Two quick updates in image world. Try adding –preview to your prompt for a early peak at V8.2 aesthetics & personalization. We've also updated our big batch draft mode to work with –sref random so you can explore style space 24x faster than before. Enjoy!
PROMPT ENGINEERING
-
Agent 2.0 converts prompts to marketing briefs and assets
By
–
Introducing Agent 2.0
— Runway (@runwayml) 25 juin 2026
Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets.
Agent is being built… pic.twitter.com/VZINWuEA7UIntroducing Agent 2.0 Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets. Agent is being built
-
DomainShuttle: Freeform Open Domain Subject-driven Text-to-Video
By
–
DomainShuttle
— AK (@_akhaliq) 25 juin 2026
Freeform Open Domain Subject-driven Text-to-video Generation pic.twitter.com/QC9jYvfnnQDomainShuttle Freeform Open Domain Subject-driven Text-to-video Generation
-
14-Step Guide: Moving from Hand Prompting to Automated Loop Engineering Systems
By
–
/5 Loop engineering has been everywhere lately. This 14-step guide shows what it actually means to move from prompting coding agents by hand to designing systems that prompt, verify, remember state, and keep running without you babysitting every turn. It covers the basics of
-
Top AI Educational Pieces of the Week June 18-25
By
–
Top AI Educational Pieces of the Week (June 18 – 25) 1. Autoresearch for GitHub repos 2. How to configure agent identity in Claude Tag 3. Codex's SSD bug and how to safely check disk usage
4. Andrew Ng: Prompting could be gone in 3-6 months 5. The 14-step guide to loop -
AI shifts from rigid prompts to live brainstorming conversations
By
–
It moves completely away from traditional prompt engineering workflows. You don't just type out a rigid command and hope for the best, instead, you brainstorm through a natural live conversation starting from just a vague idea. The AI works directly with you on a single
-
LLMs should request delay for hard questions or provide quick guesses
By
–
This asynchrony really should exist in normal one-on-one chatbot interactions. When you pose ask a hard question to an LLM it should say, immediately, “This is a hard problem — give me 15m.” If that’s an issue, you should be able to say so and get a quicker guess.
-
Asking which model created her perfect appearance
By
–
What model did you use to create her? She looks so perfect.
-
26 slash commands every power user needs to know
By
–
Want to master Claude Code? Here are 26 slash commands every power user needs to know. Save this list to supercharge your AI coding workflow ↓
-
Path-scoped rules keep Claude’s context clean for big codebases
By
–
6/ For a big codebase, do not pile everything into one file. Use path-scoped rules in a .claude/rules/ folder. They load only when Claude touches the matching part of your code, so the context stays clean instead of carrying everything at once.