DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Stop sending your users' SSNs to the LLM

Stop sending your users' SSNs to the LLM

Comments
5 min read
Circuit Breaker for LLM Calls: Stop Hammering a Provider That Is Already Down

Circuit Breaker for LLM Calls: Stop Hammering a Provider That Is Already Down

Comments
4 min read
AgentSnap: Usage Tracking With Cost Aggregation for LLM Agents

AgentSnap: Usage Tracking With Cost Aggregation for LLM Agents

Comments
4 min read
Build Anthropic Content Blocks Without Wrestling With Dicts

Build Anthropic Content Blocks Without Wrestling With Dicts

Comments
3 min read
When the Model Says 'ASCENDING' and Your Enum Wants 'asc': tool-arg-fuzzy

When the Model Says 'ASCENDING' and Your Enum Wants 'asc': tool-arg-fuzzy

Comments
5 min read
claude-cost: Cache-Aware Claude Cost Calculator for Rust (Anthropic API + Bedrock)

claude-cost: Cache-Aware Claude Cost Calculator for Rust (Anthropic API + Bedrock)

Comments
4 min read
Fix Bad Structured Output by Feeding the Error Back to the Model

Fix Bad Structured Output by Feeding the Error Back to the Model

Comments
4 min read
PII Redaction Before LLM Calls: Keep User Data Out of Your Prompt Logs

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

Comments
4 min read
In-Process LRU Cache for LLM Calls: Stop Paying for the Same Response Twice

In-Process LRU Cache for LLM Calls: Stop Paying for the Same Response Twice

Comments
4 min read
Register Named Health Checks for Your Agent So You Know What's Broken

Register Named Health Checks for Your Agent So You Know What's Broken

Comments
4 min read
LLM Jury: Get a Better Answer by Asking Multiple Models to Vote

LLM Jury: Get a Better Answer by Asking Multiple Models to Vote

Comments
4 min read
Persist LLM Conversations Safely: JSONL, Redaction, and Encryption

Persist LLM Conversations Safely: JSONL, Redaction, and Encryption

Comments
6 min read
Ordered Provider Failover: Try Anthropic, Fall Back to OpenAI, Then Gemini

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

Comments
4 min read
Declarative Tool Prerequisites: Enforce Tool Ordering Before the Agent Calls in the Wrong Order

Declarative Tool Prerequisites: Enforce Tool Ordering Before the Agent Calls in the Wrong Order

Comments
4 min read
Strip Thinking Tags From LLM Output Before Sending to Users

Strip Thinking Tags From LLM Output Before Sending to Users

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