AI agents · How Founders Use AI
Prompt engineering, RAG, or fine-tuning: which one does my product actually need?
Work up the ladder: better prompts cost hours, RAG costs days and adds your own live data, fine-tuning costs weeks and only changes behaviour and style, not knowledge. Most teams that fine-tune could have gotten the same result from a cleaner prompt and better retrieval, so treat fine-tuning as a last resort for narrow, repeatable patterns at volume. The emerging umbrella skill is context engineering: deciding exactly what information lands in the model's window for each request.
On the AI map, 29 October 2026 Frontier modelsOpen-weight modelsDecision models
Go deeper18 sources
-
RAG vs Fine-tuning vs Prompt Engineering: The Complete Guide
Aakash Gupta (Product Growth) · Article · 2025
A PM-friendly decision guide with real cost and time estimates for each rung of the ladder.
-
RAG vs fine-tuning vs prompt engineering
IBM · Article · 2025
A neutral, definition-first explainer you can hand to any teammate.
-
Effective context engineering for AI agents
Anthropic · Article · Sep 2025
The lab's own framing of the successor skill to prompting: keep context informative yet tight.
-
Context Engineering for Agents
LangChain · Article · 2025
The complementary view from the biggest orchestration framework, with concrete patterns.
-
Context engineering: memory, compaction, and tool clearing (Claude Cookbook)
Anthropic · Guide · 2025
Runnable code for the context techniques the essays describe.
-
Model optimization (OpenAI docs)
OpenAI · Guide · 2025
OpenAI's own flywheel: evals feed prompts, prompts feed fine-tuning data, in that order.
-
Fine-tuning best practices (OpenAI docs)
OpenAI · Guide · 2025
What fine-tuning is actually for: repeatable patterns and output shapes, not new knowledge.
All 18 sources
-
Fine-tuning (OpenAI learn track)
OpenAI · Guide · 2025
The gentler learning path covering all four fine-tuning methods and when each applies.
-
Fine Tuning OpenAI Models: Best Practices
Parlance Labs · Guide · 2024
Practitioner war stories on when fine-tuning paid off and when it was resume-driven engineering.
-
Fine-Tuning vs RAG vs Prompt Engineering: When to Use What
Safoura Jolfaei · Article · Nov 2025
A concise engineer's take with the production reality that the three usually combine.
-
Fine-Tuning vs RAG vs Prompt Engineering
Analytics Vidhya · Article · Mar 2026
Fresh 2026 treatment from India's biggest data science community.
-
RAG vs fine-tuning vs prompt engineering: And the winner is...
K2view · Article · 2025
Argues the case for RAG as the default middle path, with enterprise examples.
-
Andrej Karpathy: Software Is Changing (Again)
Andrej Karpathy (YC AI Startup School) · Video · Jun 2025
The Software 3.0 keynote: prompting as the new programming, essential framing for this whole question.
Watch it here
-
Karpathy on Software 3.0: Software in the Age of AI
Latent Space · Article · Jun 2025
The annotated written companion to the keynote if you prefer reading.
-
Anthropic's Interactive Prompt Engineering Tutorial
Anthropic · Course · 2024
Nine hands-on chapters that take you from novice to competent prompter in a weekend.
-
Prompt engineering overview (Claude docs)
Anthropic · Guide · 2025
The living reference for every major technique: examples, XML structure, chaining, roles.
-
Using GPT-6: prompt guidance
OpenAI · Guide · 2026
OpenAI's own prompting guidance for its current models, at an address that moves with each new one.
-
Context Engineering for Long-Horizon Agents, with Harrison Chase
Sequoia Capital (Training Data) · Podcast · 2025
Where the prompt-vs-RAG-vs-fine-tune debate is heading as tasks get longer.