---
name: llm-selection-by-task
description: Use when choosing which model handles a specific step in an AI pipeline or feature.
---

# LLM Selection by Task

## Overview

One flagship model for everything is expensive and slow. **LLM selection by task** assigns each step the smallest model that clears the bar: fast models for routing and classification, stronger models for synthesis and reasoning.

## When to Use

- Designing a multi-step pipeline (retrieve → classify → generate)
- Copilot feels slow or costly on simple requests
- Eval shows a cheap tier passes on subset of tasks
- Skip when a compliance rule mandates one approved model

## Quick Reference

| Task type | Typical tier |
|---|---|
| Intent routing / classification | Fast, cheap |
| JSON extraction from short text | Fast with schema validation |
| Long-form synthesis, multi-doc reasoning | Strong |
| Code generation across files | Strong + IDE agent |
| Embeddings | Dedicated embedding model |

## Implementation

1. **List pipeline steps** — each gets its own model decision.
2. **Define pass criteria per step** — not one global "quality" score.
3. **Benchmark 2 tiers per step** on 30+ real inputs.
4. **Assign models in router config** — role-based, not hardcoded per route file.
5. **Log model ID per request** — so you can prove the split works in production.
6. **Re-eval when providers ship new tiers** — the map changes quarterly.

## On This Portfolio

Admin settings pick copilot provider/model; server code resolves via a single router (`copilot` role). Assistant retrieval and generation can use different cost profiles — the task picks the tier, not habit.

## Common Mistakes

- Using the strongest model for boolean classification
- Selecting models from leaderboard hype, not your eval set
- Changing model in one file while ten routes still call the old default

## Related Skills

- Cost-latency-accuracy tradeoff analysis
- Provider-agnostic abstraction layer design
- Latency benchmarking across providers