DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Stateful Rolling Chat History: Manage Conversation Memory Without Blowing the Context Window

Stateful Rolling Chat History: Manage Conversation Memory Without Blowing the Context Window

Comments
4 min read
The conversation you saved to disk still has the SSN in it

The conversation you saved to disk still has the SSN in it

Comments
6 min read
Build System Prompts From Named Sections Instead of One Giant String

Build System Prompts From Named Sections Instead of One Giant String

Comments
4 min read
Tool Call Deduplication: Stop Your Agent from Doing the Same Thing Twice

Tool Call Deduplication: Stop Your Agent from Doing the Same Thing Twice

Comments
6 min read
Static Lint Rules for Your LLM Prompts (Before They Hit Production)

Static Lint Rules for Your LLM Prompts (Before They Hit Production)

Comments
3 min read
Single-Flight LLM Calls: Coalesce 50 Concurrent Identical Requests Into One API Call

Single-Flight LLM Calls: Coalesce 50 Concurrent Identical Requests Into One API Call

Comments
4 min read
Your Agent Loop Needs a Real Exit: llm-stop-conditions

Your Agent Loop Needs a Real Exit: llm-stop-conditions

Comments
5 min read
prompt-template-version: Semver-Pin Your System Prompts So You Can Always Roll Back

prompt-template-version: Semver-Pin Your System Prompts So You Can Always Roll Back

Comments
6 min read
agentvet-rs: Validate Tool Args Before Your Agent Executes Them (Rust)

agentvet-rs: Validate Tool Args Before Your Agent Executes Them (Rust)

Comments
5 min read
50 Users Ask the Same Question. Your Agent Makes 50 API Calls. Here's the Fix.

50 Users Ask the Same Question. Your Agent Makes 50 API Calls. Here's the Fix.

Comments
4 min read
The Agent That Retried Five Times Over a String: tool-arg-coerce-py

The Agent That Retried Five Times Over a String: tool-arg-coerce-py

Comments
5 min read
Score Your Agent's Responses With a 0.0-1.0 Rubric (No LLM Judge Required)

Score Your Agent's Responses With a 0.0-1.0 Rubric (No LLM Judge Required)

Comments
4 min read
Which Agent Feature Costs the Most? Here's How to Find Out.

Which Agent Feature Costs the Most? Here's How to Find Out.

Comments
7 min read
tool-call-budgets: Stop Runaway Agent Loops Before They Hit Your Invoice

tool-call-budgets: Stop Runaway Agent Loops Before They Hit Your Invoice

Comments
5 min read
llm-retry: Full-Jitter Exponential Backoff for LLM API Calls in Rust

llm-retry: Full-Jitter Exponential Backoff for LLM API Calls in Rust

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