How to Evaluate Voice Agents with LangSmith | Focused
A voice agent finishing a call doesn't mean it worked. A scheduling agent can call the right tools in the right order and still book the wrong time,…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Agent State, Memory & Checkpointing: Where the Boundaries Blur
Hi again. In Part 1, I tried to separate state, memory and checkpointing in the simplest way I understand them: State tells the agent where it is an…
Keep Every LangSmith Trace Without the 10 Retention Bill
LangSmith is excellent for debugging live AI systems. But keeping every trace in its extended-retention tier can turn observability into a surprisin…
User-Scoped Memory in Deep Agents: What It Is and Why You Need It
Imagine you build one AI agent and 1,000 people use it. Alice tells the agent: "I prefer Python examples and concise answers." Later, Bob asks: "How…
Graph Engineering Explained: The Missing Fifth Layer of AI Agent Architecture
Every "my agent isn't working" postmortem starts the same way: someone rewrites the prompt. Adds a constraint. Adds an example. Ships it again. Thre…
Add human approval to a LangChain agent in 5 minutes
Add human approval to a LangChain agent in 5 minutes Your agent can send the email. That's the whole problem. A month ago it could only draft one. N…
Benchmarking Gemini, Claude, and OpenAI for Structured Document Extraction
A few fellow engineers and I were talking about field extraction the other day. They were both saying Gemini's been surprisingly good at pulling str…
How to Build a Voice Agent with LangChain?
How to Build a Voice Agent with LangChain: Architecture, Streaming, Tools, and Production Patterns Building a voice agent is not simply a matter of…
LCEL vs. Legacy Chains: From Recipe Confusion to Clear Pipelines 🚀
TL;DR: Legacy Chains are the old way—rigid, class-heavy, and frustrating. LCEL is the new standard—visual, modular, and future-proof. Always choose…
Why Basic RAG Fails in Production and How Adaptive Query Routing Fixes It
Most developers build Retrieval-Augmented Generation (RAG) pipelines assuming every user query needs a vector search. In production, this naive appr…
Building a Ride-Share Zone-Balancing Agent with LangGraph — Part 5: Coordinating Two Zones at Once
This is Part 5, the last part of this series. Part 4 let a human step into the loop before a risky decision executes. Every part so far, though, has…
Building a Ride-Share Zone-Balancing Agent with LangGraph — Part 4: Letting a Human Step In
This is Part 4 of a 5-part series. Part 3 gave the agent memory. It can now run for hours on its own, cycle after cycle, without forgetting what it…
Human Oversight of AI Agents Failed 33% of the Time in Testing
When AI agents ask for permission to act, how often do humans actually catch the dangerous ones? A study on AI agent command approval accuracy acros…
Optimizing LLM Stream Ingestion: Reconstructing Truncated JSON Payloads in 0.0122ms
Every engineering team deploying production-grade LLM agents or RAG pipelines faces the exact same architectural bottleneck: truncated network data…
Top 5 Dev Tools Released in Late July 2026
LangChain 0.3.0 LangChain 0.3.0 is a popular AI framework that enables developers to build applications with large language models through enhanced…
LangChain Essentials — The Only Things You Need Before LangGraph
Note: This article was written in July 2026 using LangChain 0.3.x. APIs may change in future versions — check the LangChain docs if something doesn'…
Handoffs can turn one task into a 15x token bill
Handoffs are useful when a specialist agent needs to take over a task. They also make cost easier to hide, because the bill is spread across graph n…
Delegation Masking: Why Your LangChain Callbacks Lie About Sub-Agent Failures
You delegate a task from Agent A to Agent B in LangChain. Agent B fails. Agent A's callback chain fires 'success' anyway. This is the observability…
Stop your Grok 4.5 agents from blowing past the context window
Long-running agents have a boring failure mode: they accumulate conversation until they hit the model's context window and fall over. xAI ships a fi…
Understanding FilesystemBackend in LangChain's Deep Agents
In a previous example, we used StateBackend , where files belonged to a specific LangGraph conversation thread. This time, we are using something di…
AI Agents in Finance Live or Die by Runtime Receipts | Focused Labs
The board wants to see the bottom line of the RFP. Show the receipt. Financial services boards want to know what they get from the spend on AI in La…
Understanding Middleware in Deep Agents (With Runnable Examples)
If you've built even a simple AI agent, you've probably noticed that the "agent loop" itself is deceptively simple: the model gets a message, decide…
LangChain Advanced Patterns: Building Production-Grade AI Systems
Beyond Basic LangChain You've built a simple agent. Now scale it. Production LangChain systems require: Memory management Error handling Performance…
Understanding "Handoffs" in LangChain(One Agent, Many Personalities)
If you've been building with LangChain agents, you've probably run into a situation like this: you want your agent to behave differently depending o…
Building a Robust RAG Pipeline Architecture for Production
Answer up front: A RAG pipeline architecture is a set of connected services that ingest raw documents, turn them into embeddings, store them in a ve…
RAG from Scratch with ChromaDB (No LangChain Required)
Frameworks like LangChain are great for moving fast, but they also hide a lot of what's actually happening under the hood. If you want to understand…
We deployed a LangChain agent for a client and it silently failed for two weeks. Here's what we built to make sure it never happens again.
Six weeks ago, a LangChain agent we'd deployed for a B2B client started failing on roughly 30% of its sessions. No exceptions. No 500s. Nothing in t…
Your AI Agent Is Leaking Data Right Now — And Every Tool Call Looks Safe
How I built the first open-source tool to catch the attacks that no guardrail sees coming We talk a lot about AI safety. Prompt injections. Jailbrea…
Tell your AI agent if the ground is sinking: measured ground-motion with SibFly + LangChain
Most "is this property risky?" data your agent can reach is modeled — a prediction from soil maps and flood zones. There's a different, underused si…
Why Prompt Engineering Isn't Enough for Production AI Agents
TL;DR: Autonomous Agents frequently get trapped in execution loops, burning through API tokens and compute. Prompt engineering can't guarantee execu…