Silver Touch nabs RITES Parakh AI contract

// 2h agoNEWS

Silver Touch nabs RITES Parakh AI contract

Silver Touch Technologies Ltd has secured a ₹6.28 Cr order from RITES Limited to build "Parakh," India's first self-hosted, multi-model AI platform for appraising complex infrastructure project reports. Operating entirely on-premises with zero external data dependencies, the system integrates Llama 3.1, Mistral, and Qwen models with over 500 codified engineering rules and a hallucination prevention framework.

// ANALYSIS

This partnership represents a major milestone in the deployment of secure, localized generative AI for critical public sector infrastructure evaluation.

–The selection of self-hosted open-weight LLMs (Llama 3.1, Mistral, Qwen) highlights a strong enterprise and government preference for total data sovereignty over public cloud APIs.
–Combining the generative capabilities of LLMs with deterministic, rule-based engineering logic solves the LLM hallucination issue for high-stakes compliance and project appraisals.
–A contract size of ₹6.28 Cr showcases the growing willingness of public sector enterprises to fund custom, production-grade AI integrations.

// TAGS

silver-touchritesparakhself-hostedllmgenerative-aillamamistralqweninfrastructure

DISCOVERED

2h ago

2026-07-08

PUBLISHED

2h ago

2026-07-08

RELEVANCE

6/ 10

AUTHOR

speedystox

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

TUTORIAL39m ago

Developer maps Claude Fable 5 agentic workflows

A developer has published a visual breakdown of Anthropic's Claude Fable 5 agentic architecture, mapping its complex workflows into nine editable Excalidraw diagrams. The resource illustrates core agent concepts like trust ledgers, daily loops, and standing goals to help developers design autonomous AI systems.

OPEN SOURCE3h ago

OpenSeeFace is a lightweight, open-source facial tracking library optimized for robust and fast avatar animation.

OpenSeeFace is a lightweight facial landmark tracking library designed specifically for avatar animation, prioritizing tracking stability in challenging real-world conditions over academic benchmark scores. Powered by MobileNetV3-based models converted to ONNX, it performs fast CPU inference to track a single face at 30-60 frames per second. The project is widely used in the VTubing ecosystem, serving as the tracking engine behind popular avatar software like VSeeFace, VTube Studio, VNyan, and Warudo.

VIDEO3h ago

Anthropic Claude Code engineer Thariq Shihipar shared key insights on "unhobbling" AI agents, prompt optimization, and navigating codebase "unknowns."

Anthropic Claude Code engineer Thariq Shihipar shared technical insights on "unhobbling" AI models, highlighting that unlocking capability relies more on prompt/agent harnesses than model size. In his talk, Shihipar discussed how Claude Code uses active tools (like writing search scripts) to solve tasks that standard chat models fail, and revealed that the team counterintuitively removed 80% of Claude Code's system prompt because new models are constrained by too many examples. This shifts the engineering bottleneck onto the developer, where the primary skill becomes mapping and surfacing codebase "unknowns" before the agent encounters them—utilizing techniques like blind-spot passes, brainstorm prototypes, and proactive interviews. Additionally, Shihipar advocated for an "unreasonable" mindset shift, arguing that the traditional tradeoff of choosing only two between good, fast, and cheap is no longer real when building with agentic workflows.