Topic
All digests tagged Agentic Systems
Suggested route
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Learn how to secure AI agents against the OWASP Top 10 risks. This talk provides practical, layered security models for mitigating goal hijacking, tool misuse, and cross-agent privilege escalation.
Read article
AI attackers move at machine speed, finding 0-days by reversing open-source code. To defend, security must automate remediation, implement forensic-grade detection, and use deception (digital twins) to counter the threat.
Read article
The AI Engineer role is shifting from writing features to building self-improving loops. This requires building always-on agents that consume telemetry, run in durable sandboxes, and are continuously tested using advanced evaluation systems.
Read article
To ensure AI agent reliability, the speaker details a five-step regression loop. This process uses production traces as the source of truth, employing LLMs as judges to quantify subjective metrics and integrating automated gates into CI/CD.
Read article
Joseph Kim details how ChatGPT for Financial Services addresses the 'capability overhang' by integrating proprietary data, firm templates, and interactive tools, setting the stage for proactive, persistent AI agents.
Read article
The session explores the future of AI, from open models to physical AI. Key topics include digital twin simulation, agentic orchestration, and multi-modal generative models like Flux 3 for robotics and manufacturing.
Read article
Nemotron 3.5 Super VL is an open-source, multimodal LLM (120B total, 12B active parameters) that powers specialized agents. It can analyze dashboards and scanned documents to propose code-based cost optimizations.
Read article
Learn how to build a highly accurate RAG assistant for complex financial rulebooks. We cover hybrid retrieval (BM25 + Embeddings), multi-tool agents, and streaming UX for production-grade AI.
Read article
CoreWeave announced CoreWeave Forge, a unified platform for the entire AI loop (Run, observe, curate, improve, evaluate). Key launches include Vera Rubin NVL72 and tools like Agent Lens and Model Distillation, streamlining LLMOps.
Read article
Watch how Gemini 4 Argon and Antigravity reconstruct a photorealistic 3D cathedral in Blender from a flat 2D concept image using the Model Context Protocol (MCP).
Read article
Dyna Robotics uses the Dyna-2 world action model, trained on 1M+ hours of video, to guide physical robots. By combining Diffusion Transformers with agentic harnesses, they achieve general-purpose automation for complex, real-world workflows.
Read article
Learn how to build robust AI agents by mastering hybrid search. This workshop covers combining semantic (vector) and lexical (BM25) search, using ESQL, and implementing advanced reranking techniques in Elasticsearch.
Read article
Reducto is an agentic document platform that turns messy, unstructured documents (scans, handwriting, redacted PDFs) into structured data for AI. It uses a rasterization-based approach and a multi-stage pipeline (Parse, Split, Extract, Edit, Classify).
Read article
A 4B model trained with RL on financial data beat a 235B model on complex tasks. Specialization and simple rewards proved more effective than raw scale for enterprise AI.
Read article
Higgsfield enables developers to build complex, interactive media using agentic systems that self-provision compute and choose optimal models like Astra, democratizing high-end content creation.
Read article
The Software Factory proposes an autonomous system of agents that converts input signals (like bug reports) into production code. The focus shifts from coding to governing agents, emphasizing model-agnostic principles and measuring outcomes like signal-to-production time.
Read article
The Gemini Interactions API handles server-side state and long-running background jobs, replacing user/model turns with a structured timeline of steps. Agents run in a managed cloud sandbox, allowing them to execute code and share persistent environments.
Read article
AI struggles with production because it spans code, infrastructure, and telemetry. To fix this, a robust agentic harness requires six pillars: Model Orchestration, Causal Reasoning, Context Engineering, and more.
Read article
The future of AI infrastructure demands a shift from separated cloud layers to a co-designed stack. Speakers detailed the move from pull-based web search to agent-driven, push-based data consumption, emphasizing the need for GPU-native indexing and robust, holistic security.
Read article
Agent memory is solved, but shared learning across agents is not. The solution requires an agent-native persistence layer (Meko) to promote private memories into governed, shared data packs.
Read article