Our proposal · what we can do
Custom models and inference, on one context.
Four things we build with Policybazaar. The first two are the core.
- 1Custom trained models· PB Flash and PB Pro, trained on your data.CoreBeat frontier models at 1/60th the costOur Banking77 study: a post-trained 0.5B model, 88.1% vs 81.2% for Claude Sonnet 4.5, ₹1.30 vs ₹83 per 1,000
PB Flash and PB Pro, trained on your data.
- Trained on your chats, calls and outcomes
- Released only when they beat the frontier on your evals
- Owned by Policybazaar, at a fraction of the cost
- 2Inference· The right model for each job, served in India.CoreSave up to 85% on inference spendpb.ai's 31 test chats: ₹0.13 a chat on open models vs ₹0.99 on today's Gemini stack, at higher quality
The right model for each job, served in India.
- One API for every agent
- The cheapest open model that passes your tests
- A custom model where it pays
- 3Shared context layer· One memory of each customer, under every channel.Zero questions asked twicepb.ai's test chats: 5 of 5 ask-once checks passed, against 2 of 5 on today's stack
One memory of each customer, under every channel.
- Loaded on every turn, on every channel
- Each fact kept with its source
- Said once, never asked again
- 4Evals· Prove it works, on Policybazaar's own chats.Every answer checked before it shipsRouting, prices, safety and style, scored on every release
Prove it works, on Policybazaar's own chats.
- Each agent tested on Policybazaar's past chats
- You set the pass mark; nothing goes live below it
- Every new version re-tested before go-live