Agentic
Agentic Code Review: Prompts That Catch Bugs Static Analysis Misses
The code review prompt chain that finds logic errors, not just style violations
Brian Gagne
Author
Brian Gagne
CTO, Kief Studio
CTO of Kief Studio. 20+ years technology consulting. Cisco Certified Ethical Hacker, UPenn AI for Business, Perplexity AI Business Fellow. Builds the tools Qurtoo teaches you to use.
75 articleskief.studio
Articles by Brian Gagne
SecurityBuilding Prompt Guardrails: Input Filtering and Output Validation for LLM-Powered Apps
The defense-in-depth prompt security stack every AI app needs
Brian Gagne
SecurityPrompting for Threat Modeling: STRIDE Analysis With an LLM Co-Pilot
Turn architecture diagrams into threat models in 15 minutes
Brian Gagne
SecurityWriting Incident Response Prompts That Actually Speed Up Triage
Pre-built prompt templates for log analysis, IOC extraction, and timeline reconstruction
Brian Gagne
SecurityPrompt Injection Testing for Production Apps: A Red Team Playbook
16 injection techniques to test before your users find them first
Brian Gagne
AgenticFeedback Loop Prompting: Teach Your Agent to Critique and Retry Its Own Output
The inner-loop pattern that turns a single LLM call into an iterative refinement engine
Brian Gagne
AgenticMulti-Agent Handoff Prompts: How to Write Instructions That Transfer Context Between Agents
The system prompt architecture behind reliable agent-to-agent coordination
Brian Gagne
AgenticDesigning Tool-Use Prompts That Don't Hallucinate Tool Calls
Why agents invoke wrong tools and the prompt structure that fixes it
Brian Gagne
AgenticThe Plan-and-Execute Pattern: Use a Frontier Model to Plan, a Cheap Model to Execute
Cut your agentic workflow costs by 90% without losing quality
Brian Gagne
TechniquesTemperature Is Not a Creativity Dial: What Sampling Parameters Actually Do and When to Change Them
The real mental model for temperature, top-p, and top-k with evidence
Brian Gagne
TechniquesThe Verification Prompt Pattern: Build Self-Checking Into Every LLM Call
One extra prompt turn that catches hallucinations before they ship
Brian Gagne
TechniquesStructured Output Prompting: Force Any LLM to Return Valid JSON Every Time
The schema-first prompting pattern that eliminates parsing failures
Brian Gagne