Madhu Shantan

Madhu Shantan

xMemory: Why Top-k Retrieval Breaks for Agent Memory

xMemory: Why Top-k Retrieval Breaks for Agent Memory

Introduction LLM agents no longer begin and end in a single context window. We’re now in the era of cross-session, long-running agents. Products like Claude Code, OpenClaw, and other agentic workflows are built to carry context across days of work, not minutes. The bottleneck is not context length anymore.

The Skills vs MCP Debate: Understanding Two Layers of the Same Stack

The Skills vs MCP Debate: Understanding Two Layers of the Same Stack

How coding agents reshaped the tool integration landscape and what actually survived We're in an interesting moment for AI's application layer. Agents can now write code (better than most programmers), call APIs, query databases, and orchestrate complex workflows. But the infrastructure underneath - how agents actually

Voice Simulation: Testing Voice Agents the Way Users Experience Them

Voice Simulation: Testing Voice Agents the Way Users Experience Them

Introduction Voice is rapidly becoming the next frontier of AI interaction (along with physical AI). As more companies deploy voice agents for customer support, sales, and service operations, the stakes have never been higher. A poorly tested voice agent doesn't just frustrate users - it can damage your

The Discipline Layer: Harnesses as the Missing Piece in Autonomous Coding

The Discipline Layer: Harnesses as the Missing Piece in Autonomous Coding

Introduction If you've been working with AI agents on longer tasks, you've probably developed your own tricks for dealing with context window limits. Maybe you hit /summarize in Cursor when things get bloated or you ask the agent to write a summary.md file at the

AgentFold : What If AI Agents Managed Memory Like Humans Do?

AgentFold : What If AI Agents Managed Memory Like Humans Do?

Introduction If you've spent time working with LLM agents for web research, coding assistance in cursor or even extended conversations in ChatGPT, you've probably noticed something: as tasks or multi turn conversations grow longer and more complex, the quality of responses deteriorates - essentially because of

MCPToolBench++: Raising the Bar for Realistic AI Agent Tool-Use Benchmarks

MCPToolBench++: Raising the Bar for Realistic AI Agent Tool-Use Benchmarks

Introduction At the heart of reliable AI agents lies one critical skill: effective tool calling. We can see this in action with systems like the new Kimi K2, which connects seamlessly to dozens of tools, including web search, map navigation, financial analysis, and automated workflows. This results in impressive versatility

When Your AI Can't Tell the Difference Between "Fine" and Frustration

When Your AI Can't Tell the Difference Between "Fine" and Frustration

Final Results of SER Accuracy of Gemini 2.5 Flash and GPT 4o across the two modalities.

PaperBench: Can AI Agents Actually Replicate AI Research?

PaperBench: Can AI Agents Actually Replicate AI Research?

Model's Replication Scores Average Replication Scores on PaperBench

Tool Chaos No More: How We’re Measuring Model-Tool Accuracy in the Age of MCP

Tool Chaos No More: How We’re Measuring Model-Tool Accuracy in the Age of MCP

Introduction Picture this scenario: you’ve built an AI agent, given it access to dozens of tools, and deployed it to handle a complex workflow. But instead of executing queries crisply, it’s making redundant tool calls, burning API credits needlessly, and overcomplicating straightforward processes. This isn’t just an

User Simulation in AI: From Rule-Based Models to LLM-Powered Realism

User Simulation in AI: From Rule-Based Models to LLM-Powered Realism

What if you could test your AI system with thousands of diverse users without recruiting a single person? User Simulation makes this possible. Simulating human users - a fundamental application of AI has driven progress in both research and industry. By allowing machines to imitate real user interactions, user simulation

Do Language Models Know That They're Being Evaluated?

Do Language Models Know That They're Being Evaluated?

Picture this scenario: You’re very new to AI, exploring chatgpt by testing its capabilities on various topics, expecting honest answers unaware that behind the scenes, it already figured out that it’s being tested and is subtly changing its behaviour to ace your tests. This feels like a subtle

AlphaEvolve : AI for Scientific Discovery

AlphaEvolve : AI for Scientific Discovery

Introduction Consider a scenario: You're facing a complex optimization challenge with no known solution - the kind that requires inventing entirely new algorithms, not just tweaking existing ones. There's no textbook answer, no established approach. Existing coding models like Claude, Gemini 2.5 can implement known