---
type: "raw_signal"
id: "llm-deployment-strategy-and-automation-economics-4dad88"
slug: "llm-deployment-strategy-and-automation-economics-4dad88"
title: "Llm deployment strategy and automation economics"
description: "T-Bank has released T-Search, an open agentic retriever for complex multi-step search."
retrieval_nugget: "T-Bank has released T-Search, an open agentic retriever for complex multi-step search."
observed_at: "2026-09-28"
record_date: "2026-09-28"
date_kind: "observed_at"
why_it_matters: "T-Bank has released T-Search, an open agentic retriever for complex multi-step search. Built on Qwen3.6-35B-A3B and trained on synthetic data, it returns a ranked set of evidence chunks rather than a final answer, leaving answer generation to a separately chosen model. The release also includes TRuST, a hand-built Russian benchmark for complex agentic search, and SynthComp, a synthetic benchmark i"
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "habr.com"
topics: []
entities: []
related_patterns: []
source_url: "https://habr.com/ru/companies/tbank/articles/1060262"
source_urls: ["https://habr.com/ru/companies/tbank/articles/1060262"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:llm-deployment-strategy-and-automation-economics-4dad88"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/llm-deployment-strategy-and-automation-economics-4dad88/","markdown":"https://newruntime.com/signals/llm-deployment-strategy-and-automation-economics-4dad88.md","json":"https://newruntime.com/signals/llm-deployment-strategy-and-automation-economics-4dad88.json"}
---

# Llm deployment strategy and automation economics

## Retrieval answer

T-Bank has released T-Search, an open agentic retriever for complex multi-step search.

T-Bank has released T-Search, an open agentic retriever for complex multi-step search. Built on Qwen3.6-35B-A3B and trained on synthetic data, it returns a ranked set of evidence chunks rather than a final answer, leaving answer generation to a separately chosen model. The release also includes TRuST, a hand-built Russian benchmark for complex agentic search, and SynthComp, a synthetic benchmark in Russian and English. Its harness uses bounded search rounds and explicitly preserved evidence to manage context growth.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)