Stop testing and rewriting prompts manually! Most teams run evals, look at failures, guess what's wrong, rewrite the prompt, then repeat. It's slow and you never know if your rewrite actually fixes the root issue. The better way is evolutionary optimization. Instead of manual
AUTOMATION
-
Codex Goal Feature Unleashes 24/7 AI Workforce
By
–
Codex new `/goal` is literally INSANE You can easily transform your AI bots into a tireless 24/7 workforce that grinds for HOURS completely unguided Codex desktop → Settings → Config, set
goals = true Check out the ace cheat sheet + article by @aiedge_ to master it -
BMS Boosts Drug Manufacturing Output by 40% Using AI
By
–
@BMSnews boosted drug manufacturing output 40% with AI. They're now targeting a 3-yr reduction in time to market. That's production-scale AI in one of the most regulated industries. We're proud to help half of the top 20 drive AI value. NYT:
-
AI-powered solar rovers remove weeds without herbicides
By
–
-
OpenSquilla Releases Cost-Efficient Open-Source AI Agent for Long-Running Tasks
By
–
OpenSquilla released a new open-source AI agent designed for executing cost-efficient, long-running tasks. It offers 60-80% token savings and is available under the Apache-2.0 license! > ML classifier sends simple tasks to cheap models, complex ones to stronger models > 60-80%
-
Automated codex review loop skill with architecture limitation
By
–
Wrote a skill that runs codex /review in a loop until there's no booboos anymore. Caveat: It won't fix system architecture for ya, so you still need BRAIN as master model. https://
github.com/steipete/agent
-scripts/blob/main/skills/codex-review/SKILL.md
… -
Claude Code introduces autonomous goal-oriented agent workflows
By
–
Claude Code just shipped /goal. You set a condition. Claude keeps working across turns until it's met. No babysitting. No prompting each step. A separate AI checks the work after every turn. Not Claude judging itself. Set it. Walk away. Come back to finished work. I made a
-
Google to Reveal New Gemini Spark AI Agent at Google I/O
By
–
GOOGLE : A new Gemini Spark Agent is about to be revealed during Google I/O. Gemini Spark will work as a 24/7 assistant that can learn from user behavior and work with connected apps and skills. > Let Gemini do more as your everyday AI agent, ready 24/7 to help with your
-
Unsupervised AI analysis as a new operational risk
By
–
PMs running AI analysis unsupervised is a new category of problem.
-
Build Your AI Employee in One Afternoon
By
–
this guy literally breaks down the exact Claude + Obsidian playbook to build your own AI employee in a single afternoon