close

DEV Community

Debashish Ghosal profile picture

Debashish Ghosal

Getting back into coding after 15 years as a people manager

Location Seattle, WA Joined Joined on  Personal website https://github.com/deghosal-2026/ github website
I Planned 10 LLM Evaluation Experiments And Only Ran 1. It Was Enough.

I Planned 10 LLM Evaluation Experiments And Only Ran 1. It Was Enough.

BERJAYA BERJAYA BERJAYA 3
Comments
13 min read

Want to connect with Debashish Ghosal?

Create an account to connect with Debashish Ghosal. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
I Connected 3 MCP Servers to One Agent. It Got Scary Fast.

Exposes glaring security gaps in multi-MCP setups

I Connected 3 MCP Servers to One Agent. It Got Scary Fast.

BERJAYA BERJAYA BERJAYA 10
Comments 10
5 min read
Platform Strategy That Ships: The 90-Day System I Trust More Than AI Roadmaps

Platform Strategy That Ships: The 90-Day System I Trust More Than AI Roadmaps

BERJAYA BERJAYA BERJAYA 5
Comments
7 min read
4 Open-Source AI Tools, 1 MCP Server — What I Built and What I Learned

Overcoming internal dev tool adoption hurdles

4 Open-Source AI Tools, 1 MCP Server — What I Built and What I Learned

BERJAYA BERJAYA BERJAYA 9
Comments 14
15 min read
The Best AI Productivity Win I Got This Month Wasn't From Coding

The Best AI Productivity Win I Got This Month Wasn't From Coding

Comments
4 min read
Your Flaky Tests Aren't Flaky

Your Flaky Tests Aren't Flaky

Comments
6 min read
i built a tool that tracks what AI tasks actually cost. the real number surprised me.

i built a tool that tracks what AI tasks actually cost. the real number surprised me.

Comments 3
6 min read
i've been building platforms first for 25 years. i think it's wrong now.

i've been building platforms first for 25 years. i think it's wrong now.

BERJAYA 1
Comments
6 min read
i tested an ai incident commander against 15 real outages — 88% pass rate

i tested an ai incident commander against 15 real outages — 88% pass rate

BERJAYA 1
Comments 2
4 min read
i spent 3 days on a rag pipeline and the embedding model didn't matter at all

i spent 3 days on a rag pipeline and the embedding model didn't matter at all

Comments
6 min read
my ai agent ran for 6 hours on a 2-minute task and cost me $200

my ai agent ran for 6 hours on a 2-minute task and cost me $200

BERJAYA 1
Comments 1
6 min read
i've been doing sdlc for 25 years. ai didn't kill it. it made it the coordination layer.

i've been doing sdlc for 25 years. ai didn't kill it. it made it the coordination layer.

BERJAYA 1
Comments 1
7 min read
i was using a frontier model to update jira tickets. here's how i fixed it.

i was using a frontier model to update jira tickets. here's how i fixed it.

BERJAYA 1
Comments
6 min read
i built two langgraph projects and learned that agents are junior engineers with amnesia

i built two langgraph projects and learned that agents are junior engineers with amnesia

BERJAYA 2
Comments 8
7 min read
loading...