ai projects · 2026

[00] applications in artificial intelligence · coimbatore, india

Systems we have built.

Three AI products built by AppsInAi, with the screens, the AI features and the stack behind each one. The company presentation has the services, the case studies and how we work.

scores, deal health and summaries are computed from your data; the model only explains them, so outputs stay grounded and auditable, and every feature still works when no model is configured.

projects.log

01PulseAi CRM
Self-hosted sales and marketing CRM with an AI layer
02Invoice Agent
AI-powered invoice processing agent
03HTTTP.IN
URL-shortening SaaS with an AI layer, live at htttp.in

[01] pulseai crm · self-hosted sales and marketing crm with an ai layer

A self-hosted sales and marketing CRM with a Python AI layer for drafting emails, scoring and enriching leads, and summarising deals.

Pulse CRM covers the full revenue lifecycle: leads with firmographic and behavioural scoring, segments and lifecycle stages; contacts, companies and deals on a stale-deal-aware Kanban pipeline; templated email with open and click tracking and send-later scheduling; a visual workflow and automation builder with campaigns; proposals with PDF generation and e-signature hooks; and goals, reports, a command palette, calendar export, audit logs and a duplicate finder.

On top sits an AI layer orchestrated in Python and built for graceful degradation: every AI capability runs through one orchestration layer that calls an LLM when a provider is configured and otherwise falls back to deterministic heuristics, so features work with no API key. Deal health, scores and summaries are computed from the CRM data; the LLM only narrates them, which keeps outputs grounded and auditable.

Python REST APIReact + TypeScript front endToken auth, role-based accessAsync task queueWorks with no API key

PulseAi CRM

[01] pulseai crm · ai features, architecture and stack

Twelve AI features. And the system behind them.

ai features · current and candidate features

01
AI email drafting from intent and tone
02
AI reply drafting from a logged thread
03
Template generation from a plain-language purpose
04
Draft refinement: shorten, expand, formalise, proofread
05
Predictive lead scoring with a heuristic fallback
06
Lead enrichment: company tech stack and firmographics
07
Conversational lead qualification and auto-routing
08
"Catch me up" summaries of a contact, company or deal
09
Deal health and win-probability insights
10
Inbound email triage and needs-reply classification
11
Natural-language segment and audience builder
12
Meeting-note summaries and next-step suggestions

architecture

01 · data and triggers

CRM data: contacts, companies, dealsEmails, notes and activityWorkflow triggers
↓

02 · orchestration

LangChain + LangGraph: a stateful agent graphPydantic: typed, validated outputsCelery + Redis: enrichment, scoring and triage jobs
↓

03 · model layer

LLM provider: Claude, OpenAI, Gemini or OllamaDeterministic fallback: works with no API keypgvector embeddings: semantic search and RAG
↓

04 · features

Email AILead and deal AIKnowledge AI

built with · LangChain · LangGraph · FastAPI · LangSmith · Pydantic · Anthropic Claude · OpenAI · Google Gemini · Ollama · Sentence-Transformers · pgvector · Celery · Redis · scikit-learn · PostgreSQL · React

[01] pulseai crm · screens

Four more screens. PulseAi CRM in use.

Workflow rules: plain language becomes trigger, condition and action rules
Workflow rules: plain language becomes trigger, condition and action rules
"Catch me up" on a contact, with the predicted fit and its heuristic fallback
"Catch me up" on a contact, with the predicted fit and its heuristic fallback
An email template drafted from a plain-language purpose, with merge tags and a preview
An email template drafted from a plain-language purpose, with merge tags and a preview
Inbox triage: needs-reply classification and thread summaries
Inbox triage: needs-reply classification and thread summaries

[02] invoice agent · ai-powered invoice processing agent

Invoice automation that turns incoming emails into validated business transactions through OCR, AI extraction and workflow integration.

The agent monitors a Gmail or Outlook inbox, identifies invoice attachments, extracts the invoice data with OCR and an LLM, validates each invoice against configurable rules, and uploads approved invoices to the ERP or accounting system through its API. Exceptions go to a review queue, and every step is logged.

It is built as a Python service with FastAPI and PostgreSQL, a React dashboard for monitoring and rules, AWS Textract or Tesseract for OCR and OpenAI GPT models for extraction, and deploys with Docker.

Gmail, Outlook and IMAP inboxesOCR + LLM extractionConfigurable validation rulesERP and accounting uploadAudit logs

Invoice Agent

[02] invoice agent · ai features, architecture and stack

Eight AI features. And the system behind them.

ai features

01
Email inbox monitoring: Gmail, Outlook, IMAP
02
Invoice detection and extraction from attachments
03
OCR and AI-powered data processing
04
Configurable validation rules
05
Automated approval workflow
06
Third-party API integration with ERP and accounting systems
07
Error handling and notifications
08
Audit logs and tracking

reported outcomes · not one of our published case studies

Manual invoice processing reduced by up to 90% · Improved accuracy and compliance · Faster invoice approval and processing cycles · Seamless integration with ERP and accounting systems · Real-time monitoring and reporting · Scales with growing invoice volumes

architecture

01 · inbox

Gmail APIOutlook APIIMAP
↓

02 · detect and extract

Invoice attachment detectionOCR: AWS Textract or TesseractField extraction with an LLM
↓

03 · validate and approve

Configurable validation rulesApproval workflowExceptions queue, errors and notifications
↓

04 · deliver and audit

Upload to ERP or accounting via APIAudit logs and trackingMonitoring dashboard

built with · Python · FastAPI · OpenAI GPT · AWS Textract · Tesseract OCR · PostgreSQL · React · IMAP · Gmail API · Outlook API · Docker

[03] htttp.in · url-shortening saas with an ai layer, live at htttp.in

Shorten URLs, generate QR codes, create bio pages and track every click with real-time analytics, with an AI layer on top.

HTTTP.IN is a full-featured, self-hosted URL-shortening SaaS: custom aliases, expiry by date or click count, bulk CSV import and Safe Browsing scans, styled QR codes, link-in-bio pages, one-time secret sharing with AES-256 encryption, and click analytics by country, city, device, browser and referrer, plus geo and device targeting, A/B testing, link rotation and retargeting pixels.

The backend is FastAPI over PostgreSQL with pgvector, with Celery and Redis for background jobs; the front end is React with TypeScript; billing runs on Stripe and sign-in on JWT and OAuth2 with two-factor codes. It is multi-tenant with teams, roles and custom domains, and deploys with Docker Compose.

Live at htttp.inMulti-tenant: teams, roles, custom domainsStripe billingDocker Compose deployment

htttp.in

HTTTP.IN

[03] htttp.in · ai features, architecture and stack

Seven AI features. And the system behind them.

ai features

01
AI phishing and malware detection on every new link
02
Smart alias suggestions from the destination page
03
Natural-language analytics chat: "why did clicks spike?"
04
Predictive click forecasting and traffic anomaly detection
05
Bio pages and QR designs generated from a prompt
06
A weekly performance digest written in plain language
07
Natural-language link creation: "shorten X, expire Friday"

architecture

01 · backend, data and events

FastAPI backend: ingests link eventsPostgreSQL + pgvector: data and embeddingsRedis + Celery: async task queue
↓

02 · ai orchestration

LangGraph: stateful agentsLangChain: tools and RAGClaude API and embeddings: reasoning, classification, vector search
↓

03 · ai features

Threat scannerSmart aliasesAnalytics chatClick forecastBio and QR studio

built with · FastAPI · PostgreSQL · pgvector · Celery · Redis · LangChain · LangGraph · LangSmith · Anthropic Claude · Pydantic · scikit-learn · XGBoost · React · Stripe · Docker

[03] htttp.in · screens

One more screen. HTTTP.IN in use.

Admin overview: users, workspaces, links, abuse reports and platform health
Admin overview: users, workspaces, links, abuse reports and platform health

[04] next step

Let’s talk about your project.

Book a free 30-minute call. You get a range on the first call and a fixed quote after discovery, and if AI is not the right answer to your problem we say so before you spend money on it.

Book a free call calendly.com/appsin-ai/30min

phone & whatsapp
+91-9025555584
email
sales@appsin.ai
web
appsin.ai

office · mon–fri, 09:30–17:00 ist

AppsInAi Private Limited
Housing Unit, Sf No. 393, CMS School Backside, 3rd Street, Nehru Nagar, Ganapathy,
Coimbatore 641006, Tamil Nadu, India

cin U72200TZ2018PTC030580

← → or PageUp / PageDown step through the slides · F presents full screen (Esc leaves) · Ctrl+P prints (Save as PDF, margins none, background graphics on)