The compliance prompt alone is worth bookmarking. Especially for startups navigating multiple jurisdictions.
PROMPT ENGINEERING
-
What to add for AI agent testing best practices
By
–
Tu verrais quelque chose à rajouter @conseilsmkg en matière de test d’agent IA ?
-
A highly tactical and forward-looking AI prompt
By
–
Bookmarking this prompt forever. It's rare to find something tactical and forward looking at the same time.
-
User experiences improved results using Grok 4 for market research
By
–
Just tested the market research and script prompts, both delivered surprisingly sharp results. Grok 4 might actually replace a few tools for me.
-
AI Agents: Are You Really Prepared for Implementation?
By
–
L’agent IA décroche : êtes-vous (vraiment) prêt ? Un bon agent IA comprend, décide… et agit.
Mais sans contexte bien pensé, il peut vite interpréter de travers, voire embarquer vos utilisateurs dans le mur. C’est la 2e leçon du #FlashCahierdeVacances – IA Edition. À lire -
Deep Research Excels at Clarifying Concise Writing
By
–
deep research is v good at explaining my dense-to-be-concise prose here
-
Viral AI Prompts: Encouraging Creative Experimentation Beyond Formulas
By
–
Its interesting how viral my prompt has gone.
— Ethan Mollick (@emollick) 21 juillet 2025
Like with the Ghibli trend, I think a lot of people want very clear formulas for fun stuff they can do with AI. I get it, but also would encourage people to experiment widely to figure out novel combinations. Much is unexplored. https://t.co/YGMYv7C5fiIts interesting how viral my prompt has gone. Like with the Ghibli trend, I think a lot of people want very clear formulas for fun stuff they can do with AI. I get it, but also would encourage people to experiment widely to figure out novel combinations. Much is unexplored.
-
DSPy: Prompting Library Without Model Weight Updates
By
–
from what I know DSPY is just a prompting library… not actually updating any model weights
-
Optimizing Reasoning Models Through Prompt Rewriting Fine-tuning
By
–
By this, I mean:
– Take an already-trained, frozen reasoning model (i.e. o4-mini via API)
– Add a smaller LLM that takes in a prompt, and rewrites it to improve how the frozen model performs
– Update the smaller LLM's weights, keep the larger LLM frozen The hope is that the
