A simple trick cuts your LLM costs by 50%! Just stop using JSON and use this instead: TOON (Token-Oriented Object Notation) slashes your LLM token usage in half while keeping data perfectly readable. Here's why it works: TOON's sweet spot: uniform arrays with consistent fields per row. It merges YAML's indentation and CSV's tabular structure, optimized for minimal tokens. Look at the example below. JSON: { "𝘂𝘀𝗲𝗿𝘀": [ { "𝗶𝗱": 𝟭, "𝗻𝗮𝗺𝗲": "𝗔𝗹𝗶𝗰𝗲", "𝗿𝗼𝗹𝗲": "𝗮𝗱𝗺𝗶𝗻" }, { "𝗶𝗱": 𝟮, "𝗻𝗮𝗺𝗲": "𝗕𝗼𝗯", "𝗿𝗼𝗹𝗲": "𝘂𝘀𝗲𝗿" } ] } Toon: 𝘂𝘀𝗲𝗿𝘀[𝟮]{𝗶𝗱,𝗻𝗮𝗺𝗲,𝗿𝗼𝗹𝗲}: 𝟭,𝗔𝗹𝗶𝗰𝗲,𝗮𝗱𝗺𝗶𝗻 𝟮,𝗕𝗼𝗯,𝘂𝘀𝗲𝗿 It's obvious how few tokens are being used to represent the same information! To summarise, here are the key features: 💸 30–60% fewer tokens than JSON 🔄 Borrows the best from YAML & CSV 🤿 Built-in validation with explicit lengths & fields 🍱 Minimal syntax (no redundant braces, brackets, etc.) IMPORTANT!! That said, for deeply nested or non-uniform data, JSON might be more efficient. In the next tweet, I've shared some benchmark results demonstrating the effectiveness of this technique in reducing the number of tokens and improving retrieval accuracy with popular LLM providers. Where do you think this could be effective in your existing workflows? Find the relevant links in the next tweet!

XBOW raised $117M to build AI hacking agents. Now someone just open-sourced it for FREE. Strix deploys autonomous AI agents that act like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Why it matters: The biggest problem with traditional security testing is that it doesn't keep up with development speed. Strix solves this by integrating directly into your workflow: ↳ Run it in CI/CD to catch vulnerabilities before production ↳ Get real proof-of-concepts, not false positives from static analysis ↳ Test everything: injection attacks, access control, business logic flaws The best part? You don't need to be a security expert. Strix includes a complete hacker toolkit - HTTP proxy, browser automation, and Python runtime for exploit development. It's like having a security team that works at the speed of your CI/CD pipeline. The best part is that the tool runs locally in Docker containers, so your code never leaves your environment. Getting started is simple: - pipx install strix-agent - Point it at your codebase (app, repo, or directory) Everything is 100% open-source! I've shared link to the GitHub repo in the replies!

As usual, Anthropic just published another banger. This one is on building efficient agents that handle more tools while using fewer tokens. Agents scale better by writing code to call tools and the article explains how to use MCP to execute this code. A must-read for AI devs!

Every LangGraph user I know is making the same mistake! They all use the popular supervisor pattern to build conversational agents. The pattern defines a supervisor agent that analyzes incoming queries and routes them to specialized sub-agents. Each sub-agent handles a specific domain (returns, billing, technical support) with its own system prompt. This works beautifully when there's a clear separation of concerns. The problem is that it always selects just one route. For instance, if a customer asks: "I need to return this laptop. Also, what's your warranty on replacements?" The supervisor routes this to the Returns Agent, which knows returns perfectly but has no idea about warranties. So it either ignores the warranty question, admits it can't help, or even worse, hallucinates an answer. None of these options are desired. This gets worse as conversations progress because real users don't think categorically. They mix topics, jump between contexts, and still expect the agent to keep up. This isn't a bug you can fix since this is fundamentally how router patterns work. Now, let's see how we can solve this problem. Instead of routing between Agents, first, define some Guidelines. Think of Guidelines as modular pieces of instructions like this: ``` agent.create_guideline( condition="Customer asks about refunds", action="Check order status first to see if eligible", tools=[check_order_status], ) ``` Each guideline has two parts: - Condition: When it gets activated? - Action: What should the agent do? Based on the user's query, relevant guidelines are dynamically loaded into the Agent's context. For instance, when a customer asks about returns AND warranties, both guidelines get loaded into context simultaneously, enabling coherent responses across multiple topics without artificial separation. This approach is actually implemented in Parlant - a recently trending open-source framework (15k+ stars). Instead of routing between specialized agents, Parlant uses dynamic guideline matching. At each turn, it evaluates ALL your guidelines and loads only the relevant ones, maintaining coherent flow across different topics. You can see the full implementation and try it yourself. That said, LangGraph and Parlant are not competitors. LangGraph is excellent for workflow automation where you need precise control over execution flow. Parlant is designed for free-form conversation where users don't follow scripts. The best part? They work together beautifully. LangGraph can handle complex retrieval workflows inside Parlant tools, giving you conversational coherence from Parlant and powerful orchestration from LangGraph. I have shared the repo in the replies!

RAG vs. CAG, clearly explained! RAG is great, but it has a major problem: Every query hits the vector database. Even for static information that hasn't changed in months. This is expensive, slow, and unnecessary. Cache-Augmented Generation (CAG) addresses this issue by enabling the model to "remember" static information directly in its key-value (KV) memory. Even better? You can combine RAG and CAG for the best of both worlds. Here's how it works: RAG + CAG splits your knowledge into two layers: ↳ Static data (policies, documentation) gets cached once in the model's KV memory ↳ Dynamic data (recent updates, live documents) gets fetched via retrieval The result? Faster inference, lower costs, less redundancy. The trick is being selective about what you cache. Only cache static, high-value knowledge that rarely changes. If you cache everything, you'll hit context limits. Separating "cold" (cacheable) and "hot" (retrievable) data keeps this system reliable. You can start today. OpenAI and Anthropic already support prompt caching in their APIs. I have shared a link to OpenAI's prompt caching guide in the replies. Have you tried CAG in production yet?

Meta just changed the RL game! The hardest part of reinforcement learning isn't training. It's managing the environment: the virtual world where your agent learns by trial and error. With no standard way to build these worlds, each project starts from scratch with new APIs, new rules, new feedback loops. The result? Agents that can't move across tasks, and researchers spending more time wiring environments than improving behavior. This is exactly what PyTorch OpenEnv solves. Think of it as the MCP moment for RL training. OpenEnv standardizes how agents train with reinforcement learning. It gives every RL system a shared, modular world. A containerized environment built on Gymnasium-inspired APIs that speak a common language: - reset() → start a new episode - step(action) → take an action and get feedback - state() → observe progress Each environment runs in isolation over HTTP: simple, type-safe, and reproducible. Here's the flow in practice: - An agent connects through the OpenEnv client - The client routes actions to a FastAPI environment running in Docker - The environment processes, updates state, and returns feedback - The loop continues Same pattern, whether it's a toy game, a coding environment, or any custom world you want your agents to interact with. Just like MCP standardized tool calling for agents, OpenEnv standardizes how agents interact with RL training environments. The best part everything is 100% open-source! In the replies, I've shared a reproducible example that uses UnslothAI to fine-tune GPT-OSS 20B to play the game 2048, plus the link to Meta's open-source OpenEnv repo.