PulseAugur
EN
LIVE 18:27:50

Perplexity optimizes Search as Code, cutting costs by 10%

By PulseAugur Editorial · [3 sources] ·

Perplexity has announced significant optimizations to its Search as Code (SaC) system, which was initially released in June. These updates aim to further enhance performance and reduce the cost per task by nearly 10%. The company also reported improvements in the reliability of its Search SDK updates within the 'Computer' environment, raising execution reliability from 81.9% to 92.6%. These advancements are expected to translate into higher user satisfaction and more capable orchestration across various real-world user workflows. AI

IMPACT These optimizations could lead to more efficient and cost-effective AI agent development and deployment.

RANK_REASON Product update and optimization announcement for an existing tool.

Read on X — Perplexity →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Perplexity optimizes Search as Code, cutting costs by 10%

COVERAGE [3]

  1. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    These improvements show up across a wide range of real-world user workflows.

    These improvements show up across a wide range of real-world user workflows. In Computer, SaC optimizations delivered higher user satisfaction at an 8% lower per-task cost. https://t.co/RrVBvesoYE

  2. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    How an SDK is shaped determines how well models can use it.

    How an SDK is shaped determines how well models can use it. We’ve rolled out two batches of Search SDK updates within Computer, raising execution reliability from 81.9% to 92.6%. More reliable action execution enables more capable orchestration. https://t.co/5nNFNUrciD

  3. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    We released Search as Code (SaC) in June, achieving state-of-the-art performance on wide and deep research.

    We released Search as Code (SaC) in June, achieving state-of-the-art performance on wide and deep research. This week, we’re rolling out optimizations to SaC that further improve performance while cutting cost per task by nearly 10%. https://t.co/58Caylqbsy

RELATED ENTITIES

RELATED TOPICS