Akash Hadagali Persetti (@akashpersetti)

@akashpersettiBloomington, Indiana, United StatesJoined June 2026

Shipping production agentic AI systems on AWS | LangGraph, FastAPI, Bedrock | MS CS ’26, Indiana University | Open to New Grad AI Engineer & SWE roles

@akashpersettiBloomington, Indiana, United StatesJoined June 2026

Shipping production agentic AI systems on AWS | LangGraph, FastAPI, Bedrock | MS CS ’26, Indiana University | Open to New Grad AI Engineer & SWE roles

Akash Hadagali Persetti

About

Available for

Akash Hadagali Persetti's blogs

Recently published

My eval leaderboard published a negative retry count

I Ran terraform validate Inside a Lambda. Two Things Broke.

The cost of a serverless agent isn't the Lambda. It's the loop.

Four rival LLMs, zero consensus: designing an MCP panel

I grade my AI twin on real traffic, not just an offline test set

Akash Hadagali Persetti

About

Available for

Akash Hadagali Persetti's blogs

Recently published

My eval leaderboard published a negative retry count

I Ran terraform validate Inside a Lambda. Two Things Broke.

The cost of a serverless agent isn't the Lambda. It's the loop.

Four rival LLMs, zero consensus: designing an MCP panel

I grade my AI twin on real traffic, not just an offline test set

Akash Hadagali Persetti

About

Available for

Akash Hadagali Persetti's blogs

Recently published

My eval leaderboard published a negative retry count

I Ran terraform validate Inside a Lambda. Two Things Broke.

The cost of a serverless agent isn't the Lambda. It's the loop.

Four rival LLMs, zero consensus: designing an MCP panel

I grade my AI twin on real traffic, not just an offline test set

Search Hashnode

Akash Hadagali Persetti

About

Available for

Akash Hadagali Persetti's blogs

Recently published

My eval leaderboard published a negative retry count

I Ran terraform validate Inside a Lambda. Two Things Broke.

The cost of a serverless agent isn't the Lambda. It's the loop.

Four rival LLMs, zero consensus: designing an MCP panel

I grade my AI twin on real traffic, not just an offline test set