AI systems that survive
contact with production.

Agentic AI, RAG and automation — built to be checked, not trusted.

See how we built it Start a conversation
Scroll

Most AI pilots die between the demo and deployment.

The agent works beautifully in a notebook, then hits real data and starts hallucinating. The RAG pipeline degrades. Nobody can explain what the model decided. Security has no audit trail.

The project quietly gets switched off.

We build for the other side of that gap.

Featured work — Scopeline, AI-assisted estimating & document review

An AI tool found low-six-figures of unpriced scope four days before a tender closed — on a package the team had already read by hand.

The client

A mid-size mechanical and plumbing contractor bidding institutional, commercial and industrial work in Southern Ontario. Their five-person estimating team was losing roughly a third of every bid cycle to document handling rather than pricing. Named client withheld under NDA.

The problem

A typical tender package arrives as 900–1,600 pages of mixed PDF, plus a drawing set of 180–380 large-format sheets. Equipment schedules live as vector tables inside those sheets — not as text, not as a spreadsheet, and frequently rotated 90°. Specification-to-drawing verification was done by memory and highlighter, under deadline, by whoever was free.

What we built

Scopeline ingests an entire tender package and produces three reviewable artifacts in about forty minutes: a contract risk register, a structured equipment and valve schedule extract, and a scope discrepancy report comparing what the specifications require against what the drawings actually show.

Every extracted number, clause and schedule row carries a provenance link back to a page, a bounding box and a source span. An estimator can click any figure and land on the exact region of the exact sheet it came from. That single design decision is what moved the tool from an interesting demo into something the team bid live work with.

The engineering note

Never ask a vision model to read a whole drawing. An E-size sheet downsampled enough to fit a single call renders schedule text at two or three pixels of stroke height. The model will still return numbers — they just won't be the right ones.

Region-first reading of a large-format drawing sheet Left: a whole E-size sheet downsampled into one model call, where schedule text collapses to two or three pixels. Right: deterministic analysis proposes candidate regions, and only those regions are read at native resolution. one call · whole sheet schedule text ≈ 2–3px stroke · numbers returned, not read regions proposed read at native resolution accuracy on schedule rows ≈ 2×
Cheap deterministic analysis decides where to look; the model only reads what it can actually see.

Instead: cheap deterministic analysis proposes regions — vector ruling lattices, text-density clustering, whitespace gutters — and the model reads those regions at native resolution. Accuracy on schedule rows roughly doubled after that change.

Then three checks before anything is accepted:

  • Row count must match detected horizontal rulings.
  • Values must fall in trade-standard ranges.
  • The same tag on two sheets must resolve to the same record.

An illegible cell is reported as illegible. It is never inferred from the rows above it.

40m

Package receipt to reviewed contract risk register — down from 6.5 hours

0.94

F1 on structured schedule extraction, 1,100-row gold set

97%

Recall on the 42-item high-risk clause taxonomy

0.6%

Silent error rate at handover — down from 12.4%

Measured on the client's own tender packages, from first integration through handover.

Also shipped — cross-platform mobile product

A privacy-first dating app, shipped on both stores

Meeting people without handing over your identity

A location-based social product for Android and iOS where people meet without exposing their name, number or exact location. Built from one Flutter codebase, with a FastAPI backend, a separate real-time chat service, and a web dashboard for moderation and analytics.

Location is handled as map zones rather than GPS coordinates — exact position is never stored, and zones below a minimum population are hidden entirely. Photo uploads have their embedded location data stripped on the device before anything is transmitted.

Built with Flutter · Python · FastAPI · PostgreSQL + PostGIS · Celery · Firebase · Cloudflare R2
  • 84 features delivered
  • 1,240 automated tests passing
  • 99.8% crash-free sessions
  • 1.9s cold start on a mid-range handset
  • 20 physical devices tested

Anatomy

Every system we build has the same spine.

The interesting part is not the model call. It is the validation step before an action fires, and the log that lets you reconstruct why it fired.

Automations

  1. Trigger event
  2. Data ingestion
  3. AI processing
  4. Decision and validation
  5. Action and integration
  6. Logging and monitoring
  7. Notification

Triggers

EmailWebhook or APIForm submissionFile upload

AI processing

ClassificationEmbeddings and searchExtractionSummarisation

Actions

Send replyGenerate reportCreate taskUpdate CRM

Monitoring

LogsAnalyticsAlerts

A trigger enters at the top, the model does one narrow job, an action fires only once it passes validation, and every step writes to the log. Swap the trigger and the action and the middle stays the same, which is why a second automation costs a fraction of the first.

Mobile apps

The same shape with one difference that changes the architecture: the handset has to keep working with no signal. Anything that can run on the device does, and the sync queue drains when the connection comes back.

  1. Interface
  2. State
  3. Online check
  4. Local store or sync queue
  5. Cloud and model
  6. Update the UI
  7. Analytics
  8. Push notification

What the person does

Camera captureVoice inputManual entryLocation

On the device

SQLite storageOCR via ML KitTFLite and MediaPipeSpeech and TTS

In the cloud

Firebase or SupabaseModel callsVector searchWeather and Maps

What comes back

Cloud syncInsightsChartsNotifications

Pose detection, OCR and classification all run on the handset, so the camera features work on a plane. The cloud is for what genuinely needs it — sync, longer model calls and retrieval — and anything sensitive is stripped or encrypted before it leaves the device.

Web platforms

A request comes in, authentication decides what it is allowed to touch, and the model is one service among several rather than the centre of the system. Most requests never reach it.

  1. Interface
  2. API layer
  3. Auth check
  4. Business logic
  5. Model or database
  6. Cache
  7. Response
  8. Update the UI
  9. Logging

Frontend

Next.js and ReactState managementTailwind CSSReal-time WebSockets

Backend

Node.js or FastAPIREST and GraphQLJWT and OAuthBackground jobs

AI layer

LangChain orchestrationModel callsVector searchSpeech and vision

Data layer

PostgreSQLMongoDBRedis cacheObject storage

Integrations and outputs

Slack, Notion, JiraZendesk and HubSpotStripeDashboards and exports

Background jobs carry anything slow, so a model call never blocks a page render. The cache sits in front of the expensive paths, and every request writes to the log whether it touched the model or not.

Delivered work

Twenty-two systems, built and shipped.

Client work across three tracks. Open any card for the problem it solved, how the flow runs and what it was built on.

AI automation

AI Email Triage & Auto-Responder

Reads incoming mail, classifies intent and urgency, drafts a grounded reply and routes it to the right team.

PythonFastAPIGmail APILangChain
Email inClassifyDraft replyRoute and log

Read the detail

AI automation

Resume Screening & Candidate Ranking

Parses resumes, scores them against the job description and syncs a ranked shortlist to the ATS.

PythonStreamlitembeddingsLangChain
Resume inParseScore vs JDRanked shortlist

Read the detail

AI automation

Meeting Notes & Task Extractor

Transcribes a recording, pulls out action items with owners and dates, and files them in your tracker.

WhisperLangChainNotion APITrello and Jira APIs
RecordingTranscribeExtract tasksFile and recap

Read the detail

AI automation

Support RAG Chatbot & Ticket Deflector

Answers repeat questions from your own docs, cites the source, and escalates when confidence drops.

PythonFastAPILangChainvector retrieval
QuestionRetrieveCited answerEscalate or log

Read the detail

AI automation

Invoice & Receipt Processing

Watches an inbox or folder, extracts invoice fields, validates them and posts to the accounting system.

Pythonvision OCRTesseractGoogle Drive API
Invoice inExtractValidatePost to ledger

Read the detail

AI automation

Lead Enrichment & Personalised Outreach

Enriches inbound leads, scores fit, drafts outreach that references something real, and syncs to CRM.

PlaywrightPythonHubSpot and Salesforce APIsInstantly
Lead listEnrichScore and draftCRM and follow-up

Read the detail

Mobile app

AI Habit Tracker & Coach

Habit streaks with reminder timing tuned to actual behaviour, and a coach that reads your week back to you.

FlutterFirebaseSupabaselocal notifications
Open appLog habitSync and streakTimed nudge

Read the detail

Mobile app

AI Receipt & Expense Scanner

Point the camera at a receipt; it extracts merchant, date and total, categorises it and tracks the budget.

FlutterGoogle ML Kitvision modelFirebase
CaptureOCRParse and categoriseBudget view

Read the detail

Mobile app

AI Fitness Form Coach

On-device pose estimation counts reps, detects the exercise and flags form problems while you move.

FlutterMediaPipeTensorFlow LiteCameraX
Start setPose detectForm checkLog and sync

Read the detail

Mobile app

Language Learning with OCR & Speech

Point at an object or a sign, get the word, the pronunciation and a sentence you would actually say.

FlutterML Kit OCRWhispertext to speech
Point cameraTranslateFlashcardTutor practice

Read the detail

Mobile app

Plant Disease Detector

Classifies plant disease from a leaf photo on-device, with treatment guidance and weather-based risk alerts.

FlutterTensorFlow LitePlantVillage datasetFirebase
Leaf photoOn-device modelTreatmentRisk alert

Read the detail

Mobile app

Voice Journal & Mood Tracker

Speak an entry, get it transcribed and analysed, and see how mood moves across weeks.

React NativeWhisperSupabasefl_chart
RecordTranscribeMood analysisWeekly insight

Read the detail

Mobile app

Smart Attendance with Face Recognition

Face check-in with geofencing and a QR fallback, so attendance takes seconds and is hard to fake.

FlutterFaceNetTensorFlow LiteFirebase Auth
Check inFace matchGeofenceSync and report

Read the detail

Mobile app

AI Travel Planner & Itinerary

Destination, dates, budget and interests in; a day-by-day itinerary with maps and reminders out.

React NativeGoogle Maps and Places APIsFirebaseweather API
Trip inputsItineraryMap and budgetReminders

Read the detail

Web platform

Content Generation & SEO Dashboard

Topic in, outline and draft out, with keyword research and SEO scoring before it publishes to the CMS.

Next.jsNode.jsLangChainPostgreSQL
TopicDraftSEO scorePublish

Read the detail

Web platform

Support Desk with RAG

A helpdesk where the bot answers from your docs with citations, and hands off cleanly when it should not.

ReactFastAPILangChainvector retrieval
QuestionRetrieveCited answerAgent handoff

Read the detail

Web platform

Social Scheduler with AI Drafting

Generates post ideas and captions, schedules across platforms, and reports what actually landed.

ReactNode.jsTwitter, LinkedIn and Instagram APIsMongoDB
TopicVariantsScheduleAnalytics

Read the detail

Web platform

Resume Builder & Application Tracker

Tailors a resume to a specific job description and tracks every application on a Kanban board.

Next.jsSupabaseTailwind CSSReact DnD
ProfileTailor to JDExportTrack

Read the detail

Web platform

Data Analysis & Visualisation Platform

Upload a spreadsheet, ask a question in English, get the chart and the caveats.

ReactFastAPIPandasDuckDB
UploadAsk in EnglishChartShare

Read the detail

Web platform

E-commerce Recommendation Engine

Behavioural recommendations and semantic search, with an admin view of what each change did.

Next.jsNode.jsPython ML serviceembeddings
BrowseEventsRankMeasure

Read the detail

Web platform

Meeting Scheduler & Assistant

Finds the time across calendars and time zones, then summarises the meeting and files the actions.

ReactNode.jsGoogle Calendar APIWhisper
RequestFind timeMeetSummarise

Read the detail

Web platform

Collaborative Document Editor with AI

Real-time multi-cursor editing with conflict-free sync, plus drafting, translation and tone tools inline.

ReactYjs (CRDT)Node.jsWebSockets
Open docLive syncAI editExport

Read the detail

What we build

Three things, done properly.

Applied AI

Agentic systems and multi-agent orchestration. RAG applications and enterprise knowledge assistants. Voice and calling agents. Chatbots and conversational automation.

LangChain · LangGraph · vector retrieval · model fine-tuning · OpenCV

Product engineering

The full product around the model — APIs, dashboards, mobile apps, and the unglamorous plumbing that makes a model usable by people who don't care that it's a model.

Python · FastAPI · Django · Flask · React · Next.js · Flutter · PostgreSQL

Deployment & AI security

Getting it live and keeping it defensible. Cloud infrastructure, CI/CD, monitoring, and controls at the model, data and agent layer — permissions, audit trails, and guardrails against prompt injection.

AWS · Azure · Kubernetes · Docker · SSO · single-tenant deployments

Stack

AI & machine learning
LangChain · LangGraph · vector retrieval · pgvector · Pinecone · Chroma · Hugging Face · Whisper · MediaPipe · TensorFlow Lite · ML Kit · OpenCV
Backend & data
Python · FastAPI · Django · Flask · Node.js · PostgreSQL · PostGIS · MongoDB · Redis · DuckDB · Celery · Supabase
Frontend & mobile
React · Next.js · TypeScript · Flutter · React Native · Swift · Kotlin · SQLite · Firebase
Automation & integrations
n8n · Make · Zapier · BullMQ · Kafka · Gmail · Slack · Notion · Jira · Zendesk · HubSpot · QuickBooks · Google Calendar · Stripe
Infrastructure & security
AWS · Azure · Kubernetes · Docker · Vercel · CI/CD · SSO · single-tenant VPC deployments · audit logging

How we work

Three stages, in this order.

  1. Discovery

    We read your documents, your data and your constraints before proposing anything. Where accuracy matters, we build the evaluation set first.

  2. Working prototype

    A narrow end-to-end slice, running on your real data, early enough that integration problems surface while there's still time to fix them.

  3. Hardened deployment

    Evaluation gates, monitoring, cost controls, runbooks and documentation. You own the code and can operate it without us.

Got an AI pilot stuck in pilot?

That's the conversation we want to have. Tell us what you're trying to build and what's blocking it.

Email us LinkedIn
contact@aprellasolutions.in Noida, Uttar Pradesh, India