[CuriouslyC]

The article doesn't really give helpful advice here, but please don't vibe this.

Create evals from previous issues and current tests. Use DSPy on prompts. Create hypotheses for the value of different context packs, and run an eval matrix to see what actually works and what doesn't. Instrument your agents with Otel and stratify failure cases to understand where your agents are breaking.

[typpilol]

How hard is dspy to setup?

Isn't it a programming language type thing?

Can you even integrate that into an existing codebase easily?

[CuriouslyC]

It's pretty straightforward, different optimizers have different requirements. Some require example inputs/outputs, others will just optimize on whatever you've got. You can use codex/claude code to set it up in order to bootstrap quickly, they're decent at it.

[koakuma-chan]

Does dspy support structured outputs?

[ijk]

Yes, I was using it for structured outputs before the dedicated structured outputs got their act together.

[CjHuber]

Yes using signatures with types

[wanderingmind]

Otel meaning open Telemetry? Do they have special capability for tracking agents?

[CuriouslyC]

Yes, there is an otel standard for agent traces. You can instrument agents that don't natively support Otel via bifrost.