EdTech Tracker

← Coding lens

prompt template

technique judged 98% likely a named technique or architecture

First seen
2024-04-23
Independent sources
7
Articles
22
Last 4 weeks vs prior
0 vs 10

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
03.572024-W172026-W112026-W41
Table view
WeekArticlesSources
2024-W1711
2024-W2611
2025-W0211
2025-W3611
2026-W0921
2026-W1131
2026-W1911
2026-W3611
2026-W3711
2026-W4032
2026-W4172

In their words

Reason: Call your LLM endpoint (Ollama via LiteLLM, or a cloud model) with a fixed prompt template and max tokens.

Your response:""" ## Part 4: Prompt Optimization ### Automated Prompt Optimization python prompting/optimization.py from dataclasses import dataclass from typing import List, Callable import asyncio @dataclass class PromptCandidate: prompt: str score: float = 0.0 metadata: dict = None class PromptOptimizer: def init ( self, llm, evaluator: Callable[[str, str], float], # (prompt, expected) -> score

Prompt templates were the next small step.

AI Agent System Prompt Template: The 5 Blocks That Matter

Level 1: Unit Tests for Deterministic Parts # test_prompt_templates.py import pytest from myapp.prompts import format_rag_prompt , format_agent_prompt def test_rag_prompt_includes_context (): context = " The capital of France is Paris.

""" Model-Specific Tips GPT-4 / Claude Excellent at following complex instructions Handles long context well Good at structured output (JSON, YAML) Prefers explicit constraints Llama / Mistral (Open Weights) Benefits from more examples Needs clearer step-by-step Sometimes ignores negative constraints ("don't do X") Better with XML tags than markdown Small Models (7B and below) Few-shot critical Ke

Cache deterministic prompts If your application uses a static prompt template with variable placeholders, cache the rendered prompt before sending it to the model.

What You Get 120 production-ready prompt templates designed specifically for local LLMs—covering code scaffolding, refactoring, test generation, documentation, and debugging Context optimization guides to squeeze maximum quality from every token without bloated instructions Model-specific tuning tips for Llama-3, Mistral, and custom fine-tunes so you know exactly what works where Real-world workfl