AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
Topic

Prompt Engineering

Prompt design patterns, instruction hierarchy, and defensive prompt construction.

prompt engineeringsystem promptsinstruction hierarchyguardrailstask decomposition
Evergreen Overview

Prompt engineering is not just about better outputs. In practice it shapes reliability, scope, fallback behavior, and how well an AI system resists misuse when instructions, tools, and untrusted content collide.

What matters most
  • Instruction hierarchy and role separation
  • Clear task boundaries, fallback behavior, and refusal handling
  • Prompt structures that support monitoring and repeatable evaluation
Where teams get into trouble
  • Overloading prompts with too many responsibilities
  • Relying on wording instead of system controls
  • Treating prompts as static text instead of part of application design
Who this page is for
  • Teams operating prompt-heavy workflows
  • Builders refining assistant and agent behavior
  • Reviewers trying to connect prompt design to safety and risk
References

Current notes, events, and source material

These items are included because they add useful evidence, framing, implementation detail, or upcoming context for teams working in this area.

OpenAI News September 22, 2026 guide

Diagnose prompt-cache misses without widening an agent’s tool access

OpenAI’s prompt-caching guidance explains how to compare requests for changes that invalidate shared prefixes, place explicit breakpoints, and preserve tool definitions while changing which tools are callable. GPT-6 can also receive appended reasoning-effort updates without rewriting the earlier prefix. Workload savings still need measurement.

AI EngineeringPrompt EngineeringAgent Security
Read summary Source link
Skill engineering: independent reviews, edit hooks and rule-level evaluations video thumbnail Play video
AI Engineer September 21, 2026 video

Skill engineering: independent reviews, edit hooks and rule-level evaluations

AI Engineer’s notes from Paul Bakaus’s workshop explain separate visual and deterministic reviews, selective instruction loading, edit hooks and rule-by-rule ablation tests. They distinguish blocking pre-tool hooks from post-edit feedback, describe portability failures, and retain human judgment because aesthetic evaluators can reward the wrong behavior.

AI EngineeringModel EvaluationPrompt Engineering
Open notes Watch on YouTube
OpenAI News October 2, 2026 guide

OpenAI’s GPT-6 guide treats agent performance as a workflow measurement problem

OpenAI’s October 2026 guide recommends evaluating GPT-6-family models on complete tasks, balancing successful outcomes against latency and cost. It describes stable prompt prefixes for caching, explicit tool and authority boundaries, and context compaction that preserves important evidence during long work. Model selection and reasoning effort become variables to test against the application’s own acceptance criteria.

AI EngineeringModel EvaluationPrompt Engineering
Read summary Source link
OpenAI Alignment Research March 25, 2026 tool

Model Spec Evals translates behavioral rules into prompts and tested rubrics

OpenAI’s March 2026 Model Spec Evals release links 596 prompts to specific policy clauses and scenario-level grading rubrics. Researchers reviewed prompts and checked rubric judgments against labeled example responses; the public repository notes that nine prompts are skipped by the public API harness. Coverage is broad but sparse and primarily text-only, using everyday scenarios rather than adversarial agent workflows.

Model EvaluationPrompt EngineeringAI Compliance
Read summary Source link
OpenAI News March 24, 2026 tool

Teen-safety policy prompts: adapt labels and regression-test the classifier

OpenAI’s Teen Safety Policy Pack supplies prompt-based classification policies and matching validation datasets for gpt-oss-safeguard. The six initial areas cover risks including dangerous activities, harmful body ideals and age-restricted goods. Developers map the policy labels into filtering, review or monitoring workflows and can adapt the prompts to their application.

Prompt EngineeringModel EvaluationAI Compliance
Read summary Source link
Search all 466 Prompt Engineering items