DEV Community

Python

import antigravity

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Strip Thinking Tags From LLM Output Before Sending to Users

Strip Thinking Tags From LLM Output Before Sending to Users

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

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

Comments
6 min read
Named Persona Registry: Keep Your Agent Identities Consistent Across Every Session

Named Persona Registry: Keep Your Agent Identities Consistent Across Every Session

Comments
4 min read
Redact API Keys and Tokens From LLM Payloads Before They Leave Your Network

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

Comments
4 min read
Persist Your Agent's Conversation History Without Rolling Your Own JSON

Persist Your Agent's Conversation History Without Rolling Your Own JSON

Comments
4 min read
Composable Budget Caps for Agent Runs: Enforce Cost Limits at Multiple Levels

Composable Budget Caps for Agent Runs: Enforce Cost Limits at Multiple Levels

Comments
4 min read
Stop sending your users' SSNs to the LLM

Stop sending your users' SSNs to the LLM

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

AgentSnap: Usage Tracking With Cost Aggregation for LLM Agents

Comments
4 min read
m365-graph-incident-agent: AI-Powered Incident Triage via Microsoft Graph

m365-graph-incident-agent: AI-Powered Incident Triage via Microsoft Graph

Comments
5 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
Rule-Based LLM Output Validation: Reject Bad Responses Before They Reach Your Users

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

Comments
5 min read
Composable Output Guardrails: Filter Agent Responses Before They Reach Users

Composable Output Guardrails: Filter Agent Responses Before They Reach Users

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

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

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