Graphistry

GraphThePlanet is excited to announce another featured speaker for 2026: Justin McCarthy, Co-Founder & CTO of StrongDM Talk Topic: Software Factories Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. 🔴 Watch live on YouTube and LinkedIn Event Details: • Date: March 23, 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com Happy graphing, — The Graphistry Team #CyberSecurity #AI #RSAC2026 #GraphThePlanet #DevOps #PlatformEngineering #SoftwareEngineering

GraphThePlanet is excited to announce another featured speaker for 2026: @joshua_saxe , Former AI Security Lead (Stealth, ex-Meta) Talk Topic: Evaluating and Hill Climbing Efficacy in Cyber Defense Agents Joshua will dive into how to measure and improve the performance of cyber defense agents, focusing on practical evaluation methods and iterative approaches to make systems more effective over time. Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. 🔴 Watch live on YouTube and LinkedIn during #RSAC2026 week Event Details: • Date: 23 March RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com Happy graphing, — The Graphistry Team #AIforSecurity #AgenticAI #GenerativeAI #InfoSec #SecurityAI #RSAC2026 #GraphThePlanet

GraphThePlanet is excited to announce another featured speaker for 2026: DianaDamenova, Security Researcher at @Microsoft Talk Topic: Lifting Knowledge Graphs from Security Logs (Without ETL) Diana will show how to turn raw security logs into usable knowledge graphs without heavy ETL pipelines, enabling faster investigation workflows and more flexible analysis across large-scale data. Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. 🔴 Watch live on YouTube and LinkedIn during #RSAC2026 week Event Details: • Date: March 23, RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com Happy graphing, — The Graphistry Team #GraphThePlanet #GTP2026 #RSAC2026 #KnowledgeGraphs #CyberSecurity #SecurityAnalytics #GraphIntelligence #DataEngineering #AIforSecurity

GraphThePlanet is excited to announce another featured speaker for 2026: David Cass, CISO at @keyrock 🗣 Talk Topic: AI Safety in Regulated Enterprise Deployments David will share how regulated organizations are approaching AI safety in production from risk management and controls to what it takes to deploy AI systems responsibly in high-stakes environments. Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. 🔴 Watch live on YouTube and LinkedIn during #RSAC2026 week Event Details: • Date: March 23, 2026 RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com Happy graphing, — The Graphistry Team #GraphThePlanet #GTP2026 #RSAC2026 #AISafety #ResponsibleAI #CyberSecurity #EnterpriseAI #RegTech #GraphIntelligence

Splunk BOTS CTF is Dead The Louie.ai AI team has now solved Boss of the SOC, and we uncovered something important along the way - First, the Louie.ai team has built an AI agent that autonomously solves every challenge in Splunk’s Boss of the SOC CTF. For those new to our work, we initially went public around this time last year, sharing the first public autonomous AI agent to achieve a passing score. Our video on beating BOTS (link below) resonated widely because BOTS is one of the most realistic SOC/IR investigation CTFs, with 100+ data sources and 50+ questions covering core workflows like timelining. This year, we autonomously cleared all the challenges. Our latest stats: ~96% accuracy ~1 minute median per question Getting an A+ is a meaningful step forward. It doesn’t mean investigations are “solved,” but it does signal it’s time to raise the bar again. What drove our latest gains comes down to two themes we’ve been pushing on: ◼️ Advancing agent techniques around context engineering and tool use for data-heavy scenarios ◼️Shifting the mindset from an AI coder to a professional analyst Intuitively, AI agents investigate better when they act like professional analysts, not chatbots or AI coders. The second takeaway came from evaluating these systems: AI investigation benchmarks are starting to break As benchmarks circulate more widely, we’re seeing clear signs of benchmark contamination in frontier models on BOTS-style tasks. That makes it harder to measure real progress — and harder to meaningfully compare models and agents. To address this, we’re launching BotsBench: ◼️Vendor-neutral benchmarking for agent and model performance ◼️Standardized runs on operationally relevant challenges (starting with BOTS) ◼️Leaderboard across models and agents Open submissions: submit your agent — we’ll run it and publish results Our goal: make AI investigation systems measurable, comparable, and harder to game 🔴 If you’re building agents, submit yours and check the leaderboard: botsbench.com We’ll share more on how this works — and where it’s going — on Monday at our Security x AI summit (Graph the Planet 2026). Join online or grab one of the final in-person spots. #AIAgents #CyberSecurity #SecOps #AIinSecurity #ThreatDetection #LLM

GraphThePlanet is excited to announce another featured speaker for 2026: @dawnsongtweets , Professor at @UCBerkeley Talk Topic: Towards Building Safe & Secure Agentic AI Dawn will share perspectives from leading research on how to design and deploy agentic AI systems that are secure by default, with a focus on real-world risks, safeguards, and what it takes to make these systems reliable in practice. Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. 🔴 Sign up to watch live on YouTube and LinkedIn Event Details: • Date: March 23, 2026 RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com Happy graphing, — The Graphistry Team #GraphThePlanet #GTP2026 #RSAC2026 #AgenticAI #SecureAI #AIResearch #CyberSecurity #TrustworthyAI #GraphIntelligence

Benchmark - 50x+ speedups with GFQL Cypher: pygraphistry.readthedocs.io/en/latest/gfql… GTP 2026: graphtheplanet.com

You can now run Cypher without a database - and 50× bigger & faster. Just directly query your dataframes and go. Last year, Graphistry announced GFQL, the first open source GPU property graph query engine. This year, we've brought it to Cypher. Think of GFQL as what Pandas, DuckDB, or Spark do for tabular analytics, dashboards, and ML - but now for graph-shaped data like networks, relationships, and paths. The new GFQL support brings massive performance, cost savings, and architectural freedom for the most widely used graph query language used by half the Fortune 500. GFQL Cypher is the latest member of the @ApacheArrow and @NVIDIAaidev @RAPIDSai OSS ecosystem. We will announce more at GTP 2026 (RSAC week in SF + livestream) and are happy to chat directly Notebook is linked below so you can try for yourself.

GraphThePlanet is excited to announce another featured speaker for 2026: @daveherrald , Global Head of Cyber GTM at @databricks Bad Actors: Building Realistic Security Eval Data with Agentic AI Dave will explore how agentic AI can be used to generate realistic adversarial scenarios and evaluation data, helping security teams better test, benchmark, and improve their defenses. Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. Event Details: • Date: March 23, 2026 RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com #GraphThePlanet #GTP2026 #RSAC2026 #CyberSecurity #AgenticAI #SecurityAI #SecurityTesting #AIforSecurity #GraphIntelligence

GraphThePlanet is excited to announce another featured speaker for 2026: @aminkarbasi , Sr. Director of AI Research at @Cisco Talk Topic: Foundation-sec-8B-Reasoning: The First Open-weight Security Reasoning Model Amin will present new work on open-weight reasoning models designed specifically for security use cases, exploring how specialized models can support more capable analysis and investigation workflows. Join executives, senior practitioners, researchers, and startup founders for discussions on AI, graph intelligence, and data-driven investigations. We’re also hosting a small number of in-person Graphistry trainings during the week, including AI for Security: From Copilot to Commander and the Graph Masterclass: Digital Crime Edition. Event Details: • Date: RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: graphtheplanet.com • Trainings: louie.ai/trainings Happy graphing, — The Graphistry Team #GraphThePlanet #GTP2026 #RSAC2026 #AIResearch #SecurityAI #ReasoningModels #OpenWeights #GraphIntelligence #CyberSecurity

GraphThePlanet is excited to announce our featured speaker for 2026: Shruti Datta Gupta, @thisisSDG Product Security Engineer at @AdobeSecurity Guidance as a Service: Building an AI-Native Blueprint for Defensive Security Shruti will share how security teams can build AI-native systems that continuously deliver actionable guidance to developers and defenders, turning security knowledge into something that scales across organizations. Join executives, senior practitioners, researchers, and startup founders for discussions on #AI, #graph intelligence, and data-driven #investigations We’re also hosting in-person trainings during the week, including AI for Security: From Copilot to Commander and the Graph Masterclass: Digital Crime Edition. Event Details: • Date: RSAC Week 2026 • Location: San Francisco, CA • Registration & More Info: lnkd.in/eWR6J-RG • Trainings: louie.ai/trainings #GraphThePlanet #GTP2026 #CyberSecurity #AIforSecurity #ResponsibleAI #ProductSecurity #GraphIntelligence #DataDrivenSecurity #SecurityInnovation #AIOps #DigitalCrime #CyberDefense #SecurityLeadership

Episode #3 of AI Investigation Power Hour is starting soon: How Security Data Lakes Change Security Agents Hosts @lmeyerov , Founder of @Graphistry, and @haandkle_42, Solutions Architect and former police officer, will be joined by @daveherrald Dave Herrald, Global Head of Cyber GTM at @Databricks They’ll discuss how modern security data lakes are changing how security agents are built, deployed, and used in investigations 📷 Watch live on LinkedIn and YouTube: youtube.com/live/IeSHYZw_0… 📷 March 9, 2026 📷 9:30–10:30 AM PDT Full replay will also be available on YouTube and major podcast platforms

OK, now everything is starting to look like what I have had in my mind for so long! Volatility module output normalized, ingested into Neo4j, and then visualized in @Graphistry 😍 Nodes colored by Louvain community. Need to run this on a memdump of an infected machine next!

We are happy to share that Graph the Planet 2026 is back in SF for RSAC week, this year in proud partnership with @BloombergBeta , @Graphistry / Louie.ai, and @AnChainAI ! Graph the Planet is a special AI x Security event where we flip the signal vs noise ratio by bringing together select leaders working at the edge of investigation workflows, AI, and the technology around them. Connect with executives, senior analysts, deep technology makers, researchers, and startup founders for a day of practical discussions, food, and great company. We’re changing things up this year in a couple ways: 1. The program shifts again to match AI’s continuing evolution. Teams are deploying agentic AI in production and maxing out their AI token subscriptions as they use AI coding tools for far more than just coding. In their goal to make trustworthy autonomous flows on one side and expert human-in-the-loop ones on the other, advanced teams are building systems that investigate, reason across data, run on local fine-tunes, and overall reinventing how their systems and teams work together. Meanwhile, in the graph world, agentic memory and retrieval are outpacing traditional RAG, and doing this by leveraging automatic knowledge graphs running on in-memory graph technologies. Security teams are busy working on both sides, simultaneously using these ideas to be vastly more productive and unblock age-old problems, but are also struggling to enable safe rollouts of AI across the organization. As usual, expect far-reaching technical insights, case studies, live demos, hands-on opportunities, news, and network opportunities as we head deeper into 2026. 2. NEW for 2026: Two hands-on masterclasses during RSAC week Inspired by attendee requests on getting started, and successfully helping run the most popular training at Black Hat 2025, this year adds in-person training days: Masterclass on AI Agents and RAG for Security Automation and Investigations Graph Investigation Masterclass: Practical visual graph intelligence for complex investigations Event Details: Date: April 28, 2026 - daytime event + evening reception Location: Bloomberg R&D Tech Hub, San Francisco, CA (1.5 blocks from Moscone) Registration & website: lnkd.in/g-XP5jzr Interested in speaking or sponsoring? Visit the website for details.

Back by demand, announcing the next Graphistry Trainings: “AI for Security - From Copilot to Commander” and “Graph Masterclass: The Digital Crime Edition” We’re opening registration for the next round of Graphistry trainings, building on the most popular session at Black Hat USA and our highly rated online version, and by the team who performed the first autonomous agent speed run of an open SOC CTF. AI for Security: From Copilot to Commander (16 CPEs) Two days of instructor-led sessions, labs, and discussion on moving from copilots to agents that can plan, act, and explain. Covers foundations through hands-on work, including an AI cyber range and investigation CTF you’ll speed-run using your own agents (Splunk or Databricks). Dual tracks: prompt-only and hands-on Python. Grounded in use cases from SOC/IR/Hunt/VM and other security teams, topics include LLM foundations, RAG, workflows vs agents, planning, MCPs & SKILLs.md, working with databases and large data, and trustworthy AI & governance. Graph Masterclass for Digital Crime (8 CPEs) One intensive day focused on turning any tabular data into graphs that answers complex relationship questions as you learn to better leverage graph visualization, search, analytics, and ML/AI. Learn how to reason about graph questions, how to use them across tasks, architectures, and teams, and steadily throughout the course, how to apply them to real problems in cybersecurity, synthetic identity, fraud/AML, OSINT, and supply-chain risk. Hands-on GPU-accelerated workflows included. Who it’s for Recent participants included MSSP CEOs, public-company security leaders, startup founders, top military & law enforcement officers, security analysts, threat hunters, and solution architects for top 3 cloud companies. Our instructors build, use, and partner on these systems daily, from large-scale cyber investigations to billion-dollar fraud and litigation work to frontline SOC/IR operations. The format is deliberately interactive and peer-driven. How to attend Virtual (February): AI for Security offered in both US/Americas and a new EU/Asia time slot In-person (March in San Francisco): Full in-person editions of both trainings colocated with Graph the Planet 2026 summit during RSAC / BSidesSF week Vendor-neutral, tool-agnostic, and designed to translate immediately to your environment. Early-bird and group discounts available. #upcoming-training" target="_blank" rel="nofollow noopener">louie.ai/events/ai-agen…

As I work with more investigation team leaders across genAI deployments and our AI-for-security trainings, a consistent phase change shows up in senior conversations. Early on, teams focus on mapping problems to tools - workflows vs agents, copilots vs automations. Once the landscape is familiar, the discussion shifts. Tools still matter, but now through a bigger lens: how to scale AI responsibility safely, and what that implies for organizational transformation and compounding AI loops. The core question is simple: What decisions is the AI authorized to make, and what stays with the human? Decisions here shape the trajectory, starting with what’s feasible today and into how that capability will expand over time. Agents are the most powerful option today, which makes them the strongest ROI draw - and also operationally delicate. They demand real care. It’s easy to look at a manual process and say, “Let’s offload this to an agent.” But the moment the operator is removed, the required assurance jumps sharply. Teams naturally respond by clamping these systems down. They need a safe starting point where they can incrementaly grow use-case-level authority, most likely through observing behaviors and controls. Because this progression takes time and investment that most AI vendors don’t provide, many deployments get pushed into read-only reporting: a few AI steps used for alerting, triage, correlation, or summarization. Useful, but constrained. Vibes investigating lands in a different bucket. High-quality agents can investigate surprisingly far with read-only access. When judgment or action matters, the human is already there.Analysts sanity-check, dig deeper, approve next steps, and repeat — allowing investigation to go arbitrarily far without crossing unsafe responsibility boundaries. In security and safety-critical fields we worry about humans as liability sponges; for vibe AI systems, that’s a feature, not a bug. It’s the same dynamic that made vibe coding take off so quickly, now applied to data instead of code. Traditional RAG chatbots are unbalanced in where they place responsibility, which helps explain the continuing decline in ROI stories. They fetch data and reduce hallucinations, but they don’t decide what to do next. Serious agent systems still retrieve data too - the difference is whether the system can choose tools, sequence queries, and know when to return control to a human. Better responsibility placement wins the game. The second mistake teams make is treating genAI as a one-time tool decision instead of a long-living program. Teams on critical paths don’t jump straight into unbridled autonomy. Real paths look more like: read-only investigation → supervised runs → longer qualified loops → selective autonomy. Each transition requires higher assurance, better instrumentation, and tighter feedback. The need to scale responsibility is why I’m optimistic about teams starting with vibes investigating and fast following with simple automations. Analysts stay close to the data, surface failure modes early, and define guardrails. That’s how agents earn longer run budgets and expanded authority. As investigation flows harden into patterns, they become candidates for automation, and the AI loop gets to expand. Next time a discussion gets stuck on “AI workflows vs agents” or “copilots vs automation”, it helps to zoom out. The end state is AI taking on more responsibility - and yes, that currently means agents. The bigger question is how fast that responsibility can expand without breaking guarantees, and what is that path. (Bonus: This topic repeatedly came up in our latest AI x Security training, and we just announced are next Americas + EU/Asia cohorts, link below.) #upcoming-training" target="_blank" rel="nofollow noopener">louie.ai/events/ai-agen…

We’re excited to share that our Solutions Architect, Sindre Breda, will be taking the stage today at the Nordic Splunk User Conference 2026 in Oslo 🇳🇴 His talk will cover Graphistry and how Louie.ai speedran the BoTS, dives into how our AI, Louie.ai, tackled and speedran the Boss of the SOC challenge showing how graph-powered investigations and agentic workflows can dramatically accelerate detection, triage, and response. If you’re attending, don’t miss it: 🗓 Today, Jan 16 📍 Technical Museum, Oslo 🎯 Session: 13:00–13:50 GTM+1 After the session, come say hi to Sindre Breda and the team. And if you’re curious about building your own AI for cybersecurity, check out our Louie.ai early access and our hands-on trainings at louie.ai. Whether you’re new to Splunk or a seasoned power user, this conference is shaping up to be two packed days of learning, networking, and great conversations. See you in Oslo! #Splunk #NordicSplunk #AISOC #AIAgents #GraphRAG #Cybersecurity #SecurityAutomation #Graphistry #LouieAI

If you couldn’t make it to the 39th Chaos Communication Congress in person, the talks are now available online. Our CEO, Leo Meyerovich, presentation “Breaking (Splunk) BOTS: How We Cheated at Blue Team CTFs with AI Agent Speed Runs”, walking through how we used AI agents and graph workflows to outperform traditional blue team approaches with real results. Livestream + ReLive recordings streaming.media.ccc.de/39c3/