How does a DSPy signature differ from a prompt template?

Attempt it

A signature is a typed declaration of input fields → output fields with short semantic descriptions, e.g. class GenerateAnswer(Signature): question = InputField(); answer = OutputField(desc='short factual answer'). A prompt template is a literal prompt string with placeholders. The crucial difference: the developer never writes the final prompt. DSPy's compiler reads the signature plus the chosen module (Predict, ChainOfThought, ReAct) and produces a prompt plus demonstrations bundle optimised against a metric. The signature declares intent; the template prescribes exact text.

Your answer

Quick reference

TL;DR

A DSPy signature declares input and output fields with semantic descriptions; the compiler turns it into an optimised prompt, while a template is the literal prompt you wrote.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine comparing a recipe to a meal order. A meal order at a great restaurant says 'I want a light starter and a hearty main, no dairy.' The kitchen translates that intent into actual dishes that change with the season and the cook's experiments. A recipe spells out 'mix 200g flour with 100ml milk, bake 30 minutes'. Change anything and the recipe is no longer the recipe. A DSPy signature is the meal order: you say what you want as input and output. A prompt template is the recipe: you spell out the exact words. The kitchen, the DSPy compiler, does the cooking, and it can try new dishes against your taste test.

Key concepts

LLM Frameworks Prompt Engineering

Quick scan · 2–4 min

Everything important, quickly.

7 min: signature versus template, the compiler step, modules, optimisers, metric-driven adaptation across model upgrades, when DSPy is wrong.

Code example

python

import dspy

# 1) Signature: declare the contract
class GenerateAnswer(dspy.Signature):
    """Answer a factual question concisely."""
    question = dspy.InputField()
    answer   = dspy.OutputField(desc="a short factual answer")

# 2) Module: choose the reasoning structure
qa = dspy.ChainOfThought(GenerateAnswer)

# 3) Metric + small trainset feed an optimiser
def em_metric(example, pred, trace=None):
    return example.answer.strip().lower() == pred.answer.strip().lower()

from dspy.teleprompt import BootstrapFewShot
compiled_qa = BootstrapFewShot(metric=em_metric).compile(qa, trainset=trainset)

print(compiled_qa(question="Capital of France?").answer)

Side-by-side

Aspect	DSPy signature	Prompt template
Who writes the prompt	DSPy compiler	Developer
Form	Typed input/output fields with descriptions	Literal string with placeholders
Optimisation	Search over demonstrations and rewrites via metric	Hand-tuning by re-running and editing
Model-switch cost	Recompile against new model	Re-engineer prompt manually

Real-world examples

Real products, models, and research that use this idea.

STORM (Stanford) uses DSPy signatures plus optimisers to compile multi-stage research-report generation
Several Anthropic and OpenAI internal eval pipelines adopt DSPy patterns to make extraction prompts portable across model versions
DSPy is the reference framework in academic papers on automatic prompt optimisation (MIPROv2, COPRO) shipping in 2025-26

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow do BootstrapFewShot and MIPROv2 differ as optimisers?

Sign in or go Pro to see the approach for this follow-up.

QWhat changes when you swap a Predict module for ChainOfThought on the same signature?

Sign in or go Pro to see the approach for this follow-up.

QHow would you migrate a hand-engineered prompt suite to DSPy?

Sign in or go Pro to see the approach for this follow-up.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.