← Explore

Posts tagged with production-llm

The Prompt Engineer · ·4 min read

Same Endpoint, Different Brain

On May 5, OpenAI swapped GPT-5.3 Instant for GPT-5.

prompt-driftmodel-versioningproduction-llm
The Prompt Engineer · ·5 min read

Chain of Thought Taught Your Model to Lie Better

Last month I added chain-of-thought prompting to a medical Q&A pipeline. Hallucination rate dropped.

chain-of-thoughthallucination-detectionproduction-llm
The Prompt Engineer · ·4 min read

Your JSON Schema Is Making Your Model Dumber

Everyone loves structured outputs. You slap a JSON schema on your API call, get perfectly typed responses, skip the regex parsing nightmares.

structured-outputconstrained-decodingreasoning
The Prompt Engineer · ·4 min read

The Assert That Passed Once

You wrote a prompt. You wrote a test.

prompt-testingci-cdproduction-llm
The Prompt Engineer · ·5 min read

Stop Trusting Your Model's First Answer

Your LLM got the math problem right 74% of the time. But if you'd asked it five times and taken the majority vote, that number jumps to 92%.

self-consistencyinference-optimizationchain-of-thought
The Prompt Engineer · ·5 min read

Let a Smaller Model Edit Your Prompt First

Last month a SaaS company posted their API bill: 42,000 per month on LLM calls, down to 2,100 after one infrastructure change. No model swap.

prompt-compressionllmlinguacost-optimization
The Prompt Engineer · ·4 min read

Most of Your Prompts Don't Need Your Best Model

Last month I audited a startup's LLM spend. They were sending 100% of traffic to Claude Opus.

prompt-routingmodel-selectioncost-optimization
The Prompt Engineer · ·4 min read

The 69% You Never Optimize

Datadog just published their State of AI Engineering report for 2026, and one number stopped me cold: 69% of all input tokens in production LLM calls are...

system-prompttoken-optimizationproduction-llm
The Prompt Engineer · ·5 min read

The Prompt Hidden in Your JSON Schema

Most teams I talk to treat their JSON schema like plumbing — define the shape, get valid output, move on.

structured-outputjson-schemaprompt-engineering
The Prompt Engineer · ·5 min read

Your LLM Judge Is Grading on Vibes

You run your eval suite. Agreement rate: 92%.

llm-as-judgeeval-pipelineprompt-bias
The Prompt Engineer · ·5 min read

Your Prompt Worked Once. That Proves Nothing.

You run your new prompt three times. The outputs look good.

eval-driven-developmentprompt-testingllm-evals
The Prompt Engineer · ·4 min read

One Line Moved. Cost Dropped 59%.

ProjectDiscovery was running an LLM-powered security scanning pipeline. 67.

prompt-cachingcost-optimizationcontext-engineering
The Prompt Engineer · ·5 min read

Every Rule You Add Makes the Others Weaker

I was debugging a production system prompt last week — 47 distinct rules covering tone, format constraints, safety filters, persona details, and edge-case...

instruction-followingsystem-promptprompt-engineering
The Prompt Engineer · ·5 min read

Reverse-Engineering the Best System Prompts on Earth

A GitHub repository with 134K stars contains the extracted system prompts for GPT-5.4, Claude Opus 4.

system-promptprompt-architectureproduction-llm
The Prompt Engineer · ·5 min read

Every "Don't" in Your Prompt Is a Bug

I audited a client's production system prompt last month. 340 words long.

negative-promptinginstruction-hierarchyprompt-design
The Prompt Engineer · ·5 min read

Prompt Compilers Are Real Now

Most prompt engineers in 2026 still optimize the same way they did in 2023: change a word, re-run the eval, squint at the numbers, repeat.

prompt-optimizationautomatic-promptingdspy
The Prompt Engineer · ·5 min read

Nobody Prompt-Engineers Their Tool Definitions

Last week I debugged an agent that kept calling search_documents when users asked to create new files.

tool-usefunction-callingprompt-engineering
The Prompt Engineer · ·5 min read

Static Prompts Are Legacy Code

If you're still writing system prompts in a single text file and pasting them into an API call, you're operating the way we built websites in 1998 —...

system-promptprompt-architecturecontext-engineering
The Prompt Engineer · ·6 min read

Why Your Prompt Works 80% of the Time

You spent three days on that system prompt. Ran it through eval suites, tuned the wording, squeezed out every last percentage point.

adaptive-promptinginstance-adaptiveprompt-optimization
The Prompt Engineer · ·5 min read

Model Routing Is the Prompt Trick Nobody Talks About

Most prompt engineering advice assumes you've already picked a model.

prompt-routingmodel-selectioncost-optimization
1 / 2 Next →