Log inSign up
TensorZero
273 posts
Image
user avatar
TensorZero
@TensorZero
NYC
github.com/tensorzero/ten…
Joined October 2023
2
Following
1,357
Followers
  • Pinned
    user avatar
    TensorZero
    @TensorZero
    Mar 23
    We’re building TensorZero Autopilot, an automated AI engineer that analyzes LLM observability data, optimizes prompts and models, sets up evals, and runs A/B tests. It dramatically improves the performance of LLM agents on every single benchmark we’ve tried. Read more below.
    Image
    9.4K
  • TensorZero reposted
    user avatar
    Kristian Ernst
    @_kristianernst
    Jun 7
    Just wanted to give a huge shoutout to @TensorZero! you guys have really done an amazing job. De facto recommendation on every client project we work on right now.
    940
  • TensorZero reposted
    user avatar
    Michelle
    TensorZero
    @michellehui
    Jun 3
    it was a full house last night! (pun intended) inaugural @TensorZero ai poker night co-hosted with @BessemerVP
    Image
    Image
    Image
    Image
    509
  • TensorZero reposted
    user avatar
    Gabriel Bianconi
    TensorZero
    @gabrielbianconi
    Jun 3
    🃏 Great time last night at @TensorZero's inaugural AI Poker Night co-hosted with @BessemerVP!
    Image
    Image
    Image
    Image
    392
  • user avatar
    TensorZero
    @TensorZero
    May 18
    You might be overpaying 5.3x+ for Claude Opus 4.7! Our CEO @gabrielbianconi found out that on tool-heavy workloads, you're paying 5.3x more for Claude Opus 4.7 than GPT 5.4. The common metric is to compare cost per million tokens. But different providers use different
    Image
    00:00
    1.8K
    user avatar
    TensorZero
    @TensorZero
    May 18
    Image
    Stop comparing price per million tokens: the hidden LLM API costs · TensorZero
    From tensorzero.com
    198
  • user avatar
    TensorZero
    @TensorZero
    May 12
    LLM evaluators are often noisy and weakly correlated with real-world outcomes. Noisy evaluators have limited value for production decisions that hinge on judging a single output (e.g. guardrails). However, even (very) noisy evaluators can reliably tell you which agent is better
    Image
    639
    user avatar
    TensorZero
    @TensorZero
    May 12
    Image
    Even (very) noisy LLM evaluators are useful for improving AI agents · TensorZero
    From tensorzero.com
    147
  • user avatar
    TensorZero
    @TensorZero
    May 11
    Michelle Hui is joining us with a focus on developer relations. She recently graduated from Cornell with BS & MS degrees in computer science, during which she organized large tech events, conducted ML research, and held product internships (Alphabet / Wing, UN). Welcome to the
    Image
    2.7K
  • user avatar
    TensorZero
    @TensorZero
    May 5
    "If your security relies on your code being obfuscated, you're telling yourself a fake story." Our CTO Viraj Mehta (@thebigmehtaphor) chats about AI scaling, open source, and being a technical founder following his PhD in Reinforcement Learning at CMU. In our in-depth
    Image
    00:00
    1K
    user avatar
    TensorZero
    @TensorZero
    May 5
    192
  • user avatar
    TensorZero
    @TensorZero
    Apr 28
    TensorZero is committed to open source. We sit down with our CTO Viraj @thebigmehtaphor. Takeaways: 1. Thinking closed-source code == security is a LIE. You still need to build from first principles and fundamentally secure code. 2. Open-source keeps more eyes on your code,
    Image
    00:00
    264
  • user avatar
    TensorZero
    @TensorZero
    Apr 16
    Article cover image
    Article
    Stop comparing price per million tokens: the hidden LLM API costs
    Summary Token pricing is misleading: the same input produces 2.65x+ more tokens depending on the model. We got wildly different token counts from identical content using OpenAI, Anthropic, and...
    1.3K
  • user avatar
    TensorZero
    @TensorZero
    Mar 25
    Can an automated AI engineer autonomously debug and optimize an LLM pipeline in 5 minutes? Last night, ours did: it cut errors in ~half during its first live demo. TensorZero Autopilot (our automated AI engineer) analyzed hundreds of historical LLM traces to identify failure
    Image
    Image
    3.3K
    user avatar
    TensorZero
    @TensorZero
    Mar 25
    Learn more: tensorzero.com/blog/automated…
    Image
    236
  • user avatar
    TensorZero
    @TensorZero
    Mar 23
    Replying to @TensorZero
    Read more about this work on the TensorZero Blog:
    Image
    We're building an automated AI engineer, and it works · TensorZero
    From tensorzero.com
    237
    user avatar
    TensorZero
    @TensorZero
    Mar 23
    TensorZero Autopilot is powered by our open-source LLMOps platform that unifies an LLM gateway, observability, optimization, evaluation, and experimentation. The open-source project is used by companies ranging from frontier AI startups to the Fortune 10 and powers ~1% of the
    228

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms of Service|Privacy Policy|Cookie Policy|Accessibility|Ads info|© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up