New in week 43

Full-stack observability for AI applications, LLMs and agents, covering performance, cost, quality and compliance

Monitor the performance, usage, cost and guardrails of LLM and agentic AI apps in Elastic Observability

Guardrails, red teaming and risk management platform for securing AI applications and agents.

Guards AI models, apps and agents against prompt injection, data leakage and harmful outputs.

Control plane for enterprise AI agents covering monitoring, evals, enforcement and governance

AI observability and eval engineering platform where offline evals become production guardrails

Enterprise service for objective evaluation of generative AI models using adaptive and static rubrics

Google Cloud service that screens LLM prompts and responses for prompt injection, sensitive data and harmful content.

OpenTelemetry-native observability for LLMs, vector databases, GPUs, MCP servers and AI evaluations in Grafana Cloud

Active behavior assessment and runtime enforcement for AI agents, built on adversarial red teaming research.

Trust platform for voice and chat agents: pre-launch testing, red teaming and production monitoring

Security platform for AI covering asset discovery, supply chain checks, attack simulation and runtime defense.

Connects prompts, model calls, tool use, cost and failures to help debug LLM apps and agents in production

Agent observability platform for tracing, evaluating, monitoring and improving AI agents

Platform to discover, protect and govern AI agents and AI interactions, with runtime enforcement

Automated red teaming for AI apps and agents that tests for safety, security and responsible AI failures.

Security for AI agents at enterprise scale: runtime protection for every agent you build and deploy

Meta's open classifier models that detect prompt injection and jailbreak attacks on LLM inputs.

Framework that detects and mitigates AI-centric security risks in agents and LLM applications.

Platform for developers of AI chatbots and LLM apps, covering monitoring, prompts and analytics

End-to-end platform for simulating, evaluating and observing AI agents and applications

Attack-led AI security platform that finds, validates and helps fix vulnerabilities in AI systems and agents.

APM-based AI monitoring for end-to-end visibility into the performance, cost and quality of LLM apps

Agent security and governance platform that controls agent behavior at runtime across endpoint, SaaS and cloud.

Simulation and evaluation platform that tests voice and text agents with synthetic users

AI governance platform to discover, test, monitor and govern AI systems and enforce controls

Real-time semantic firewall and gateways that allow, block or redact AI agent actions and MCP traffic.

Discovers, tests, secures and governs every AI agent in an organization from one platform.

Traces every LLM call in your AI product, with prompt, tokens, cost, latency and the user who triggered it

AI security platform covering discovery, assessment, runtime protection and governance of AI apps and agents

Platform for governing AI tool use, securing agents and protecting AI applications in real time

Collaboration layer for AI engineering teams: prompt management, agent observability and evals

Guardrails, evaluation and pre-production red teaming for AI agents, RAG apps and chatbots.

Monitoring platform for AI agents that discovers silent agent failures in production

Enterprise platform for AI asset discovery, red teaming and runtime security across agentic workflows and MCP.

AI router with built-in observability, automated evals and red-teaming for agent runs

AI quality platform for developers that builds evaluators, guardrails and monitoring for LLM applications

Simulation platform for building frontier AI agents, testing them on realistic scenarios with evals

AI observability in Sentry for tracing and debugging agent runs, tool calls, token usage and errors

Unified platform to test, protect and govern AI, covering red teaming, runtime guardrails and AI asset discovery.

Discovers AI agents, MCP servers and skills, tests them adversarially and blocks attacks at runtime.

Security and governance platform for employee and agent AI use, covering visibility, controls and runtime protection.

Secures AI agents by discovering them, enforcing policy on their actions and detecting threats at runtime.