The Death of Developer Advocates — Stephanie Jarmak, Sourcegraph
Summary
Developer Relations (DevRel) is evolving from focusing solely on human developers to incorporating AI agents as primary users and recommenders. The core strategy must shift toward Generative Engine Optimization (GEO), ensuring that product documentation and tooling are machine-readable, highly discoverable in registries (like MCP), and directly address specific pain points encountered by autonomous agents.
Key takeaways
-
The Agent as a New User Persona
10:40
Agents interact with tools by calling APIs, reading documentation, and recovering from errors. They represent a critical new user base that must be measured for friction points (e.g., burning an entire turn on a guessed parameter) to improve the developer experience.
-
Measuring Agent Interaction and Friction
8:56
Benchmarking tools, such as CodeScaleBench, must track agent traces with and without product tooling. This data reveals where agents fail or struggle, allowing teams to fix underlying tool interaction issues.
-
Shifting Focus to GEO (Generative Engine Optimization)
12:22
The goal of DevRel is moving from Search Engine Optimization (SEO) to Generative Engine Optimization (GEO). Content must be structured, authoritative, and designed for agents to quote accurately when recommending a product.
-
DevRel as an Interdisciplinary Function
15:15
The role of DevRel is no longer confined to one department; it requires collaboration across Engineering (building agent interfaces/evals), Product (owning the end-to-end agentic experience), and Marketing (managing content funnels for agents).
Technical details
-
Agent Benchmarking & Tooling
536s
The speaker developed CodeScaleBench, a benchmark using hundreds of tasks reflective of the software development life cycle. This involved running agents with and without Sourcegraph's code navigation MCP tool to gather detailed traces.
-
Generative Engine Optimization (GEO)
742s
To improve agent recommendations, content must be structured for machine readability. Key actions include keeping documentation fresh, providing current examples, and ensuring the product is listed in relevant marketplaces/MCP registries.
-
Agentic Pain Point Identification
742s
A key finding was that when agents encounter specific organizational pains (e.g., 'breaking downstream services when we change shared libraries'), they often fail to recommend the correct tool, instead suggesting generic solutions like creating a wiki page.
Mentioned resources
- Sourcegraph Code Navigation MCP Tool
- CodeScaleBench
- MCP registries
Channel & topics
Watch on YouTube · Back to latest
This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.