Sujayath

Co-founder: Silq Group (Sary, ShopUp, Voonik)

[Sujayath @sujayath]

A mega-thread on AI concepts that every founder / PM should know. The no-jargon version.

[Sujayath @sujayath]

@BeingPractical @upadhyay_harsh1 @RaiseTheBarHQ Good things happen to Good people !!

[Sujayath @sujayath]

Update on managing Claude Cowork memory, ~2 weeks since the last post.

Now I have added: A wiki layer on top of atomic memory. Karpathy-style synthesized pages organized by subject (companies/, people/, strategy/, etc.) with cross-links and an explicit Lint workflow. When I commit, new atomic facts propagate to affected wiki pages. The wiki self-maintains.

Verification in the Commit Protocol. Every commit now reports actual byte sizes, entry counts, and wiki page diffs with line deltas. Caught silent write failures I'd never have noticed.

Building next: Two-tier commits. Narrow-scoped chats (mounted at a subfolder only) commit to local memory in their folder. A full-mount chat fans into canonical + wiki. Anyone solved the narrow-mount-chat-updating-canonical-memory problem differently?

Will also tinker with /Goal.

PS: What's the same: typed atomic files (feedback/, projects/, reference/, people/), daily journals, weekly cleanup, per-project CLAUDE.md + TASKS.md, global layer for cross-project prefs.

[Sujayath @sujayath]

How are you guys managing context memory in Claude Cowork?

Approach I was using: A custom "Commit" command that wrote facts directly into memory files mid-chat and saved copies of those memory files in the working folder. Snapshots taken manually when needed or after compacting.

Approach I use now: Daily journal entries from chats. Claude classifies the conversation's durable facts and writes them to typed atomic files (feedback/, projects/, reference/, people/) plus appends the journal entry. A weekly scheduled task handles cleanup - dedup, rotate snapshots, and regenerate MEMORY.md indexes.

Each project has CLAUDE.md + TASKS.md + memory folder with journal/, feedback/, projects/, reference/, people/, snapshots/. A single global layer holds cross-project preferences.

Any better approach - without piping into a third-party "Brain"?

[Sujayath @sujayath]

Looks great, Gokul! Proud investor !!

[Gokul Cholaghar @CholagharGokul]

Introducing Libra AI, the SOTA super agent that amplifies your work, enabling you to bring your best everyday. Your work life will never be the same starting today.

> Libra understands all your data and context like a human teammate
> Takes actions on your behalf
> Replaces the patchwork of vertical AI tools with one that actually does the work

Experience it today, now in early access @librahq⚡️

[Sujayath @sujayath]

How are you guys managing context memory in Claude Cowork?

Approach I was using: A custom "Commit" command that wrote facts directly into memory files mid-chat and saved copies of those memory files in the working folder. Snapshots taken manually when needed or after compacting.

Approach I use now: Daily journal entries from chats. Claude classifies the conversation's durable facts and writes them to typed atomic files (feedback/, projects/, reference/, people/) plus appends the journal entry. A weekly scheduled task handles cleanup - dedup, rotate snapshots, and regenerate MEMORY.md indexes.

Each project has CLAUDE.md + TASKS.md + memory folder with journal/, feedback/, projects/, reference/, people/, snapshots/. A single global layer holds cross-project preferences.

Any better approach - without piping into a third-party "Brain"?

[Sujayath @sujayath]

@zachtratar Is there any write up on using Notion as company's context layer ?

[Vivekananda Hallekere @vivekanandahr]

Most people think Bounce died in COVID. We didn’t.
We pivoted to manufacturing our own electric scooters and renting them to India’s gig workers. 9K on the road today across Bangalore and Delhi-NCR. Going to 40K in under 18 months.
Here’s what we’re building.

[Sujayath @sujayath]

@Citrini7 https://t.co/0cCpX7ZBX8

[Sujayath @sujayath]

Many of you have read that Citrini article. For those who haven't - here it is summarized in the form of newspaper clippings.

[Sujayath @sujayath]

If you found this useful, check out my similar thread on AI concepts every founder / PM should know.

https://t.co/22ekibTyWU

[Sujayath @sujayath]

A mega-thread on AI concepts that every founder / PM should know. The no-jargon version.

[Sujayath @sujayath]

A mega-thread on strategic concepts that every founder / PM should know.

[Sujayath @sujayath]

46. Category Management: The process of managing categories as independent business units, in a way that enables maximum consumer appeal while maximizing profits. Category Management aims to provide customers with what they want, where they want it, and when they want it.

[Sujayath @sujayath]

Many of you have read that Citrini article. For those who haven't - here it is summarized in the form of newspaper clippings.