DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Your Bedrock Cost Estimate Was Wrong: Cross-Region Inference Multipliers
mukundakatta profile

Why Your Bedrock Cost Estimate Was Wrong: Cross-Region Inference Multipliers

#hermeschallenge #ai #rust #agents
Comments
5 min read
Strip Thinking Tags From LLM Output Before Sending to Users
mukundakatta profile

Strip Thinking Tags From LLM Output Before Sending to Users

#hermeschallenge #ai #python #agents
Comments
4 min read
Stop sending your users' SSNs to the LLM
mukundakatta profile

Stop sending your users' SSNs to the LLM

#hermeschallenge #ai #python #agents
Comments
5 min read
Stop Branching on Error Strings: A Closed Enum for Tool Exceptions
mukundakatta profile

Stop Branching on Error Strings: A Closed Enum for Tool Exceptions

#hermeschallenge #ai #python #agents
Comments
4 min read
tool-arg-coerce-py: Coerce LLM Tool Args to Expected Types Before They Break Things
mukundakatta profile

tool-arg-coerce-py: Coerce LLM Tool Args to Expected Types Before They Break Things

#hermeschallenge #ai #python #agents
Comments
5 min read
Redact API Keys and Tokens From LLM Payloads Before They Leave Your Network
mukundakatta profile

Redact API Keys and Tokens From LLM Payloads Before They Leave Your Network

#hermeschallenge #ai #python #agents
Comments
4 min read
Thread a Run ID Through Every Agent Call So You Can Debug Anything
mukundakatta profile

Thread a Run ID Through Every Agent Call So You Can Debug Anything

#hermeschallenge #ai #python #agents
Comments
4 min read
PII Redaction Before LLM Calls: Keep User Data Out of Your Prompt Logs
mukundakatta profile

PII Redaction Before LLM Calls: Keep User Data Out of Your Prompt Logs

#hermeschallenge #ai #python #agents
Comments
4 min read
Fast Heuristic Token Counter: Know Your Prompt Size Without Calling tiktoken
mukundakatta profile

Fast Heuristic Token Counter: Know Your Prompt Size Without Calling tiktoken

#hermeschallenge #ai #python #agents
Comments
4 min read
Rule-Based LLM Output Validation: Reject Bad Responses Before They Reach Your Users
mukundakatta profile

Rule-Based LLM Output Validation: Reject Bad Responses Before They Reach Your Users

#hermeschallenge #ai #python #agents
Comments
5 min read
Multi-Provider Streaming Chunk Reassembly: Collect an LLM Stream Into a Complete Response
mukundakatta profile

Multi-Provider Streaming Chunk Reassembly: Collect an LLM Stream Into a Complete Response

#hermeschallenge #ai #python #agents
Comments
4 min read
Self-Impose Rate Limits on Your Agent Before Your Provider Does
mukundakatta profile

Self-Impose Rate Limits on Your Agent Before Your Provider Does

#hermeschallenge #ai #python #agents
Comments
6 min read
Ordered Provider Failover: Try Anthropic, Fall Back to OpenAI, Then Gemini
mukundakatta profile

Ordered Provider Failover: Try Anthropic, Fall Back to OpenAI, Then Gemini

#hermeschallenge #ai #python #agents
Comments
4 min read
Render Tool Output as LLM-Friendly Markdown: Give the Model Readable Data, Not Raw JSON
mukundakatta profile

Render Tool Output as LLM-Friendly Markdown: Give the Model Readable Data, Not Raw JSON

#hermeschallenge #ai #python #agents
Comments
5 min read
In-Process Pub/Sub for Agent Events: Decouple Your Observability From Your Logic
mukundakatta profile

In-Process Pub/Sub for Agent Events: Decouple Your Observability From Your Logic

#hermeschallenge #ai #python #agents
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.