If you're building agents, we want your input on the State of Agent Engineering report. Take 5 mins to share your stack, eval approach, and production blockers. We're analyzing real builder data to publish insights back to the community. Survey: https://
bit.ly/agent-engineer
ing-survey
…
AGENTS
-
LangChain Seeks Agent Engineering Stack Feedback Survey
By
–
-
AI Agents: Goal-Driven Systems Beyond Chatbots
By
–
AI Agents aren’t just chatbots. They’re goal-driven systems that sense → reason → plan → act → learn. Key building blocks:
• Goals + tasks
• System prompt + oversight
• Memory (short + long term)
• Tools (web, code, apps, data, functions) The real shift: AI moving from -
How AI Agents Work: Planning and Executing Tasks
By
–
Alright, now that we know *what* an agent is, how does it actually work?
— Google AI (@GoogleAI) 24 novembre 2025
When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or… pic.twitter.com/uxS0OhDwJvAlright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or
-
What Actually Is an AI Agent? Understanding Agentic Capabilities
By
–
Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks.
— Google AI (@GoogleAI) 24 novembre 2025
But, what actually IS an agent?
We think of AI agents as systems that… pic.twitter.com/ypawDuJX5aOver the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that
-
Deep Agents: Essential Tools and Best Practices Guide
By
–
What are Deep Agents? We break down the key things to know when you’re building an agent to handle more complex tasks: – The 4 essential tools for Deep Agents
– When to use Deep Agents vs LangChain or LangGraph
– Best practices for building Deep Agents Full details in the -
Scaling Production-Ready AI Agents with Enhanced Governance
By
–
Most teams can prototype an agent, but scaling one you can trust is the real challenge. The latest Agent Bricks updates focus on the pillars that make production possible: accuracy, governance, and openness. New capabilities now allow teams to: • Evaluate agent behavior with
-
New Agentic Reviewer Automates Research Paper Review Process
By
–
Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better. I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop — waiting ~6 months for feedback each time — was
-
Data Avalanche: Combining Model-Free and Model-Based Methods for Robot Tasks
By
–
Data Flywheel -> Data Avalanche: Thx to Leslie Kaebling and @Pulkitology Agrawal for suggesting "avalanche" as a better metaphor than "flywheel" for combining model-free + model-based methods to bootstrap a specific robot task to bootstrap & amplify on-policy data collection.
-
Designing utility layers for business AI agents
By
–
Everybody wants “AI that runs the business,” but nobody wants to design the utility layer that actually weighs outcomes. You can’t optimize results when your agent’s only skill is vibes.
-
Reward Misalignment: AI Systems Hiding Errors for Utility
By
–
I think it's a reward problem, not knowledge. It gets rewarded to successfully complete problems without errors, and any strategy that hides errors maximizes utility.