Managed Deep Agents - Tools
Learn how to add custom tools to your managed deep agent using LangChain. Tools allow agents to interact with external APIs and databases by defining them as decorated Python functions.
Read articleDrishvada technical video digests
Managed Deep Agents - Skills
Skills package task-specific procedures and context into reusable directories. You can define them in markdown files, and they are picked up automatically by the agent.
Read article
Managed Deep Agents - Instructions and Context Hub
Instructions define an agent's behavior and can be managed via the Context Hub. This allows modifying instructions directly in the UI without redeploying code, streamlining agent maintenance.
Read article
Managed Deep Agents - Quickstart
This guide walks through scaffolding and deploying Managed Deep Agents using the MDA CLI. Key steps include defining instructions in `instructions.mmd`, local testing with `MDA dev`, and syncing context to the Context Hub before final deployment.
Read article
Trading Desks to Clinical Trials: Parallels in Applied Vertical AI — Ayush Bhardwaj, Allos AI
Applied vertical AI's true moat is not the model or infrastructure, but proprietary data and domain expertise. The key to success is narrowing the problem scope and integrating human experts into a continuous learning loop.
Read article
Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents — Vasant Kearney, Onlay
X12 should be treated as a structural harness, not just a file format. This approach grounds AI agents in the contract between providers and payers, ensuring reliable claims processing despite contradictory data sources.
Read article
Shipping AI to a Million Patients Without an A/B Test — Jared Joselowitz, Ufonia
Shipping AI safely requires moving beyond A/B testing. The solution involves building an evaluation stack using simulation (Matrix) and automated prompt optimization (Jeppa) to prove safety before patient exposure.
Read article
Guardrails First: Engineering Member-Facing Health AI — Rashi Agrawal, Hinge Health
Building member-facing healthcare AI requires guardrails that are architectural, not just prompt-based. Safety must be built into three foundations: PHI stripping at ingestion, deterministic code layers for high stakes, and continuous monitoring.
Read article
Stateless, Yet Durable: MCP Tasks v2
Cornelia Davis explores MCP Tasks v2, detailing how the protocol achieves durability for long-running workflows while remaining stateless. She contrasts V1's complexity with V2's simplified polling model.
Read article
The MCP Tasks Extension
Learn how the MCP Tasks Extension handles asynchronous, long-running workflows. We compare the 1.120 and 1.720 specs to show how modern protocols enable robust agent swarms.
Read article
MCPs for Observability Stacks
MCP servers enhance observability stacks by integrating AI for proactive monitoring. They correlate metrics, logs, and traces to automate root cause analysis using natural language.
Read article
Agentic DX: Bringing IDP into your IDE
Learn how to solve low IDP adoption by bringing agentic AI directly into the IDE. Discover Master Agent architectures, A2A protocols, and context hygiene techniques for reliable developer experiences.
Read article
MCP Release Overview: Stateless and the Big Changes in the New Spec
MCP is transitioning to a stateless architecture, eliminating session state dependencies. Key updates include Multi Roundtrip Requests (MRTR), formal extensions for UI/Tasks, and enhanced OAuth adherence.
Read article
From Ambient Documentation to Clinical Intelligence — Chaitanya Asawa, Abridge
Abridge addresses the administrative burden in healthcare by building clinical intelligence tools that decompose complex tasks into smaller, specialized models to manage cost and latency at scale.
Read article
What should security leaders do with AI? They don’t know.
Cybersecurity leaders struggle with AI deployment, leading to decision fatigue. Experts advise starting with repetitive tasks and red teaming while guarding against sophisticated threats like Ghostjacking in trusted logs.
Read article
How Claude's Text Watermarking Works
This deep dive explains how Anthropic's text watermarking works. It details how deterministic sampling is achieved by modifying the next-token selection process using secret keys and tournament sampling.
Read article
Infra behind Krea 2: How to train and serve at scale — Gabriel Jorge Menezes, Krea.ai
To train Krea 2, we built a system that handles crashes at scale and uses advanced metrics like tensor core utilization and InfiniBand monitoring to ensure stability.
Read article
Generative Video at the Speed of Light — Keegan McCallum, uRun
The frontier in generative video is shifting from quality to efficiency and long-horizon generation. Building real-time applications requires global GPU positioning, WebRTC/ICE/TURN setup, and continuous streaming pipelines.
Read article
Introducing: LangSmith Tuned Evaluators
LangSmith Tuned Evaluators automatically attach quality feedback to production traces and threads. They analyze agent interactions to find behavior that needs attention, starting with Perceived Error.
Read article
Build a live translation broadcast app with the Gemini Live API and LiveKit
Learn to build a real-time multilingual broadcast app using Gemini 3.5 Live Translate, LiveKit, and Google Cloud Run. The demo covers setting up translation sessions, managing WebSockets, and broadcasting captions via WebRTC.
Read article