LLM Classification vs Fine-Tuning vs Distillation: Which to Use?
A technical comparison of direct LLM classification, fine-tuning, and distillation/compilation — with a decision tree for choosing the right approach.
10 Jul 202611 min read
Blog
Insights & Guides
Deep dives on compiled AI, sub-100ms inference, and the economics of replacing LLM API calls.
The Complete Guide to Compiled Decision Intelligence
Compiled Decision Intelligence turns labelled decisions into fast, deployable classifiers. A guide to the three-stage pipeline, training process, and when to use it.
10 Jul 202611 min read
How to Connect Sparkient to Claude, Cursor, and VS Code via MCP
Set up Sparkient cloud MCP in Cursor or VS Code, or run the local edge MCP server in Claude Desktop and other stdio clients.
10 Jul 20268 min read
How to Run ML Classifiers Offline Without a Cloud API
Deploy ONNX classifiers to compatible Python hosts at edge and air-gapped locations, then benchmark local inference without network calls.
10 Jul 20268 min read
How to Build a Moderation API Without Any Labelled Data
Use an LLM as a teacher to generate candidate training data, then evaluate a moderation classifier without requiring a historical customer dataset.
10 Jul 20269 min read
How to Train a Classifier Using an LLM as Teacher
A technical deep-dive into the teacher-student pattern: use an LLM to generate candidate labelled data, then train and evaluate a task-specific classifier.
10 Jul 202610 min read
What Does Content Moderation Cost? A Practical Comparison Framework
Compare human review, free APIs, LLM calls, commercial services, and compiled models using your real traffic, quality requirements, and operating costs.
10 Jul 20268 min read
How to Evaluate Content Moderation in a Next.js App
Step-by-step guide to evaluating content moderation in a Next.js app with Sparkient through a cloud API route or local sidecar.
9 Jul 20268 min read
How to Add Decision Gates to a LangChain Agent
Build and evaluate a pre-action decision gate for LangChain agents using rules and a compiled classifier.
9 Jul 20268 min read
When Should You Replace an LLM Call with a Classifier?
A practical checklist for deciding when to evaluate a compiled classifier—and when to keep the current LLM path.
9 Jul 20269 min read
Content Moderation APIs in 2026: How to Compare Speed, Accuracy, and Cost
A practical framework for comparing current moderation options on quality, latency, cost, policy control, and media support.
8 Jul 20269 min read
ML Inference Latency Tiers: What to Measure in 2026
A practical framework for comparing rules, local models, compiled APIs, and live LLMs without treating provider latency as a constant.
8 Jul 20269 min read
How to Audit Your LLM Spending: A Developer's Guide
A step-by-step guide to finding LLM calls, measuring what each one costs, and identifying bounded decisions worth testing with a compiled classifier.
7 Jul 202610 min read
Why You Shouldn't Call an LLM in Your Request Handler
Putting an LLM call in your synchronous request handler creates unpredictable latency, cascade failures, and cost scaling problems. Here are the alternatives — and when each one applies.
7 Jul 20269 min read
I Need a Classifier but I Don't Have Training Data or an ML Team
Traditional ML classifiers need labelled data and a maintained training workflow. Here are four approaches for a project that does not have either yet.
6 Jul 20269 min read
I Built an LLM Prompt That Works — How Do I Deploy It Without the LLM?
If a prompt makes a bounded decision, test whether labelled examples can train a sub-100ms classifier for the normal runtime path.
4 Jul 20268 min read
My AI Agent Takes 3 Seconds Per Decision — Can a Compiled Path Meet Your Latency Target?
Trace an agent loop, identify bounded decisions, and test whether a compiled classifier improves its measured quality, latency, and cost profile.
3 Jul 20267 min read
I Need to Moderate Content but Can't Add a 1-Second API Call
Compare moderation approaches by measured quality and latency, including rules, hosted APIs, live LLMs, and compiled classifiers.
2 Jul 202611 min read
My Rules Engine Can't Handle Edge Cases but LLMs Are Too Slow
When rules miss edge cases and live models add latency, compare a three-stage pipeline on representative quality, latency, cost, and fallback tests.
30 Jun 20269 min read
I'm Spending $3K/Month on OpenAI for Classification — What Are My Options?
A cost breakdown of every alternative to GPT-4o for classification workloads: cheaper models, fine-tuning, open-source, and compiled classifiers.
27 Jun 20269 min read
My LLM Calls Are Adding 800ms to Every Request — How to Fix It
If a measured LLM call is your bottleneck, compare four options with illustrative timings, code, and workload-specific validation steps.
25 Jun 20269 min read
From Prototype to Production: What Breaks When You Scale AI Features
An illustrative scaling scenario for finding latency, concurrency, reliability, and cost limits before traffic exposes them.
23 Jun 20269 min read
5 AI Architecture Anti-Patterns to Load-Test Before Scale
Five architecture patterns that can create latency, concurrency, reliability, or cost problems as traffic grows—and how to test and replace them.
20 Jun 202610 min read
Why Your API Is Slow: Finding the LLM Bottleneck in Your Stack
Your API response time jumped from 50ms to 900ms. Here's how to find and fix the LLM call hiding in your request handler.
16 Jun 20268 min read