Pulp AI

Multi-agent LLMsSynthetic personasProvider-agnosticFastAPIpgvectorDocker

A simulation platform that lets product teams test copy, features, and pricing against AI-generated customer personas, shipping decisions in minutes instead of weeks. Built on FastAPI, Postgres (pgvector), Redis, and Docker.

Simulation running
0 personas

Variant under test

Should the Pro tier launch at $29/mo or $49/mo?

S
Sarah ChenPM · Series B SaaS

"$49 is a hard sell at renewal without a clear usage jump."

$29
R
Raj PatelIndie founder

"At $29 I'd expense it without asking anyone."

$29
M
Maya TorresVP Product · Enterprise

"$49 reads as the serious tier. $29 feels like a hobby tool."

$49
A
Alex KimGrowth lead · seed

"Lower entry point gets my whole team in faster."

$29
P
Priya MehtaHead of Product · mid-market

"I'd pay $49 if onboarding proves ROI in week one."

$49

Sample outputs from the LLM persona engine

Prediction

$29 / monthWINNER64%
$49 / month36%

Dominant cohorts

Price-sensitive SMBs37%
Growth-stage teams31%
Enterprise buyers22%
Others10%

Clustered from reasoning outputs across all simulated personas

Edvo

DartFlutterLLM Judge LoopSkill Graph

An adaptive assessment co-pilot that targets each student's mastery gaps in real time via an LLM judge loop over a skill graph. Questions are selected from a hand-curated bank with LLM fallback generation. Field-piloted across after-school learning centers.

Skill Graph

Number Theory92%
Fractions & Ratios87%
Linear Equations74%
Quadratic EquationsNOW48%
Statistics & Prob.21%

Adaptive Question

LLM JUDGE

Current target skill

Quadratic Equations

Solve: 2x² + 5x − 3 = 0

AI REASONING

Student shows mastery gaps in factoring. Curated bank match found. LLM fallback not triggered.

DartFlutterSkill GraphLLM Judge Loop

Primeplay Rentals

P2P MarketplaceNo-code MVPWhatsAppUPI

A peer-to-peer rental marketplace for high-value scuba gear across India's dive communities. Validated via a no-code MVP built on a landing page, WhatsApp coordination, and UPI payments before committing to a full build.

🧑

Owner

Lists gear

AVAILABLE
🤿

Scuba Gear

High-value equipment

🧑‍🤝‍🧑

Renter

Dive community

PEER

WhatsApp

Coordination

UPI

Payments

No-code MVP

Approach

Research & Academic

Research projects

CPI Forecasting across Indian Markets

LSTMARIMATime SeriesEconomics

Scraped ~1.2M CPI price points from 300+ Indian markets and trained LSTM models that reduced 30-day-ahead MAE by 18% versus ARIMA, revealing inflation hot-spots across eight economic zones.

Optimizing Pricing Strategies for Online Marketplace Sellers

GRUTime SeriesPricingEconomics

Trained a 2-layer GRU on 120K marketplace listings to estimate demand curves and recommend launch prices. Lifted expected seller profit by 19% and cut MAE by 8% versus a GBDT baseline. Advised by Prof. Aswini K Mishra, BITS Pilani.

Thalamo-Cortico-Thalamic Relay on SpiNNaker

Neuromorphic ComputingSpiNNakerComputational Neuroscience

Modelled the TCT relay system on the SpiNNaker neuromorphic platform for low-cost, low-power cortical signalling. Built under Prof. Basabdatta Sen Bhattacharya at BITS Pilani.

Multi-Agent Reinforcement Learning for Cooperative Hunting

MARLGame TheoryNash EquilibriumReinforcement Learning

Built a predator–prey game with Cooperate/Kill actions and trained agents with Nash-Q learning. Demonstrated that learned policies converge to the game's Nash equilibrium, confirming stable cooperative dynamics.

Neural Machine Translation: Verb Dependencies

NLPSeq2SeqMachine Translation

Built a customised Seq2Seq variant to improve NMT translation accuracy by reducing the proximity in verb phrases between source and target languages. Research conducted at IIIT Hyderabad.