Prompt Engineering
4 in the last 7 days (+33% vs. prior week)Articles
21Reasoning Budgets: When Extra Thinking Tokens Pay Off and When They Only Add Latency
Letting a model think longer before answering can help on some tasks and do nothing on others. Match the budget to the task, and verify it with your own eval.
Where You Put Things in a Long Prompt: Placement of Documents, Instructions, and the Question
With large inputs, the order of the pieces is a prompt-design decision you can test, not a formatting detail.
Retrieved Text Is Data, Not Instructions: Limiting Indirect Prompt Injection in RAG and Agents
Any text your pipeline fetches can contain instructions aimed at your model. You can't filter them all out, so design so that obeying one costs little.
Conversation History Compaction: Rolling Summaries That Don't Lose Commitments
A long chat or agent session eventually outgrows its context. How you compress it decides whether the model remembers what it promised.
Order Your Prompt for the Cache: Stable Prefix First, Volatile Content Last
Provider-side prompt caching only pays off if the front of your prompt is byte-identical across requests. A few layout rules decide whether you get the discount or silently never hit it.
Delimiters Are Cheap Insurance: Separating Instructions, Data, and Examples in a Prompt
A prompt that mixes your instructions with the text it should process invites misreadings. Consistent section markers fix most of them for almost no cost.
Majority Voting for LLM Answers: When Sampling Several Times Beats Rewriting the Prompt
Self-consistency reduces random errors, and the vote split is a useful routing signal, but it cannot fix a prompt that is wrong the same way every time.
Bisecting a Failing Prompt: Shrink It Until the Bug Has Nowhere to Hide
When a 2,000-token prompt misbehaves, reading it harder rarely helps. Delta debugging does: remove pieces until you find the smallest prompt that still fails.
When Your Prompt Gives Two Instructions That Collide: Write the Precedence Rule
Long prompts accumulate rules that conflict in edge cases. If you don't state which one wins, the model picks, and it won't pick consistently.
Evaluating Summaries by Claims, Not Vibes: Separating Faithfulness From Coverage
A single quality score hides whether a summary is wrong or merely incomplete. Decompose the check into claims and key points instead.
'Not Stated' Is an Answer: Designing Extraction Prompts That Don't Invent Missing Fields
Models asked to fill a schema will fill it. Give them a legitimate way to say the value is absent, and design the downstream code to treat that as data.
Checking Citations Mechanically: Verifying That a RAG Answer's Quotes Really Exist in the Source
If your model quotes its sources, you can verify the quotes with ordinary string matching, which catches a whole class of fabrication for almost no cost.
Dynamic Few-Shot Selection: Choosing Examples Per Request Instead of Per Prompt
A fixed set of examples is a guess about every future input. Selecting examples at request time lets the prompt adapt, but it brings its own failure modes.
Negative Examples in Prompts: When Showing the Model What Not to Do Backfires
Telling a model what to avoid can anchor it on exactly that behavior. When negative examples help, when they hurt, and what to write instead.
Building a Shared Prompt Library Without It Turning Into Tribal Knowledge
Once more than one person is writing prompts for the same product, copy-paste drift sets in fast. A few concrete conventions keep a prompt library usable instead of becoming a graveyard of near-duplicate files.
Structured Output, Compared: JSON Mode, Function Calling, and Constrained Decoding
Three ways to force an LLM into a schema look similar from the outside. They fail differently, and that difference should drive which one you pick.
Why Prompts That Work in English Quietly Fail in Other Languages
A prompt validated only on English test cases carries assumptions about tokenization, formatting, and register that don't automatically travel — and the failures rarely look like failures.
Lost in the Middle, Found in Testing: Why Context Document Order Changes Your RAG Answers
Where you put a retrieved passage in the prompt can change the answer. Here is what the research found and a cheap test to run on your own pipeline.
Where You Put an Instruction Matters As Much As What It Says
Long-context prompts don't treat every line equally — models attend more to the start and end of a context window than the middle, and that asymmetry has real engineering consequences.
Multi-Turn State: What Breaks When Your AI Feature Moves From Single-Shot to Conversational
The API remembers nothing, so your code owns the conversation. Here is what accumulates, what breaks, and what to decide on purpose.
Signal
No signals yet
Signals related to this topic will appear here as new intelligence is published.