Deductive AI的封面图片
Deductive AI

Deductive AI

软件开发

Mountain View,California 1,215 位关注者

关于我们

Deductive AI is building an AI Engineer that can help root-cause and mitigate large-scale software outages by reasoning about distributed systems, code, and statistical anomalies in real-time across unprecedented volumes of structured and unstructured data. We’re a team of 10 engineers with decades of experience in building and maintaining large-scale production systems at Databricks, Facebook, Thoughtspot, Google, Splunk, and Amazon. Currently in Stealth.

网站
https://www.deductive.ai
所属行业
软件开发
规模
2-10 人
总部
Mountain View,California
类型
私人持股
创立
2023

地点

  • 主要

    321 Castro St

    US,California,Mountain View,94041

    获取路线

Deductive AI员工

动态

  • Deductive AI转发了

    查看Sameer Agarwal的档案

    Co-Founder & CTO @ Deductive AI | Ex-Databricks | Ex-Facebook

    It was a pleasure speaking at the infra.sf meetup last week about the future of AI-driven observability. What made the experience even more meaningful was the opportunity to share the stage with Charity Majors, an engineering leader I greatly respect for her deep insights and compelling articulation. At Deductive AI, we’ve been running AI-powered agents for root cause analysis (RCA) in production for over a year and have gained some good insights along the way. While I couldn’t cover all our learnings in a short talk, I shared three design patterns with the audience that I feel can be applied to most domain-specific agentic workflows: 1. Search as the Core Primitive – Many people may not think of it this way, but RCA is fundamentally a search and query problem across structured, semi-structured, and unstructured data -- often with extremely high cardinality and dimensionality. Effectively searching across this data requires building and maintaining rich search indices that track relationships across metrics, attribute keys, values, log patterns, and code metadata. Without this, even the most advanced AI systems struggle with signal correlation and causal inference at scale. 2. Using Approximations When Possible – Humans naturally excel at eyeballing/approximations; machines do not. This gap is especially evident in observability, where the exact precision of data often matters less than detecting the presence or absence of anomalies. At scale, exhaustively analyzing every log line, metric and trace is impractical. We found that structured sampling -- leveraging entropy, anomaly scores, and cluster similarity -- is a great tool for preserving statistical significance while filtering noise. 3. Code as a First-Class Telemetry Index – We found that leveraging code to search for telemetry data significantly improves RCA. Unlike natural language, code has strict syntax, execution rules, and lower entropy, making it easier for (fine-tuned) language models to learn and predict failures. We often find that starting our investigation by retrieving/understanding code and then using it to correlate logs, traces, and metrics, significantly improves RCA by aggressively pruning the search space. These are just a few of our learnings, but there’s obviously so much more to this. If you’re also building domain-specific agents, I’d love to hear what’s worked for you -- and what hasn’t!

    查看Megan Reynolds的档案

    vvus.com vc | infra.community founder

    It was standing room only for best SRE leaders in SF to learn if they would still have a job in 5 years ?? Last week in SF we packed out the Convex office with the brightest minds in software infrastructure to hash out the future of observability over beer and pizza ???? AI is creating a tectonic shift in the way we monitor and debug systems - in 5 years does the SRE role still exist or will developers own the work with an SRE copilot? ?? Talks from these infra MVPs got the audience of engineering leaders buzzing: ??Sameer Agarwal?- CTO & Co-Founder,?Deductive AI?"building AI-Powered SRE Agents" ??Achille Roussel?- CTO & Co-Founder,?Firetiger?“streaming opentelemetry signals into iceberg“ ??Charity Majors?- CTO & Co-Founder,?honeycomb.io?“physics of computing will kill your pillars” The following discussion with engineers from the early days of Slack, Segment, Databricks and SRE leaders from Netflix, Cloudflare, Stripe made it clear that there is an exceptionally high bar for full automation to be trusted (unlikely within 5 years) but all are testing new AI tools for SREs and developers ?? I'm going to share more learnings from this group and more on where the o11y market is moving and the new opportunities emerging for startups and incumbents - watch this space! Sign-up link in the comments to join this group next time in SF or NYC ??

    • 该图片无替代文字
    • 该图片无替代文字
    • 该图片无替代文字
    • 该图片无替代文字
    • 该图片无替代文字
      +1
  • Deductive AI转发了

    查看Sameer Agarwal的档案

    Co-Founder & CTO @ Deductive AI | Ex-Databricks | Ex-Facebook

    As we wrap up an incredible year at Deductive AI, I want to take a moment to wish everyone a joyful and relaxing holiday season! We’re extremely grateful for an amazing year in which we doubled the size of our team, turned what was initially just a prototype (and a whiteboard idea) into a cutting-edge product defining the future of code-aware observability, and collaborated with some of the best and brightest minds in the industry and academia along the way. To our users -- thank you for putting your trust in us; your support and feedback fuels everything we do. To our investors -- your belief in our vision means the world. And to our growing team -- your passion and dedication inspire us every day! Here’s to an even more exciting and transformative 2025. Happy Holidays!

    • 该图片无替代文字
    • 该图片无替代文字
    • 该图片无替代文字
  • 查看Deductive AI的组织主页

    1,215 位关注者

    We're excited to welcome Ezra Stuetzel to Deductive AI as our newest Founding Software Engineer! Ezra brings over a decade of experience in software engineering, including key roles at two successful startups (RiskIQ and Appia-A part of Digital Turbine) and top-tier tech companies (Salesforce and Meta). His expertise spans distributed systems, scalable data solutions, and machine learning applications. Ezra has a proven track record of designing innovative systems, enhancing platform stability, and solving complex engineering challenges. At Deductive, we're building cutting-edge solutions at the intersection of AI, code and observability, and his deep experience and entrepreneurial spirit make him a perfect addition to our team. Welcome, Ezra!

    • 该图片无替代文字
  • 查看Deductive AI的组织主页

    1,215 位关注者

    We're extremely excited to welcome Arash Parsa to Deductive AI as our newest Founding Software Engineer! Arash joins us from Google Infra Spanner, where he was a tech lead on critical Spanner serving infrastructure projects and debugging rotations. Before Spanner, Arash spearheaded and led the development of the Cloud Firestore Key Visualizer from inception to launch for some of the largest GCP customers, in addition to other key contributions to GCP’s hotspot detection technologies. Today, the Key Visualizer for Firestore is an invaluable observability feature that is heavily relied upon by GCP customers for debugging and maintenance of their services! Before Google, Arash was a tech lead manager at Radius Intelligence working in the predictive data and ML space. He spent his undergraduate and graduate years at the University of California, Berkeley. At Deductive AI, we are solving some very hard/interesting problems in the area of code-aware observability, with a focus on building multi-agentic flows that can reason on extremely large amounts of data and code. If you are exceptional at what you do and are passionate about problems at the intersection of data and AI, please drop us a note!

    • 该图片无替代文字
  • Deductive AI转发了

    查看Pratyush Verma的档案

    Founding Engineer @ Deductive AI | ex-(Meta, Flipkart, Grab)

    Excited to share we are on a lookout for rockstar interns at Deductive AI. The role is based out of the London office in Camden. You will be working directly with me, while collaborating with the rest of the founding team in Mountain View. Apply here if you would like to work on Foundational AI, Agentic Systems and advanced data processing. https://lnkd.in/esHSd-xs

  • Deductive AI转发了

    查看Sameer Agarwal的档案

    Co-Founder & CTO @ Deductive AI | Ex-Databricks | Ex-Facebook

    As the summer season wraps up, very excited to share that we're looking for a couple of exceptional fall interns at Deductive AI in Mountain View, CA. This is a paid, hands-on role where you'll work directly with me and our founding team on building the next generation of AI and data processing systems that can understand and reason about vast amounts of data and code. In the past, our interns have worked on some core problems around search and retrieval of structured and unstructured data, LLM evaluations, and reasoning over code & logs, making a direct impact on building Deductive from the ground up. Please apply here:

  • Deductive AI转发了

    查看Madeline Cripps的档案

    Founding Software Engineer at Deductive AI

    Excited to share that we're on the lookout for a talented front end / product engineer to join our team at Deductive AI! Previous experience with React is a plus, but not required. If you’re interested in working on a product at the intersection of Observability, AI, and data visualization, drop me a note to learn more.

  • Deductive AI转发了

    查看Sameer Agarwal的档案

    Co-Founder & CTO @ Deductive AI | Ex-Databricks | Ex-Facebook

    Excited to share that we're looking for a few rockstar summer and fall interns at Deductive AI in Mountain View, CA. This is a very hands-on role where you'd be working directly with me and our amazing founding team on building the next generation of foundational AI and data processing systems that can reason on extremely large amounts of data and code.

  • Deductive AI转发了

    查看Sameer Agarwal的档案

    Co-Founder & CTO @ Deductive AI | Ex-Databricks | Ex-Facebook

    A great article by Joanne Chen and Jaya Gupta from Foundation Capital discussing the service-as-software model (SaaS v2?) and highlighting the $4.6T TAM opportunity in this area: https://lnkd.in/gTWgU6mt. We’re very grateful for their nod to Deductive AI as one of the key future players in this area. It’s also a privilege to share this space with several amazing companies in the AI-powered code generation space that we deeply respect. With the rise in popularity and adoption of GitHub copilot, Codeium, Cognition, and other powerful tools, it would not be unreasonable to imagine that the amount of software products developed in the next decade will be orders of magnitude greater than those built in the previous one (in the famous words of Andrej Karpathy, “The hottest new programming language is English”). However, at the same time, if generative models are helping write large parts of this code, our software will become more opaque over time, making it increasingly difficult for engineers and on-calls to have complete context to root causes and mitigate outages. Looking forward to seeing how root-causing and the on-call models evolve as a result of this fundamental paradigm shift in the next few years, and humbled to play a small part in defining this future!

    • 该图片无替代文字

相似主页

查看职位