What's New at Applivo
New features, improvements, and fixes to help you streamline your career growth.
The AI Transformation
Dual-LLM
Dual-LLM Job Analysis Engine Launched
Applivo now uses a two-pass AI system for job matching. Pass 1 runs a fast rule-based keyword filter using LLaMA-8B — jobs with less than 30% skill overlap are scored and skipped instantly with no LLM cost. Pass 2 sends qualified jobs to LLaMA-70B for deep structured extraction: required skills, tech stack, ATS keywords, responsibilities, match scores, and personalized recommendations.
Models Used
llama-3.3-70b-versatile & llama-3.1-8b-instant
Inference
Groq primary with Google Gemini fallback
6-Hour Autonomous Agent Cycle
Celery Beat fires the full pipeline every 6 hours: scrape, analyze, gate, queue, apply, notify, follow-up. A Priority Queue ensures Premium subscribers' applications are processed before lower-tier users.
- 7 named Celery queues
- In-memory min-heap backed by Redis
- Concurrency level 4
- Daily application limits enforced
AI Career Assistant Chat
| Plan | Monthly Credits |
|---|---|
| Starter | 100 messages |
| Pro | 500 messages |
| Premium | Unlimited |
Infrastructure & Payments
Distributed
Razorpay Subscription Billing
Full Razorpay payment flow integrated with HMAC-SHA256 verification. Automated 30-day subscription provisioning on successful capture.
6-Container Docker Compose Stack
| Container | Role | Port |
|---|---|---|
| backend | FastAPI / Uvicorn | 8000 |
| worker | Celery Worker | internal |
| database | PostgreSQL 16 | 5433 |
| redis | Redis 7 | 6379 |
Foundation
Security
AES-256-GCM Encryption
Applied session cookies and credentials encrypted at rest with random nonces. Credentials never stored in plaintext.
Lifecycle Machine
Every application tracked via immutable event logs. Logic handles transitions from Pending to Offer Accepted or Failure.