Crypto Flexs
  • DIRECTORY
  • CRYPTO
    • ETHEREUM
    • BITCOIN
    • ALTCOIN
  • BLOCKCHAIN
  • EXCHANGE
  • ADOPTION
  • TRADING
  • HACKING
  • SLOT
Crypto Flexs
  • DIRECTORY
  • CRYPTO
    • ETHEREUM
    • BITCOIN
    • ALTCOIN
  • BLOCKCHAIN
  • EXCHANGE
  • ADOPTION
  • TRADING
  • HACKING
  • SLOT
Crypto Flexs
Home»ADOPTION NEWS»New Computer, LangSmith Integration Achieves 50% Higher Recall
ADOPTION NEWS

New Computer, LangSmith Integration Achieves 50% Higher Recall

By Crypto FlexsJuly 3, 20243 Mins Read
Facebook Twitter Pinterest LinkedIn Tumblr Email
New Computer, LangSmith Integration Achieves 50% Higher Recall
Share
Facebook Twitter LinkedIn Pinterest Email





According to the LangChain blog, New Computer significantly improves the memory search system by integrating LangSmith, achieving 50% higher recall and 40% higher accuracy compared to previous baselines.

About the new computer

New Computer is the team behind Dot, the first personal AI designed to truly understand its users. Dot’s long-term memory system evolves by observing linguistic and behavioral cues, providing timely and personalized support to create a perception of true understanding.

A brief overview of Dot’s Agentic Memory

The innovative agent memory system developed by New Computer dynamically generates or precomputes documents for future retrieval. Unlike standard augmented retrieval generation (RAG) methods, this system structures information during memory generation, ensuring accurate and efficient retrieval as the memory accumulates.

Dot’s memory contains meta fields like status (e.g. completed or in progress) and date/time fields like start date or due date, which act as additional filters during high-frequency queries.

Improving memory retrieval using LangSmith

New Computer used LangSmith to rapidly iterate on a labeled example dataset. To maintain user privacy, synthetic data was generated, creating synthetic users with background stories generated by LLM. The team stored queries and available memory in the LangSmith dataset, labeled the associated memory for each query, and defined evaluation metrics such as precision, recall, and F1.

The experiment started with a baseline system that retrieved relevant memories using semantic search. A variety of techniques were tested to evaluate performance, including similarity search and keyword methods such as BM25. In some cases, pre-filtering by meta-fields was required for effective performance.

LangSmith’s SDK and experiment UI allowed New Computer to efficiently run and evaluate these experiments, and significantly improved the memory system.

Adjusting conversation prompts with LangSmith

Dot’s responses are generated by dynamic conversational prompts that integrate relevant memories, tool usage, and highly contextual action instructions. To optimize the prompts, synthetic users generated a wide range of queries, allowing the team to examine the global effects of prompt changes using LangSmith’s Experimental Comparison View.

In failure cases, we improved iteration speed while evaluating and adjusting conversation prompts by adjusting prompts directly within the LangSmith UI.

What’s next for new computers?

New Computer aims to deepen the relationship between humans and AI, and Dot continues to improve its ability to adapt to user preferences and provide personalized experiences. With a recent launch bringing in a new wave of users and a 45% conversion rate to the paid tier of the app, the partnership with LangChain and the use of LangSmith remain key to simulating complex human-AI interactions.

Image source: Shutterstock



Share. Facebook Twitter Pinterest LinkedIn Tumblr Email

Related Posts

HOLONYM’s Human Network: Convert on boarding on boarding on human -friendly keys

June 7, 2025

NVIDIA’s GB200 NVL72 and Dynamo improve MoE model performance

June 7, 2025

TEZOS promotes scaling efforts by activating data soluble layers.

June 7, 2025
Add A Comment

Comments are closed.

Recent Posts

Solana Whale will not announce $ 17 million in four years. Should I worry?

June 7, 2025

HOLONYM’s Human Network: Convert on boarding on boarding on human -friendly keys

June 7, 2025

The SEC gets $ 1.1m case when Crypto Schemer crosses the court.

June 7, 2025

NFT artists reproduce ‘password tax nightmares’ with new songs.

June 7, 2025

NVIDIA’s GB200 NVL72 and Dynamo improve MoE model performance

June 7, 2025

Despite market volatility

June 7, 2025

TEZOS promotes scaling efforts by activating data soluble layers.

June 7, 2025

It shows a graphite network. Tesla is nothing without trust because Tesla’s Tesla spent $ 150 billion after Musk and Trump’s fallout.

June 7, 2025

The merchant warns that Bitcoin is in ‘cancer price behavior’.

June 7, 2025

Is Bitcoin Price Rally $ 150K by the end of the year?

June 7, 2025

How does it affect Bitcoin?

June 7, 2025

Crypto Flexs is a Professional Cryptocurrency News Platform. Here we will provide you only interesting content, which you will like very much. We’re dedicated to providing you the best of Cryptocurrency. We hope you enjoy our Cryptocurrency News as much as we enjoy offering them to you.

Contact Us : Partner(@)Cryptoflexs.com

Top Insights

Solana Whale will not announce $ 17 million in four years. Should I worry?

June 7, 2025

HOLONYM’s Human Network: Convert on boarding on boarding on human -friendly keys

June 7, 2025

The SEC gets $ 1.1m case when Crypto Schemer crosses the court.

June 7, 2025
Most Popular

WBTC address addicts return almost all funds to their victims after negotiation.

May 11, 2024

CHAINOPERAAI and Render Network collaboration explores decentralized AI and Web3 integration.

February 15, 2025

OKX Launches Perpetual Futures for NOT Crypto

May 16, 2024
  • Home
  • About Us
  • Contact Us
  • Disclaimer
  • Privacy Policy
  • Terms and Conditions
© 2025 Crypto Flexs

Type above and press Enter to search. Press Esc to cancel.