Launching today: Instructions vs. Memory š§ aka Context v2
Not all context is equal.
So we stopped treating it that way.
Most AI tools store everything the same:
Writing rules
Personal background
Preferences
Temporary notes
But a rule like:
āUse bullet points.ā
ā¦shouldnāt behave the same as:
āI run a fintech startup and we've just raise $4mā
So we rebuilt our context system, to help Pretty Prompt give better results.
(Best part, the user owns that context, and can use it across any LLM)
Launching today Instructions vs Memory.
š Instructions
Explicit rules that always apply. Examples:
āNo em-dashesā
āKeep answers under 512 charactersā
āUse bullet pointsā
š§ Memory
Background context that only appears when relevant. Examples:
āMy audience is non-technicalā
āI'm launching on Product Hunt and like to post from a builder's mindsetā
āIām writing a client proposal that should include...ā
The best part:
You donāt organize any of this manually.
You just write naturally.
Pretty Prompt auto-classifies everything on the backend.
The goal is simple:
Make AI outputs be personal ā without adding more work.
Still bootstrapped. Still shipping š
PH community, give us feedback; we need it.
(PS - I vibed this thumbnail, don't judge me š)
Replies
Iāve honeslty struggled with AI tools mixing permanent preferences with random temporary context, so this makes a lot of sense to me.
Pretty Prompt
@malani_willaĀ Iāve honestly struggled with AI tools mixing permanent preferences with random temporary context, so this makes a lot of sense to me
@malani_willaĀ @deangelo_hinkleĀ This is actually one of the clearest explanations of context management Iāve seen. I like that I can just write naturally instead of organizing everything manually.
Pretty Prompt
@malani_willaĀ @deangelo_hinkleĀ @shawn_idreesĀ I hope you can give it a try, Context is looking pretty powerful now, and we're working on a Mac App, so this will be even more poweful when runs local on your machine!
Ā @ilaiszpĀ @ilaiszp Thatās awesome to hear about the Mac app! Running it locally makes a huge difference for context management. Definitely gonna give it a try now - manual organizing is the worst part of my workflow.
@malani_willaĀ Really like the philosophy behind this. Iāve noticed most AI tools either overuse memory or completely ignore useful context. Your separation between Instructions and memory feels practical instead of gimmicky.
Pretty Prompt
Pretty Prompt
My LLM isn't following the explicit rules no matter how many times I repeat them. Thoughts?
Pretty Prompt
@zanc_zhaoĀ Drop me an email to help@pretty-prompt.com and I'll personally look into it and help :)
Easier there so I don't miss anything
Really like this distinction. Treating āinstructionā and āmemoryā as the same thing is one of those small product choices that quietly creates a lot of mediocre AI output.
The auto-classification piece feels especially important. Most people will not maintain a context system manually, but they *will* write naturally if the product can infer what should persist, what should be temporary, and what should act like a rule.
One thing Iād be curious about: do you let users inspect or correct the classification after the fact? Iāve found that trust in AI memory often depends less on perfect recall and more on whether people feel they can see and shape what the system thinks it knows.
Pretty Prompt