Notion launches Notion Agents iOS app

// 1h agoPRODUCT LAUNCH

Notion launches Notion Agents iOS app

The Notion Agents iOS app is a mobile companion that brings Notion's AI agent ecosystem to mobile devices. It enables users to interact with their AI agents via chat to retrieve information from connected tools and Notion workspaces, capture ideas through text, voice notes, and photos, and perform quick actions like drafting updates and creating database pages on the go.

// ANALYSIS

Bringing AI agents to mobile makes captured unstructured data like voice notes and napkin sketches immediately structured and actionable.

–Extends Notion's conversational AI capability to voice and camera inputs.
–Integrates with external tools (Slack, Calendar, Email) directly from a mobile chat interface.
–Respects enterprise-level access controls and user permissions.
–Reliant on Notion's back-end agent reliability and latency.

// TAGS

productivitybotsagentiosnotionnotion-agents

DISCOVERED

1h ago

2026-07-08

PUBLISHED

7h ago

2026-07-08

RELEVANCE

8/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

VIDEO4m ago

HASE co-evolves model weights, harness

Harness-Aware Self-Evolving (HASE) is an agentic reinforcement learning framework that allows a single model to co-evolve its policy weights, task solutions, and environment harness in a unified multi-turn action space. By enabling the model to dynamically modify harness components like prompts, memory formatting, and validators, HASE allows smaller models like Qwen3-8B to match or beat the performance of models as large as 120B parameters in domains like text classification and alpha factor mining.

RESEARCH4m ago

GaP boosts robot policy reliability

Graph-as-Policy (GaP) is a robotics framework designed to bridge the reliability gap in variational automation tasks by representing robot policies as directed computation graphs of modular skills. Developed by researchers from UC Berkeley, NVIDIA, CMU, and Bosch, the framework uses an LLM-in-the-loop multi-agent system to construct, test, and refine these graphs in simulation before deployment.

NEWS4m ago

Lilian Weng outlines harness engineering for RSI

Lilian Weng argues that recursive self-improvement (RSI) in AI lies in optimizing the "harness"—the orchestration layer surrounding a base model—rather than directly rewriting weights. Weng details how harness engineering is transitioning into code-based meta-optimization, though full RSI remains bottlenecked by evaluation and memory limitations.