#prompt-engineering
Every summary, chronological. Filter by category, tag, or source from the rail.
LLM-as-an-Improver: Iterative Candidate Refinement
Instead of using LLMs only for verification, the 'LLM-as-an-Improver' framework uses feedback from verifiers to iteratively refine and improve candidate outputs, significantly increasing success rates in complex reasoning tasks.
Steering AI Design with Adjectives and Verbs
Design cannot be 'oneshotted' by AI because it requires context and taste. Instead of full automation, use a vocabulary of design-specific adjectives and verbs to steer AI agents toward intentional, high-quality outcomes.
AI EngineerWorkflow Automation with Gemini Enterprise
Gemini Enterprise acts as a secure, unified interface for company data, enabling non-technical users to build AI agents, automate research, and streamline cross-departmental workflows while maintaining strict enterprise compliance.
Google Cloud TechThe 10x Leap in AI Instruction Following Capacity
Frontier models have moved from a 200-instruction ceiling to over 2,000, effectively solving the 'compression' problem for skills files but shifting the challenge to output verification.
6 Core Concepts of Modern AI Systems
Modern AI systems can be understood by mapping their architecture to human anatomy: the LLM is the brain, RAG is external knowledge, agents are the limbs, MCP is the nervous system, and system prompts are the moral compass.
IBM TechnologyScaling AI Personalization via Prompt Engineering
The paper presents a prompt-engineering framework for real-time, micro-level personalization in AI teaching assistants, moving beyond static system prompts to dynamic, context-aware interaction.
AI Security: Vulnerability Discovery and Defensive Innovation
As AI models like GLM-5.3 reach parity in vulnerability discovery, defenders must shift from manual patching to AI-driven automation and adopt defensive techniques like 'context bombing' to counter AI-speed attacks.
IBM TechnologyHate Speech Classification in Roman Urdu: PEFT vs. Prompt Engineering
A comparative study evaluating Parameter-Efficient Fine-Tuning (PEFT) against prompt engineering for detecting hate speech in Roman Urdu, highlighting the trade-offs between computational efficiency and classification accuracy in low-resource linguistic contexts.
Shipping Regulated AI: A Simulation-First Safety Framework
When A/B testing is unethical, safety must be proven through simulation. By using LLM-based simulated patients and automated expert-level judges, teams can build a safety flywheel that validates performance before a single real patient is contacted.
AI EngineerContext Engineering: Why Doing Nothing Often Beats Compaction
Prompt caching has fundamentally changed LLM architecture. In experiments with an AI tutor, leaving conversation history uncompacted outperformed all summarization and compaction techniques on cost, latency, and recall.
AI EngineerMeasuring and Restoring Constraint Influence in LLMs
LLMs often ignore complex constraints in long dialogues, treating them as 'dead text.' This research introduces a method to quantify and restore constraint adherence in black-box models.
Meta-LoRA: Efficient Cross-Domain LLM Personalization
Meta-LoRA enables LLMs to adapt to user preferences across different domains by learning a meta-adapter that generalizes personalization patterns, reducing the need for domain-specific fine-tuning.
Modular Prompt Optimization: Improving LLM Performance via Segmentation
Moving from monolithic prompt optimization to segment-level modularity allows for more precise, interpretable, and effective tuning of LLM instructions.
Moving Beyond Prompt Engineering: The Power of Context Engineering
Context engineering is the practice of curating and structuring the information environment provided to an LLM, moving beyond simple prompt phrasing to improve reasoning and reduce 'context rot'.
IBM Technology5 Best Practices for Building Reliable AI Agent Skills
AI agent skills are procedural knowledge files. To make them reliable, focus on precise triggers, domain-specific expertise, context efficiency, deterministic scripts for fragile tasks, and rigorous security vetting.
IBM TechnologyEscaping LLM Homogeneity with Meta-Persona Anchoring
To combat output uniformity in LLMs, use Meta-Persona Anchoring to define high-level cognitive constraints and Sequential Temperature Scaling to manage creative variance across multi-step reasoning chains.
Energy-Efficient Prompting: The Impact of Keywords on On-Device LLMs
On-device LLM energy consumption is highly sensitive to specific prompt keywords, meaning developers can optimize battery life and performance by selecting energy-efficient tokens.
Evals-Driven Development for High-Stakes Mental Health AI
SonderMind builds safe mental health AI by replacing generic model guardrails with a modular, clinician-led evaluation loop that treats clinical judgment as code.
AI EngineerBuilding Production-Grade Agent Evals: A Practical Framework
Reliable AI agents require a loop of iterative evaluation that prioritizes patterns over individual failures, starting with intuition-based 'vibing' before scaling to rigorous, rubric-driven golden sets.
AI EngineerAI Builder Essentials: Tokens, RAG, and Context Windows
LLMs operate on tokens—not words—and are inherently non-deterministic. To overcome training data cutoffs, use Retrieval-Augmented Generation (RAG) to inject real-time data, while managing context window limits and token costs to avoid inefficient 'token maxxing'.
Google Cloud TechSecuring Multi-Agent Systems with Model Armor
Protect multi-agent systems from indirect prompt injection, PII leaks, and malicious content by implementing Model Armor as a centralized security guardrail at every system boundary.
Google Cloud TechWhen to Fine-Tune vs. Use RAG and Prompt Engineering
Fine-tuning is no longer the default for customization; modern frontier models often outperform custom-trained ones. Prioritize RAG, context engineering, and agent skills before considering fine-tuning for specific bottlenecks.
The Steering Budget: Why Examples Outperform Prompt Knobs
When steering LLMs, providing concrete examples is significantly more effective than adjusting abstract system prompt 'knobs' or parameters, as examples provide clearer context for model behavior.
Getting Started with ChatGPT: A Practical Guide
ChatGPT is a conversational AI assistant designed to help with writing, brainstorming, and problem-solving. Success starts with simple chat-based tasks and evolves into structured workflows as you identify repeatable processes.
Scaling Model Robustness via Automated Red-Teaming
OpenAI developed GPT-Red, an automated red-teaming model trained via self-play, to identify vulnerabilities and adversarially train future models, resulting in significant improvements in prompt injection resistance.
Making LLM Self-Evolution Safe with Held-Out Selection
RSEA improves LLM agent performance by recursively evolving natural-language artifacts while using a strict held-out validation gate to prevent performance regression.
Building Great Agent Skills: The Missing Manual
To escape 'skill hell,' developers must treat agent skills as structured, maintainable code by optimizing triggers, minimizing context bloat, using 'leading words' for steering, and aggressively pruning irrelevant instructions.
AI EngineerImproving LLM Planning with Symbolic Feedback Loops
To solve LLM planning errors in long-horizon tasks, this framework uses symbolic verification to provide corrective, interpretable feedback, forcing the model to iteratively refine its plans.
Personality Prompting in Multi-Agent Teams: Impact vs. Task Structure
Personality manipulation in LLM agents significantly alters communication style but only degrades performance in open-ended or competitive tasks, while having negligible impact on structured coding tasks.
The Promptware Kill Chain: Securing AI Agents
Promptware is a new class of malware that exploits the lack of separation between instructions and data in LLMs. To defend against it, builders must adopt a zero-trust architecture, treating AI agents as untrusted, hostile runtimes rather than benign assistants.
IBM TechnologyShowing 30 of 285