Project Showcase
Watch each project come alive with its own video, side by side.
PHARMA AI WORKSPACE
Pharma AI Workspace: One AI Workspace to Run an Entire Pharmaceutical Marketing Company
Every business needs technology to make its work smoother and more efficient — including businesses that have nothing to do with technology.
That statement sounds obvious. In practice, it almost never happens. Walk into a mid-sized pharmaceutical marketing company and you will find a WhatsApp group for the field team, an accountant's Excel file for expenses, a Word folder full of half-updated SOPs, a legal template someone downloaded in 2019, a dashboard nobody opens, and a marketing agency invoice for visuals that took three weeks to arrive.
The tools exist. They just don't talk to each other. And the cost of that disconnection is paid in the one currency a pharma company cannot afford to lose: trustworthy data.
Pharma AI Workspace is my answer to that problem. It is a single workspace where a pharmaceutical marketing company can handle nearly its entire work cycle — from naming a product to tracking the medical representative who sells it — without stitching together a dozen disconnected subscriptions.
Let me walk you through it, exactly the way I would demo it.
Table of Contents
Marketing and Field Enablement: Visual Aid and Training Academy
Market Intelligence: Opportunity Scanner, Tenders and Distributor Revival
Operations Automation: WhatsApp, Email, Tasks and Data Cleaning
MR Tracker and Field Force: Verifiable Field Data, Not Surveillance
Built in Tiers: Free for Small Business, Scalable for Enterprise
<a name="the-problem"></a>
The Problem: Non-Tech Industries Are Underserved by Tech
Software companies build software for software companies. That is where the money, the feedback loops and the early adopters are.
Meanwhile, a pharmaceutical marketing company — an industry with real regulatory pressure, real field operations, real compliance obligations and real margin discipline — is expected to run on generic tools that were never designed for its workflow.
So the company does one of two things. It either buys five or six separate SaaS products and spends its energy on integration, or it gives up and runs on spreadsheets and WhatsApp.
Pharma AI Workspace takes a different position: the technology should assemble itself around the business, not the other way around.
<a name="launching-a-product"></a>
Launching a Product: Naming, Research and Manufacturers
Suppose you want to launch a new pharmaceutical product. Where does the work actually begin?
It begins with the name.
Product Name Generator
The workspace lets you generate as many innovative product names as you want — brand-ready candidates, produced in seconds instead of over three meetings and a WhatsApp poll. You keep generating until something fits your molecule, your segment and your positioning.
Coming in the Next Updates: Market Research and Manufacturer Finder
Naming is only the first step of a launch. In upcoming releases, the workspace will also include market research and a manufacturer finder, so the full early-stage launch chain lives in one place:
Find the right product name → research the market → find the manufacturer — all inside the same workspace.
That is the pattern the whole product follows. Each feature is not a standalone toy; it is one link in a chain the business already walks every day.
<a name="communication-agreements-regulatory"></a>
Communication, Agreements and Regulatory Documents
Once a product exists, the paperwork starts. This is where most small and mid-sized pharma companies quietly lose weeks.
Translator
Pharma is not a single-language business. Distributors, manufacturers, export partners and regional field teams rarely share one language. A built-in translator handles communication and connectivity so language never becomes the bottleneck in a deal.
Agreement Formatting
Then you may need detailed agreement formatting. The Agreement Formatting feature helps you create and structure nine different types of agreements — properly formatted, properly structured, and generated in minutes rather than borrowed from an old file and edited badly.
For a PCD pharma or a marketing company that signs distributor, manufacturing, franchise and service agreements on a rolling basis, this alone replaces a recurring legal-drafting cost.
Regulatory Document Analysis
There is also a Regulatory Document Analysis feature, which lets you check and analyze regulatory documents. Instead of one person reading a dense document line by line and hoping nothing was missed, the workspace reads it with you and surfaces what matters.
In an industry where a missed clause is not an inconvenience but a liability, this is not a convenience feature. It is a risk-reduction feature.
<a name="knowledge-layer"></a>
Knowledge Layer: Meeting Minutes, SOPs and Q&A
A company's real operating knowledge usually lives in three places: meetings nobody documented, SOP files nobody updated, and the heads of two or three senior people.
The workspace turns all three into a queryable system.
Meeting Minutes
Meeting Minutes takes information from your meetings and turns it into useful, structured notes. The decision made on Tuesday is still retrievable in March.
SOP Section
A dedicated SOP section gives you a proper place to work with your standard operating procedures — not a shared drive folder, but an actual working surface.
Q&A
The Q&A section lets you get answers directly from your business knowledge. New employee asks how a return is processed? They ask the workspace instead of interrupting a manager.
Call Summarizer
The Call Summarizer turns calls into useful summaries. Distributor negotiations, doctor feedback calls, internal reviews — all of it becomes searchable text instead of a vague memory.
SOP Auto Updater
And because SOPs decay the moment they are written, the SOP Auto Updater helps keep standard operating procedures current instead of letting them rot into documents everyone ignores.
<a name="marketing-field-enablement"></a>
Marketing and Field Enablement: Visual Aid and Training Academy
Visual Aid
Visual Aid helps you create short marketing visuals that explain pharmaceutical products to doctors in a simple, clear way.
This matters more than it sounds. A medical representative gets a very small window of a doctor's attention. What they carry into that window determines the outcome of the visit. Visual Aid means that asset can be produced in-house, quickly, per product, without an agency cycle.
Training Academy
The Training Academy creates sales pitches for products that medical representatives can practice on. The MR rehearses how they will present a product before they walk into a doctor's chamber.
Most pharma companies train once at onboarding and then hope. This turns product training into something continuous, per-product and repeatable.
<a name="market-intelligence"></a>
Market Intelligence: Opportunity Scanner, Tenders and Distributor Revival
Opportunity Scanner
The Opportunity Scanner analyzes what the standing of a particular product is in the market and helps you understand its actual market opportunity. It answers the question every product manager asks and few can answer with evidence: is this worth pushing harder, or are we pouring effort into a saturated segment?
Tender Drafter and Tender Alert
Institutional business runs on tenders, and tenders run on deadlines. The workspace includes a Tender Drafter to produce the documentation, and Tender Alert so relevant opportunities reach you instead of passing you.
Distributor Revival Campaign
Every pharma marketing company has a list of distributors who used to order and quietly stopped. That list is usually the cheapest available revenue in the business, and it is almost always ignored.
The Distributor Revival Campaign feature helps businesses systematically work on inactive or declining distributor relationships instead of only chasing new ones.
<a name="operations-automation"></a>
Operations Automation: WhatsApp, Email, Tasks and Data Cleaning
This is the layer that removes repetitive manual work from the day.
WhatsApp Auto Reminder — sends automated messages to doctors and to your own team. In the Indian pharma market, WhatsApp is the communication channel; ignoring it means ignoring how the industry actually talks.
Auto Emailing — automates repetitive email communication so your team writes the emails that need a human and none of the ones that don't.
Task Tracker — keeps track of your work and tasks so accountability does not depend on somebody's memory.
Data Cleaner — cleans and organizes business data. Unglamorous, and quietly the highest-leverage feature in the list, because every analysis downstream inherits the quality of this step.
LinkedIn Auto Post
LinkedIn Auto Post is a full content pipeline, not a scheduler. It can:
Plan your content
Generate the posts
Produce different types of posts from that content — including video and audio posts
Schedule everything
Automatically publish at the scheduled time
The result is a LinkedIn presence that stays current automatically, which for a B2B pharma company is a real distribution channel for distributor acquisition and hiring — not vanity marketing.
<a name="mr-tracker"></a>
MR Tracker and Field Force: Verifiable Field Data, Not Surveillance
This is the feature I care most about, and the one that needs the most honest explanation.
How the MR Tracker Works
A Medical Representative can access the web application from any device — no app store, no company-issued hardware.
1. Starting the day. Whenever the MR starts their day, they simply tap Start. The system records the date and time the working day begins.
2. Reaching a doctor. When the MR reaches a doctor, they press Reached. At that point the system can record:
the doctor's details
a live hospital photo
the activities performed during the visit
the MR's current live location
The MR can also complete this during free time before the appointment is granted — because anyone who has done field work knows that waiting is most of the job.
3. Next doctor, repeat. Once a visit is done, the MR moves to the next doctor and repeats the same process.
4. Breaks. The MR can also specify when they are taking a break.
In short, the system can monitor and calculate their working time, their TA (travel allowance), their field activities, and the work they have actually done. All of this feeds into the Field Force dashboard, where management can finally see the field as data rather than as anecdote.
Let's Be Direct About the Ethics
Field tracking software has a bad reputation, and often it deserves it. So let me state the design position plainly.
This system is not designed for micromanagement. It is not constantly tracking the MR's location.
Location is captured only at relevant endpoints — mainly to calculate TA and to verify the authenticity of reported work. There is no continuous location stream, because a continuous location stream is not needed to answer the business's actual question.
Why does the business need this at all? Because some people may claim false expenses while doing little or even no actual work. That creates misleading company data — and misleading company data becomes fatal when management uses it to make strategic decisions.
If a territory looks weak because the product is weak, you fix the product. If it looks weak because the visits never happened, you have just spent a quarter fixing the wrong thing.
So the purpose is not to constantly watch the employee. The purpose is to give the company accurate, verifiable field data it can actually trust — and to protect the honest MR from being judged by the same undifferentiated numbers as the dishonest one.
<a name="ceo-digest-business-suite"></a>
CEO Digest and Business Suite: The Management View
CEO Digest
CEO Digest gives you an overview of your company and its products in one read, including:
product status
expiry information
complaints
other important business information
This is the answer to a specific failure mode: the founder who has all the data in the system and still cannot tell you the state of the business without three phone calls.
Business Suite
Business Suite lets you monitor your business activities, giving you nearly everything about your own business in one place. Where CEO Digest is the summary, Business Suite is the operating surface.
<a name="chat-with-data"></a>
Chat With Data: Your Automated AI Analyst
This is one of the best features in the workspace.
Chat With Data is an AI-powered smart automated analyst. Here is what it does:
You give it your data.
It cleans the data.
It generates a detailed analysis report from it.
Then you can go one step further. You can ask questions directly to your data, and it will analyze the information and answer you.
So instead of staring at spreadsheets and static reports and hoping the right question occurs to you, you can actually talk to your data.
For a company that cannot afford a full-time data analyst — which describes almost every small and mid-sized pharma marketing company in India — this is the difference between having data and using it.
<a name="built-in-tiers"></a>
Built in Tiers: Free for Small Business, Scalable for Enterprise
What makes Pharma AI Workspace genuinely different is that it is built in tiers. Small businesses, medium-sized businesses and large enterprises can all use it according to their own needs and their own budgets.
For Small Businesses
The system uses many free and unlimited tools that do not require additional subscription charges. That means a small business can use these features for free, with enough functionality for a small company to actually operate on the system — not a crippled trial, but a working setup.
This is a deliberate choice. The companies that need automation most are the ones least able to justify a per-seat enterprise contract.
For Medium and Enterprise Businesses
Larger operations get more options:
Buy APIs for higher-capacity, higher-quality model access
Use your own GPU if you have the hardware
Switch between smarter and lighter models depending on the task — heavy reasoning for regulatory analysis, lightweight models for routine formatting
Use different providers and models through OpenRouter, Grok, Gemini and other available options
Run a Local LLM in a Few Clicks
If you want to use a local AI model, you can set up your own local LLM with just a few clicks. The workspace lets you download and run a local model depending on the hardware you actually have available.
Which means: anyone can use the system, even without an expensive GPU.
For pharma specifically, local models are not only a cost decision — they are a data-residency decision. Some documents should never leave the building.
<a name="meet-mai"></a>
Meet Mai: The Voice Assistant That Operates the Workspace
And then there is Mai.
Mai is your personal assistant inside the workspace. Instead of manually opening features and navigating through the application, you simply ask Mai to do it.
You can give Mai voice commands, and it will operate the relevant functionality inside the application and return the result. You don't even need to touch the keyboard. You tell Mai what you want, and Mai works with the application to get it done.
This is what makes a 25-feature workspace usable by someone who does not want to learn a 25-feature workspace. The interface stops being something you navigate and becomes something you talk to.
<a name="the-philosophy"></a>
The Philosophy Behind It
The idea behind Pharma AI Workspace is simple:
Businesses should not need dozens of disconnected tools just to manage their daily work. The technology should come together around the business.
With Pharma AI Workspace, a pharmaceutical marketing company can go from:
product naming → market and manufacturer research (future updates) → translation → agreements → regulatory document analysis → meetings → SOPs → Q&A → visual marketing → calls → market opportunities → tenders → WhatsApp reminders → tasks → CEO reporting → MR field tracking → training → distributor revival → data cleaning → email automation → SOP updates → LinkedIn automation → data analysis → business monitoring
— all inside one intelligent workspace. And with Mai, you can interact with that workspace through your voice.
Because technology should make the business easier to operate.
The business should not have to become a technology company just to use technology.
<a name="faq"></a>
Frequently Asked Questions
What is Pharma AI Workspace?
Pharma AI Workspace is an all-in-one AI platform for pharmaceutical marketing companies. It covers the full work cycle — product naming, agreements, regulatory document analysis, meeting minutes, SOPs, visual aids, tenders, MR field tracking, data analysis and business monitoring — in a single workspace, operable by voice through an assistant called Mai.
Who is it built for?
Pharmaceutical marketing companies of any size. It is built in tiers so small businesses, medium-sized businesses and large enterprises can each use it according to their own needs and budget.
Can a small pharma company use it for free?
Yes. The system uses many free and unlimited tools that require no additional subscription charges, giving a small company enough functionality to actually operate on the system without paying for AI usage.
Does it require an expensive GPU?
No. You can run it on hosted APIs, use your own GPU if you have one, or set up a local LLM in a few clicks — with the workspace helping you choose a model that matches the hardware you already have.
Which AI models does it support?
You can switch between smarter and lighter models depending on the task, and use different providers and models through OpenRouter, Grok, Gemini and other available options — or run a local model entirely on your own machine.
Is the MR Tracker a surveillance tool?
No. It is not designed for micromanagement and does not track the medical representative's location continuously. Location is captured only at relevant endpoints, primarily to calculate travel allowance and verify the authenticity of reported work, so the company gets field data it can trust.
What does the MR Tracker actually record?
Day start time, doctor details on each visit, a live hospital photo, the activities performed, the MR's location at the visit endpoint, and declared breaks — which together produce working time, TA, field activity and completed work, visible through the Field Force dashboard.
Does the medical representative need a special device?
No. The MR Tracker is a web application accessible from any device.
What is Chat With Data?
Chat With Data is an AI-powered automated analyst. You give it your data, it cleans the data and generates a detailed analysis report — and you can then ask questions directly to your data and get analyzed answers back.
What is coming next?
Market research and a manufacturer finder, so the launch chain runs end to end inside the workspace: from finding the right product name, to researching the market, to finding the manufacturer.
Want to See It Run?
Pharma AI Workspace is a working system, not a concept deck. If you run a pharmaceutical marketing company — or you operate in any non-technical industry drowning in disconnected tools — I would like to show you what a single workspace does to your week.
Get in touch for a walkthrough.
Built by Mohammad Faisal Arif Khan — bringing AI into the daily processes of non-tech industries, so manual work shrinks and people get to spend their time thinking instead.
MAI
M.AI 0.1
Your AI. Your Infrastructure. Your Rules.
Voice + Text Assistant • 8 Providers • Persistent Memory • GitHub Awareness • Zero Cost
Why It Matters
Every mainstream AI assistant comes with the same trade: convenience in exchange for control. Your conversations live on someone else's servers. Your API access is metered by someone else's billing. Your assistant forgets you the moment a session ends — unless you pay for it to remember.
M.AI 0.1 rejects that trade entirely. It is a personal AI assistant that runs on infrastructure you control, orchestrates the free tiers of eight LLM providers into one seamless intelligence, remembers everything across sessions, and operates under a written constitution — at a running cost of exactly zero.
One Assistant. Eight Brains.
Behind M.AI's single chat window sits a capability-aware routing engine connected to Google Gemini, Groq, Cerebras, SambaNova, OpenRouter, Hugging Face and more — over twenty models in total. Every request is routed to the provider best suited for the task: lightning-fast models for voice replies, deep reasoning models for hard problems, dedicated code models for programming.
When a provider fails or rate-limits, the router silently moves to the next. A self-healing health system probes degraded providers every five minutes and restores them automatically. The user never sees an outage — they just see answers.
It Knows the Whole Portfolio
M.AI is connected to its creator's GitHub account — every repository, every project, every README. Ask it what any project does, how it's built, what technology it uses, or how two projects compare, and it answers from the actual source code, not from a stale description. It is a living, conversational index of an entire body of work — and for anyone visiting, it means the fastest way to understand any project is simply to ask.
It Remembers You
M.AI runs a three-tier memory system. Session context keeps the current conversation sharp. Project knowledge gives it deep awareness of the work you've connected. Long-term memory — stored with vector embeddings and recalled by semantic similarity — means it remembers conversations from weeks ago and brings them back exactly when relevant. Memory persists across restarts, on your storage, owned by you.
It Does Real Work
M.AI is not limited to talking. Connected projects expose skills — start a dev server, run a build, trigger a content pipeline — that the assistant executes in sandboxed processes with strict CPU, memory, and timeout caps. Its first integrated project is a complete Instagram automation system that it can drive end-to-end by voice command.
Speak to it or type to it: dual speech-to-text paths and browser-native voice output mean the entire voice experience works without a single paid speech API.
Security Without Trust
M.AI uses a bring-your-own-keys model with a guarantee most platforms cannot make: your API keys never touch the server's storage. Keys live in your browser, travel as per-request headers, are used for one call, and are discarded. No accounts, no key vaults, no server-side secrets. Even on a hosted instance, the operator never holds your credentials.
Governed by a Constitution
Nineteen written rules are compiled into the assistant's core at startup: amplify the human, never replace them. Log everything. A panic stop command is always valid and immediate. Never use a paid service. Self-modification requires a six-stage review gate with human approval. The assistant's boundaries are not implied — they are documented, versioned, and enforced.
Deployed Like Software Should Be
One Docker Compose file runs the entire system — orchestrator, web UI, and Redis — identically on a laptop, a budget VPS, or Oracle's free ARM cloud. It is live in production today, served over SSL, built for both ARM and x86. Setup is a clone, an install, and a single command.
M.AI 0.1 proves a simple thesis:
a personal AI you fully own can be as capable as one you rent —
and it can cost nothing at all.
JOBHUNT AGENT
The Self-Hosted AI Job Application Automation Platform
Automate Your Job Search • AI Resume Tailoring • 100% Private • 100% Free
Automate Your Job Search Without Giving Up Your Data
Searching for a job is a full-time job. Sourcing openings across dozens of career pages, tailoring a resume for every application, filling the same forms again and again, tracking follow-ups — the repetitive work consumes the hours that should go into interview preparation.
JobHunt Agent is a self-hosted job application automation tool that handles the entire workflow — job sourcing, AI-powered job matching, resume tailoring, automated form filling, and application tracking — while keeping every piece of your personal data on your own computer. No cloud uploads. No subscriptions. No third party ever holds your resume.
AI Job Matching That Explains Itself
JobHunt Agent automatically sources job listings from official Greenhouse, Lever, Ashby, and Workable APIs plus remote job boards like Remotive and Arbeitnow. Every job is scored by AI against your skills, target roles, and preferences — with a written reason, a list of matched skills, and a list of missing skills for every score. Duplicate listings across job boards are detected automatically using vector embeddings, so each opportunity appears exactly once.
AI Resume Tailoring That Never Leaves Your Machine
For every shortlisted role, JobHunt Agent generates a tailored resume and a custom cover letter using a local AI model running on your own hardware. Your master resume, your work history, and your personal details are never sent to any cloud service — the privacy boundary is built into the architecture itself. Cloud AI sees only the public job posting text. You see professionally tailored application documents for every role.
You Approve Every Application — Always
JobHunt Agent is not a spam cannon. Every prepared application enters a review queue where you see the job, the score, the tailored resume, and the cover letter — and nothing is submitted until you explicitly approve it. Once approved, browser automation fills the application form, attaches your documents, and captures a screenshot for your records. A built-in idempotency system makes it technically impossible to apply to the same job twice.
Application Tracking and Follow-Up, Handled
Every submitted application is tracked automatically. Follow-up reminders are scheduled seven days out. Stuck applications are flagged. A daily digest lands in your Telegram with everything that happened: new jobs sourced, scores assigned, applications submitted, and items waiting for your review. Thirteen generated PDF reports — from a top-scoring shortlist to a skills-gap analysis that tells you exactly which skills to learn next — turn your job search into measurable progress.
Private by Architecture, Free by Design
The entire platform runs on your machine in Docker containers bound to localhost — nothing is exposed to the internet. Credentials are encrypted at rest. Logs automatically redact personal information. And the entire stack is built from free and open-source components: PostgreSQL, Ollama local AI, Playwright browser automation, and self-hosted n8n orchestration. There is no subscription, no per-application fee, and no premium tier. The operating cost is zero.
Set Up in Minutes, Runs on Schedule
One docker-compose command brings up the full 11-service stack. Add your master resume, set your target roles and skills in the dashboard, and the pipeline runs automatically on a schedule — sourcing, scoring, and preparing applications around the clock, then waiting for your approval before anything goes out. Your job search keeps moving even while you sleep. The decisions stay yours.
JobHunt Agent does the hundred hours of repetitive work
so you can spend your energy on the one hour that matters — the interview.
EXAMINER AI
AI Exam Grading for Descriptive Answers — Explainable, Rubric-Based, Private
Automated Answer Evaluation • Instant Student Feedback • Local AI • Zero API Cost
Automated Exam Grading That Shows Its Work
Grading descriptive exam answers is the slowest, most expensive, and most inconsistent process in education. A trained examiner spends minutes on every long-form answer; a board exam generates millions of them. Students wait weeks for results and receive a number with no explanation. And two examiners grading the same answer routinely award different marks.
Examiner AI is an AI-powered exam evaluation system that grades descriptive and numerical answers in seconds — using the same structure a human examiner uses: a marking rubric, partial credit, step verification, and penalty deductions. Every score comes with a transparent, criterion-by-criterion breakdown showing exactly where each mark was earned or lost.
Three Signals. One Defensible Score.
Most AI grading tools ask a chatbot for a number and hope. Examiner AI triangulates three independent evaluation signals: a deterministic rubric engine aligned to Maharashtra SSC marking standards, neural semantic similarity that measures whether the student understood the concept — even in their own words — and AI-generated feedback that explains the result. The rubric carries the most weight; the AI never grades alone.
A student who paraphrases a correct answer still earns marks, because the system compares meaning, not vocabulary. A student who skips a solution step loses exactly the marks that step was worth — and is told so.
Instant Feedback Students Can Learn From
Every evaluated answer receives constructive, educator-style feedback generated by a locally-running AI model: what was done well, which key points are missing, and what to improve next time. Grading stops being a verdict and becomes a teaching moment — delivered in seconds instead of weeks.
Handles the Answers That Matter
• Long-form theory answers — solution structure, diagram presence and labeling, language clarity
• Short definition answers — keyword and concept coverage with penalty deductions
• Numerical problems — formula correctness, substitution steps, unit validation, and final-answer tolerance within ±2%
The rubric engine is fully extensible — new answer types and marking schemes plug into the same scoring pipeline.
Private by Architecture
Student exam data is among the most sensitive data an institution holds. Examiner AI runs every AI component locally — the embedding model and the feedback LLM both execute on the institution's own hardware through Ollama. No student answer, no question paper, and no grade ever touches a cloud API. There are no per-evaluation fees, no API keys, and no external dependencies in the grading path.
Built for Trust, Not Just Speed
Every evaluation carries a confidence score, and the system is designed for human-in-the-loop review: low-confidence cases escalate to a human examiner rather than being silently auto-graded. Every rubric result exports as a structured audit record — so when a grade is questioned, the institution can show precisely how it was computed. Examiner AI is built to assist examiners and earn the trust of students, parents, and boards.
Weeks of grading, delivered in seconds —
with every mark explained, every answer private, and every educator still in control.
PLANT DISEASE DETECTION
AI Crop Disease Diagnosis With Treatment and Dosage — From a Single Leaf Photo
38 Diseases • 14 Crops • Instant Diagnosis • Exact Dosage • Weather-Aware Advice
AI Plant Disease Identification From One Photo
Crop diseases destroy up to 40 percent of global agricultural production every year — and for most farmers, getting a reliable diagnosis means waiting days for an expert, guessing from a search engine, or spraying the wrong chemical and hoping. By the time the disease is identified, it has often already spread.
Plant Disease Detection is an AI-powered crop disease diagnosis system that identifies 38 plant diseases across 14 crops — tomato, potato, corn, grape, apple, and more — from a single leaf photograph, in seconds. The deep learning model, built on ResNet50 transfer learning and trained with field-realistic image augmentation, recognizes fungal, bacterial, and viral diseases as well as pest damage, even in imperfect phone photos.
From Diagnosis to Treatment Plan — Automatically
A disease name alone does not save a crop. For every diagnosis, the system delivers a complete, actionable treatment plan: the specific fungicide or pesticide product for that disease, step-by-step application instructions, spray schedules, prevention strategies for the next season, and expert tips on timing and safety. Disease identification becomes disease management.
Exact Dosage for Your Exact Field
Pesticide overdosing wastes money and damages soil; underdosing lets the disease survive. Enter your field size in hectares, and the system automatically calculates the precise quantity of product needed — based on the recommended concentration and standard water requirements per hectare. The built-in cart turns that calculation into a ready shopping list. No guesswork, no waste, no under-treatment.
Smart Farming Advice That Knows the Weather
The advisory layer integrates a 7-day weather forecast — temperature, humidity, and rainfall from NASA satellite data — directly into the recommendation. A locally-running AI agronomist combines the diagnosis, the forecast, and the field context into practical guidance: spray before tomorrow's rain, adjust for crop maturity, monitor for secondary infections. Optional satellite vegetation indices add field-level crop health monitoring. This is precision agriculture made accessible.
Serious Machine Learning Underneath
The model is built like production ML, not a demo: ResNet50 transfer learning with a deep custom classification head, two-phase fine-tuning that protects pre-trained knowledge, aggressive augmentation simulating real field photography, mixed-precision GPU training, and rigorous per-class evaluation with full confusion-matrix analysis across all 38 classes. A lightweight 25 MB inference model makes deployment affordable — from cloud hosting down to edge devices.
Built for Real Farms
Every design decision targets practical farming: treatment recommendations drawn from products farmers can actually buy, dosage mathematics in hectares and liters, weather data from a free public API, and AI advice that runs on local hardware with zero per-query cost. The entire system operates without subscription fees — the technology serves the farm, not the other way around.
One photo. One diagnosis. One complete plan —
delivered in the seconds between noticing a sick leaf and deciding what to do about it.
AI-Powered Social Media Automation for Filipino Community Creators
The Creator's Problem
Building a consistent, high-quality Instagram presence for a Filipino community audience is a full-time job. Scripts need to be written in Taglish. Videos need to be assembled. Captions need hashtags that actually work. News needs to be found, verified, and turned into content before it goes cold. And none of it can sound like it came from a generic AI tool — because Filipino audiences immediately recognize and reject content that doesn't speak their language.
Palawan Creator automates the entire pipeline. From finding the news to posting the Reel, every step is handled automatically — on a schedule, in the right voice, in the right format, at the right time of day.
Seven Pillars. Seven Voices. One System.
Palawan Creator operates across seven content pillars — Local News, Job Alerts, OFW Support, Palawan Cuisine, Nature & Science, Environmental Conservation, and Government Programs. Each pillar has its own AI persona with a distinct Taglish voice: Manong Ronnie for news, Ate Cita for jobs, Nanay Mely for recipes, Kuya Jun for OFW families, and more.
Audiences don't experience a brand posting at them. They experience a neighbor talking to them. That is an intentional design decision — and it is why this content performs.
What the System Does — Automatically
• Monitors six RSS feeds and scores articles by local relevance, engagement potential, and content safety — no manual topic selection
• Writes scripts in the voice of the assigned pillar persona, then passes every script through a five-gate constitutional AI safety check before it is used
• Generates captions with exactly 25 Taglish hashtags within Instagram's character limit
• Converts scripts to audio using Microsoft's Filipino neural voice (BlessicaNeural) with word-level timestamps for frame-accurate subtitles
• Assembles portrait 1080x1920 MP4 Reels with stock footage, voice track, and burned-in subtitles via bundled FFmpeg
• Posts to Instagram via the official Graph API on a PHT-timezone schedule — with automatic retry for any failed posts within a 4-hour recovery window
• Detects breaking news spikes and triggers the relevant pillar outside the normal schedule
• Accepts voice commands in Taglish — so the creator can control the pipeline from anywhere, without touching a screen
Built on a Foundation That Never Goes Down
Every critical system in Palawan Creator has a fallback. The LLM dispatcher chains across Gemini, Groq, OpenRouter, and Pollinations automatically — if one provider rate-limits or fails, the next takes over without interrupting the pipeline. The scheduler detects and recovers missed posts. The topic pool is pre-generated so posting never waits on real-time scoring. The system is designed to keep running even when individual components do not.
Privacy and Security by Design
All API credentials are stored encrypted using Fernet symmetric encryption, tied to the user's machine. No credentials are stored in plain text anywhere in the application. Changing the account's content niche requires a PIN to prevent accidental misconfiguration. Each account's data — topics, post history, settings — is stored in isolated user data directories that survive app reinstalls.
Zero Cost to Operate
Palawan Creator runs entirely on free-tier services — Gemini Flash, Groq, Edge TTS, Pexels, Pollinations, and the Instagram Graph API. A creator posting multiple Reels per day across seven content pillars pays nothing in API fees. The only infrastructure required is the Windows machine the app runs on.
One Installer. Ready in Minutes.
Palawan Creator ships as a single Windows executable. Python, FFmpeg, and all dependencies are bundled inside. The first-run wizard walks through API key setup and Instagram authentication. From installation to first automated post takes less than 20 minutes. Updates install silently in the background — no creator action required.
Palawan Creator gives a solo community creator
the content output of an entire production team —
without the team, without the budget, and without the hours.