← all topics

✏️ Prompt Engineering

Prompting patterns — few-shot, chain-of-thought, ReAct, structured output, prompt management at scale.

12 videos · prompt-engineeringevalsprompt-optimizationclaudecontext-engineeringai-coding

The workflow

flowchart LR
    A[Task definition] --> B[System prompt<br/>role + rules]
    B --> C{Pattern}
    C -->|Few-shot| D[Curated examples]
    C -->|CoT| E[Step-by-step]
    C -->|ReAct| F[Thought + action loop]
    C -->|Structured| G[JSON / XML schema]
    D --> H[Iterate on traces<br/>+ regressions]
    E --> H
    F --> H
    G --> H

Prompt engineering is engineering: version, test, regression-gate. The clever wording usually doesn't matter.

Key takeaways

Context artifacts (prompts, skills, agent.md) need the same generation, testing, observability, and versioning rigor we apply to code.
Iterative prompt engineering with structured XML context and a test-case eval harness in the Anthropic Console produces measurably better Claude outputs than vibe-based editing.
Replace manual prompt fiddling with an evaluator-in-the-loop optimizer agent that rewrites prompts until the judge score improves.
For most agent teams, eval-driven prompt learning with natural-language feedback beats RL on data efficiency and engineering cost.
Optimize prompts by feeding the LLM rich English feedback about *why* each failure happened, not just scalar scores or output diffs.
Become a 10x engineer by treating the LLM as a translation/word-simulation engine and using concrete habits like regeneration, response-editing, transcript summarization and ridiculous domain framing.

Videos (12)

Context Is the New Code — Patrick Debois, Tessl

Context artifacts (prompts, skills, agent.md) need the same generation, testing, observability, and versioning rigor we apply to code.

65.8K views · May 03, 2026

Building with Anthropic Claude: Prompt Workshop with Zack Witten

Iterative prompt engineering with structured XML context and a test-case eval harness in the Anthropic Console produces measurably better Claude outputs than vibe-based editing.

37.7K views · Aug 17, 2024

Prompt Engineering is Dead — Nir Gazit, Traceloop

Replace manual prompt fiddling with an evaluator-in-the-loop optimizer agent that rewrites prompts until the judge score improves.

24.9K views · Jun 27, 2025

The Unreasonable Effectiveness of Prompt Learning – Aparna Dhinakaran, Arize

For most agent teams, eval-driven prompt learning with natural-language feedback beats RL on data efficiency and engineering cost.

16.0K views · Dec 23, 2025

Build a Prompt Learning Loop - SallyAnn DeLucia & Fuad Ali, Arize

Optimize prompts by feeding the LLM rich English feedback about *why* each failure happened, not just scalar scores or output diffs.

12.1K views · Jan 06, 2026

10x Development: LLMs For the working Programmer - Manuel Odendahl

Become a 10x engineer by treating the LLM as a translation/word-simulation engine and using concrete habits like regeneration, response-editing, transcript summarization and ridiculous domain framing.

9.2K views · Aug 21, 2024

Principles for Prompt Engineering - Karina Nguyen (Claude Instant @ Anthropic)

Prompting Claude well means treating it like a person, structuring inputs with consistent XML tags, and iterating like creative writing.

8.8K views · Oct 20, 2023

Optimizing LLMs in Insurance with DSPy: Jeronim Morina

Treat LLM apps as compilable programs: define metrics on real production data, then let DSPy optimize prompts rather than hand-tweaking templates.

6.0K views · Feb 16, 2025

The Model Isn't Wrong—You're Just Bad at Prompting

Prompt engineering is still the cheapest lever — but reasoning models invert the old rules, preferring minimal prompts with encouragement to think longer.

2.9K views · Feb 22, 2025

The Coherence Trap: Why LLMs Feel Smart (But Aren't Thinking) - Travis Frisinger

LLMs feel intelligent because of coherence, not understanding — engineers should design and evaluate around that illusion rather than be fooled by it.

2.3K views · Jun 03, 2025

Prompt Engineering Tactics: Dan Cleary

Three cheap, research-backed prompt edits—multi-persona, 'according to', and emotional stimuli—measurably lift output quality with no code change.

1.3K views · Feb 05, 2025

Your LLM Ran Out of Knowledge — Now What?

For low-knowledge domains, encode expert heuristics as a rule library and route prompts to the right rule set before reasoning — wisdom rules in, reasoning model on top.

732 views · Feb 22, 2025