Recursive is emerging into the category. AGI ALPHA has already been building the category in public. #AGIALPHA #MontrealAI #QuebecAI
AGI
-
Best-of-N : optimisation parallèle d’agents IA
By
–
4/5 Best-of-N: Run one agent config N times in parallel → select the best trajectory. Leverages LLMs’ non-determinism – but hinges on a good eval mechanism (we use an LLM-as-a-Judge). Can increase accuracy without linearly increasing latency – but parallel runs can add up $$.
-
Agent Scaffolding: Building the Infrastructure
By
–
3/5 Agent scaffolding: Adjust prompts, integrate tools/skills, set execution policies, retries, memory, etc. → create the operational framework. Useful for long-horizon or multi-step tasks.
-
AI Agent Must Cut Tokens via MCP
By
–
Your AI agent must connect to its MCP server and follow the workflow to significantly reduce token usage.
-
Man builds laser drone using Claude Code
By
–
Man builds a drone that tracks targets with a laser using Claude Code pic.twitter.com/ZeTSHZZrXC
— AI Breakfast (@AiBreakfast) 13 mai 2026Man constructs a drone that tracks targets with a laser, powered by Claude Code
-
Kanwas AI Agents Get Product Context via Graph-Based System
By
–
Kanwas gives AI agents the context they actually need to do product work. • Centralizes PRDs, decisions & research into one graph
• AI auto-drafts strategy docs & roadmaps from it
• Open-source + Git-friendly storage
• Model-agnostic agents that work while your team -
5 new AI tools with unique practical applications
By
–
5 AI tools recently dropped at futurepedia that are actually doing something new. A sales call coach. A product brain. An autonomous agent team. A headshot generator. And one that quietly gets you money back from airlines. Here's what they do
-
Android’s AI agent upgrade with Gemini Intelligence
By
–
Android is becoming an AI agent!@Google just unveiled “Gemini Intelligence” – a major upgrade that turns Gemini from a chatbot into an assistant that can actually do things across your phone.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 13 mai 2026
New features include:
• AI that navigates apps for you
• Automated form filling… pic.twitter.com/4Spg3WPxXdAndroid is becoming an AI agent! @Google just unveiled “Gemini Intelligence” – a major upgrade that turns Gemini from a chatbot into an assistant that can actually do things across your phone. New features include:
• AI that navigates apps for you
• Automated form filling -
AI Autonomy Levels: Presets, Refined Inputs, and Evaluated Outputs
By
–
increasing levels of autonomy: /skill: preset prompts /plan: human-refined inputs /goal: AI-evaluated outputs
-
Key Personalization for Research Agents
By
–
Pay attention to this if you build research or knowledge-work agents. Most research-agent systems generate uniform outputs regardless of who is using them. This new work, NanoResearch, argues that personalization is a prerequisite for true usability and proposes a three-level approach.