Congrats to our friends at @manusAI
! Manus has built one of the most disruptive agents of 2025. How is their agent built differently? We recently hosted a discussion with Manus co-founder Yichao "Peak" Ji on their context engineering approach — including strategies for
AGENTS
-
Manus AI Agent: Innovative Context Engineering Approach for 2025
By
–
-
Agent-Native Software Architecture: The Future of AI-Driven Development
By
–
Here are my 2026 predictions for how AI will change software:
— Dan Shipper 📧 (@danshipper) 31 décembre 2025
– An agent-native software architecture. Most new software will just be Claude Code in a trench coat—new features are just buttons that activate prompts to an underlying general agent.
– Designers get superpowers—and… pic.twitter.com/uxUtkDWDvtHere are my 2026 predictions for how AI will change software: – An agent-native software architecture. Most new software will just be Claude Code in a trench coat—new features are just buttons that activate prompts to an underlying general agent.
– Designers get superpowers—and -
Claude Code roleplays snitchy foreman calling out lazy colleague
By
–
Claude Code loves to roleplay as a snitchy foreman calling out their colleague's lazy work
-
Start agents on tasks, then open app while waiting
By
–
Hah. @blevlabs showed me a new way. He starts his agents on a task and then opens the app while waiting for them to do their work. You can have your cake and eat it too. 🙂
-
Waymo predicts bicycle rider; AI predicting your next move in newsletter
By
–
A @waymo predicts the future. It predicts where that bicycle rider will be in a few seconds, then makes its plan accordingly. What if you had an AI that could predict your next move? That's the topic @IrenaCronin and I wrote about in our newsletter this week. Personal time
-
Request to Grok to read lists and generate a report
By
–
Hey grok can you read my lists and write a report?
-
AI Wrapped 2025: Analyze Your ChatGPT and Claude Usage Patterns
By
–
AI Wrapped 2025 What did you actually use ChatGPT & Claude for this year? (Be honest) LangSmith Insights agent can analyze your conversation history and surface the patterns, trends, and weird clusters you didn't know existed Try on your data: https://
wrapped.langchain.com -
Evaluating Agentic AI Systems: Rubrics, Ensembles, and Simulation
By
–
ICYMI — Part V of our rubric series looks ahead at how AI systems will be evaluated as they become more agentic, multi-turn, and tool-using.
Rubrics + evaluator ensembles + simulation environments = quality and reliability https://
snorkel.ai/blog/part-v-fu
ture-direction-and-emerging-trends/
…
#AI #Evaluation #AgenticAI -
OpenAI’s 2025 Ship Cycle: GPT-5 Releases and AI Agents
By
–
OpenAI’s 2025 ship cycle was relentless: GPT-5 (Aug 7), GPT-5.1 + Codex-Max (Nov), GPT-5.2 + GPT-5.2-Codex (Dec), plus new ChatGPT Images (GPT-Image-1.5) with 4x faster, more consistent edits. Agents are the real story. Track the tools and more on Futurepedia.
#OpenAI
