully deployed INSIS

  • Serves all 5 group brands (4 client-facing + Inside Media internal)
  • 30 WhatsApp numbers with auto-mode AI agent in 3 languages
  • 1,500+ landing pages on two independent websites
  • 25+ publications per day across 30+ channels
  • SEO team shrunk from 7 to 1–2 operators
  • Cost per Lead down 60%
  • Mobile app iOS + Android in production
  • Ready to spin out as a SaaS product
End of 2027

INSIS as a SaaS product

  • SaaS product for other UAE/MENA real estate companies
  • White-label under client brand
  • Marketplace of design templates and agent skills
  • Potential exit or Series A
Principle 1
No MVP

Every phase production-grade from day 1. No "we'll rewrite later."

Principle 2
Augmentation, not replacement

Makes people 3–5× more effective. Doesn't replace fully. Human checkpoints everywhere.

Principle 3
Brand authenticity

Every brand has its own voice. The system doesn't dilute that for the sake of uniformity.

Principle 4
Data sovereignty

Self-hosted where possible. Client and business data with us — not vendors.

§ 13 · talk to us

Questions?
Ideas? I'm listening.

This site is a concept preview for our team. If you read this far and have questions, objections, ideas, or "in my role it doesn't work like that" — come talk. Every comment is valuable — we're still at the stage where everything is cheap to redesign.

Especially keen to hear from:

  • Brokers — what should be in the app that isn't on the screens
  • Editorial team — what default formats are missing from the bundle mix
  • SEO — what dual-brand metrics need monitoring
  • Everyone — anything critical we didn't mention at all
Telegram
@Balakirev
Direct DM
Email
reg.balakirev@gmail.com
Long thoughts with decks and screenshots
Documentation

Full architectural docs (35+ files: vision, system-design, ADRs, iterations, brand guides) live in a private GitHub repo. Ping me on Telegram for access.

CLAUDE.md6 ADRs10 iterations5 agent prompts