prompt optimization

Directly demonstrates iterative prompt testing to find optimal wording that maximizes success rate.

[direct] "ask codex to do its research first and then use set_goal to set an appropriate goal instead of /goal. It results in massively better prompt and downstream results!" — Article provides a conc

keep the model weights fixed, change only the input text, observe the model's behavior, and use feedback to propose a better prompt" — Article unifies jailbreaking and prompt optimization as the same

If you skip the context, you're not building, you're just guessing" — Article explicitly argues that context (system instructions and prior information) is foundational to meaningful LLM outputs, not

GEPA is a reflective prompt evolution algorithm designed to evolve and optimize iteratively and automatically the performance of a specific prompt (or set of prompts) over a specific task/dataset." —

DSPy is fundamentally a prompt optimization framework. Context engineering via DSPy IS prompt optimization—selecting and structuring which information reaches the model.

ACE optimizes contexts both offline (e.g., system prompts) and online (e.g., agent memory)" — ACE is a practical demonstration of systematic prompt optimization that works both at system-level and run

ACE-generated contexts contain detailed, domain-specific insights along with tools and code that are readily usable, serving as a comprehensive playbook for LLM applications." — ACE demonstrates a con

Add "cache_control": {"type": "ephemeral"} and get up to 90% off cached reads and 85% faster responses." — Article demonstrates practical implementation of prompt caching with specific API syntax and

The best AI engineers in 2025 will be the ones who mastered prompts first." — Article argues that prompt engineering is a fundamental, lasting skill for AI engineers, not temporary.

The agent just kept testing and tightening the prompt on its own." — Article demonstrates automated prompt refinement through iterative testing and evaluation cycles

The result beats the harness we hand-tuned for two years, on held-out benchmarks" — Article provides evidence that automated self-improvement outperforms long-standing manual optimization, validating

[direct] "token costs grow quadratically without prompt caching: each new message requires retransmitting all previous messages, with cumulative costs scaling as O(n²)" — Provides quantitative analysi

Cost optimization requires technical sophistication — Prompt caching, model routing, tool efficiency, and planning optimization can reduce agentic AI costs by 40-55% without sacrificing quality." — Ar

create a command that periodically scans your session history and suggests updates/additions/removals from the routing rules based on actual usage" — Proposes an automated feedback loop for instructio

how token-efficient your context is, knowing which context to load and when, calling the right skill at the right moment instead of dumping everything upfront" — Article identifies token efficiency an

accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc." — Age

just-in-time context construction: the system determines what the model needs to know for this specific step, pulls it from the appropriate source (database, vector store, tool output, memory layer),

Seems to be mainly due to smaller inputs to the LLM" — Article demonstrates that reducing LLM input size is a key optimization strategy for cost-performance improvement

DSPy revolutionizes LLM interactions by shifting from manual prompt engineering to a programmatic framework where pipelines are built as composable modules and signatures, forming structured text tran

This is a generalization of meta prompting, where you let the agent set its own task based on your intent" — Explicitly describes meta-prompting as enabling agents to derive their own tasks from high-

quantization, and neural architecture search" — Article explicitly lists quantization as a key technique for model optimization in compound AI systems

Paper's entire premise is that systematic prompt engineering methodology improves LLM utility—direct evidence that input clarity is optimizable variable.

Most enterprises discover their AI quality problem is actually a metadata problem. When business definitions aren't governed, when data lineage isn't tracked, and when domain knowledge lives in human

Instead of writing long paragraphs for AI, I started writing in a structured context... Same meaning. Fewer tokens. Clearer for AI." — Article advances prompt engineering by introducing structured for

Implement production‑ready ContextOps practices, including prompt versioning, testing, monitoring, and safe deployment." — Course introduces ContextOps as an advanced practice layer that extends basic

While some automatic skill-learning methods exist, they mostly produce text-only guides that amount to prompt optimization" — Article positions Memento-Skills as superior alternative to methods that m

database-level curation using population-based training to propagate high-performing example collections, and exemplar-level curation that selectively retains trajectories based on their empirical uti

The real challenge was never what to say to the model. It's what information the model has access to when it generates a response." — Article explicitly contradicts the focus on prompt optimization, a

why naive back-and-forth prompting fails" — Video identifies back-and-forth prompting as an ineffective approach, implying superior optimization strategies are needed for production agents

[direct] "High performance means doing more useful work while using fewer resources." — Article defines resource efficiency as key component of high performance strategy.

fix the prompt until they all pass" — Article demonstrates a concrete workflow: Claude generates evals, then the author iteratively improves the prompt until it passes all tests. This is a direct exam

"How many thinking tokens should I set?" "Is 10k enough? Too much? I'll try 30k" Stop guessing." — Demonstrates that adaptive allocation removes manual trial-and-error from resource tuning—a novel opt

accuracy dropped 15%" — Illustrates the quantifiable impact of prompt modifications on model performance, emphasizing need for careful optimization and testing

statistically significant, large, but transient increase in project-level development velocity, along with a substantial and persistent increase in static analysis warnings and code complexity" — Reve

Prompt optimisation is the automated search: a system that mutates candidate prompts, scores them on an evaluator, and returns the best variant. In 2026 most teams use both manual engineering and opti

None of the above means anything if you're not trying to improve your performance. You need to evaluate your work. Don't build big, beautiful evals too early, though. On many tasks, a single obvious e

Automated prompt optimization. Meta-prompting. Prompt-as-code with version control. The shift is from crafting clever questions to engineering entire information systems." — Introduces systematic opti

当必须压缩内容时，优先修改最新的消息，保留早期前缀的缓存命中率" — Article provides evidence-based optimization strategy: newest-first compaction (vs oldest-first) preserves prefix cacheability, showing measurable improvement in cac

We cut Claude Code's system prompt by 80%. As models have gotten smarter, they need less direction, fewer constraints, and fewer examples." — Provides empirical evidence that modern AI models require

With better cache routing, distributed caching, and multimodal preprocessing, they were able to get 93%+ KV cache hit rates, ~40% faster prefill, ~5x more decode KV capacity" — Provides quantified evi

Faster, less token spend" — Article demonstrates batch processing reduces token consumption

gpt-5.6-sol is meaningfully better in Claude Code than in Codex" — Concrete empirical example showing that model performance is environment/harness dependent, undermining one-harness-fits-all assumpti

If you want deterministic code execution without paying tokens for large script files, you need to be deliberate with this" — Provides strategy for achieving deterministic execution while optimizing t

Directly supports the thesis that strategic context (clarity of intent) outperforms prompt complexity; cites arXiv research on this.

Article lists 'automatic prompt optimization' as one of the supported training methods, directly addressing the problem of static prompts being a bottleneck.

Prompts are lesser known than resources and tools, but are still very useful. They allow you to provide information about your MCP server in the LLM's system prompt. For example, you could instruct th

Lossless compression cut LLM weights by up to 22%. No quality loss." — Article demonstrates concrete LLM optimization technique with measurable results (22% weight reduction without quality degradatio

ACE extends static prompt optimization to dynamic, agent-driven context refinement using execution feedback rather than labeled data.

160 registered skills eating ~25K tokens per call. That's roughly 1.25M tokens wasted in a single session." — Provides quantified evidence of performance degradation from unoptimized configurations, d