> Markdown version of [/events/conference-india-2026/sessions/2030-decision-models-for](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2030-decision-models-for). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Decision models for developers who use LLMs


- **Event:** Conference India 2026

## Description

Many AI features ask a model to make a decision rather than write text. Is this support ticket urgent? Which tool should the agent call next? Does this review break the content policy? Teams often send these questions to a general-purpose LLM and parse the reply into a label. That works, but it costs more and takes longer than the task needs.

Discriminative models are built for this kind of task. They read text and return one answer from a set you define, such as a label or a score, usually with a probability attached. They cannot answer outside that set. When one fits the task, it costs less per call and replies faster than an LLM. Open models add two more benefits: you can run them on your own infrastructure, and you can retrain them yourself when they get something wrong.

The hard part is knowing when one fits. I use three questions: does the request repeat, is the output structured, and is the set of possible answers finite? I apply them to a few common features, including one where an LLM is the better choice. Then I compare the options available today: fine-tuned BERT-family encoders, newer decision models such as Jev (hosted) and Laya (open weights), and small task-specific models such as the Fern models we build at antelligent.

The last part is a live demo. I run a set of customer support requests through an LLM and two smaller models, and compare accuracy, response time and cost per 10,000 calls. Then I retrain one of the small models on a ticket it got wrong and run that ticket again. The remaining time is for questions.

## Speaker

### [Anurag Bhandari](https://www.wearedevelopers.com/@anurag-bhandari)

Chief Technologist at Antelligent


## Related talks at this congress

- [The Dream Team You Didn't Know You Had - Multi-Model, Multi-Agent, One Software Lifecycle](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2026-the-dream-team-you) — Aditya Dua
- [Stop Counting Tokens, Start Making Them Count](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2034-stop-counting-tokens) — Vicky Israni
- [Build a Zero-Cost AI Agent in Your Browser](https://www.wearedevelopers.com/events/conference-india-2026/sessions/1980-build-a-zero-cost-ai) — Aishwarya Mathuria, Nishant Thakur
- [Enterprise AI Memory at Scale](https://www.wearedevelopers.com/events/conference-india-2026/sessions/2038-enterprise-ai-memory) — Aditya Joshi

## Watch remotely

Can’t make it to Bengaluru? Watch this session live with Pro. You also get:

- All full videos, bookmarks, and playlists
- World Congress livestreams

[See pricing](https://www.wearedevelopers.com/pricing)

## Links

- [Get tickets](https://www.wearedevelopers.com/conference-india/tickets)