Jiten Oswal

That's the ceiling nobody prices in. The AI reads your data, writes a beautiful summary of the problem, and then a human copies the customer list into another tab and starts the actual work by hand.
So we built the part after the insight. Basedash Actions writes and runs the SQL to find the answer, then reaches into the tools where the work actually lives (Stripe, HubSpot, and anything else with an MCP server) and does the follow-through. Find the accounts, update the CRM, chain the steps into a workflow that runs on its own.
The obvious objection: nobody sane wants an AI acting on production data unsupervised. Agreed, which is why every action runs through a human approval gate. You see exactly what it's about to do, in plain terms, before it does it.
The gates add friction, and that's deliberate. Trust in agents gets earned one approved action at a time, and I'd rather ship the training wheels than ship the incident report.
We just launched yesterday on Product Hunt. Would you trust this?

https://www.producthunt.com/prod...

When it comes to AI Memory, everyone's arguing "RAG vs. grep" like it's a religious war. It's not. It's just a cost curve. I've gotten this question so many times that I thought I'd just share my thoughts. So here goes:
Vector search wins when your corpus is massive, messy, and unstructured. Thousands of docs, no clean boundaries, meaning matters more than exact words.
Filesystem plus grep wins when your corpus is structured and actually yours. A folder of markdown files you can open, read, and audit line by line. No infra required.
Anthropic already ran this experiment in production. Claude Code dropped its RAG pipeline for plain agentic search (grep, glob, read) and it outperformed the vector pipeline on real work. Not close.
But the benchmark wars are missing the actual point. It was never about picking one. It's about knowing what each layer is for.
Markdown is your source of truth. Portable, human readable, greppable, not locked to one provider. Memory you can actually own and move.
Vector search is an accelerant on top of that truth. A fast index for when the haystack gets too big for exact match to keep up.
Use either one alone and it breaks down:
- Markdown alone stalls at scale and struggles with paraphrasing or fuzzy recall
- Vectors alone turn your memory into a black box you can't read, audit, or export
The next step for memory infrastructure isn't picking a side. It's the filesystem as the ledger and RAG as the index on top of it, so memory stays legible and portable, and still fast when it needs to be.
This is the exact direction we're building with AI Context Flow: markdown as the portable, ownable source of truth, with retrieval layered on top instead of replacing it.
If your memory only exists as embeddings inside someone else's vector DB, that's not memory. That's a lease.
Which team are you on?

I've been running Claude Code, Cursor, and Codex pretty heavily for the last few months and I keep hitting the same loop:

1. Start a task in one agent

2. Switch to something else (Slack, Twitter, another terminal)