---
title: "DSPy"
category: "companies"
aliases: ["DSPy"]
website: "https://dspy.ai/"
sourceLabels: ["Official speaker roster", "Official conference schedule", "Public company site", "Automated company profile fetch"]
---
# DSPy

## Overview
DSPy is represented at AI Engineer World's Fair 2026. Its public site describes it this way: The framework for programming—rather than prompting—language models.

## Background
The official speaker roster connects DSPy to Maxime Rivest. The public company site was discovered by domain-guess and fetched for homepage metadata.

## Conference Relevance
DSPy matters to this wiki through 1 official speaker(s) and 1 scheduled session(s), including: The Unreasonable Effectiveness of Separating the Task from the Model.

## Conference Sessions
- [[2026-07-01-maxime-rivest-the-unreasonable-effectiveness-of-separating-the-task-from-the-model]] - The Unreasonable Effectiveness of Separating the Task from the Model (2026-07-01, 9:40am-10:00am)

## Connections
- [[maxime-rivest]] - Core Contributor

## Sources
- [DSPy](https://dspy.ai/)

## Evidence Graph
This evidence graph summarizes how this organization appears across the conference source graph: scheduled sessions, linked videos, transcripts, and slide-derived evidence.

### Linked Sessions
- [[2026-07-01-maxime-rivest-the-unreasonable-effectiveness-of-separating-the-task-from-the-model|The Unreasonable Effectiveness of Separating the Task from the Model]]

### Media Signals
- `youtube-I2cbIws9j10` — 91,792 transcript words; 7 slide-derived text signals
- Transcript signals for `youtube-I2cbIws9j10`: code, model, back, system, well, first, today, even.
- Slide-derived themes for `youtube-I2cbIws9j10`: context, window, selects, response, facts, retry, coerce, rollback.
- Evidence links for `youtube-I2cbIws9j10`: [[youtube-I2cbIws9j10]], [[youtube-I2cbIws9j10-transcript]], [[youtube-I2cbIws9j10-slides]], [[youtube-I2cbIws9j10-dense-slides]]

## Notes
- Automated company profile fetch status: fetched.

## Evidence Boundary
Official roster and schedule facts are treated as canonical for conference participation. Public company sites, documentation, and professional profiles are supporting context used to explain what the organization does and why it is relevant.