Kurtis Kemple
Developer Strategy @ Slack (Agentic AI & Platform XP)
Virginia Beach, Virginia, United States
Actions
Kurtis Kemple is a formerly incarcerated tech leader whose extensive experience across software engineering, developer relations, platform experience, and agent design has made him a leading voice in the field. His work is unified by a relentless focus on clarity—whether that means making implicit system dynamics explicit through frameworks and programs, removing friction along the developer journey, or teaching developers, designers, and product managers how to build best-in-class agentic experiences.
Through his work at Integral Ad Science and Major League Soccer he built deep foundations in real-time analytics, ETL infrastructure, and delivering integrated experiences across digital and physical interfaces. Apollo GraphQL and AWS sharpened his understanding of developer-first product thinking, API infrastructure, and platform engineering at genuine scale. Slack and Salesforce brought it all together—putting him at the center of platform experience and agentic AI at the exact moment they became the most consequential challenges in the industry. Now he's channeling that accumulated expertise into writing as the author of Effective DevRel, releasing in May 2026 through Apress, with two more in the works—currently titled "Platform Engineering for AI" and "Agentic Experience Design."
Currently, Kurtis leads developer strategy for the Slack platform as Sr. Director of Developer Relations, where he focuses on agentic systems, experience design, and platform strategy. Outside of work, he pursues independent research at the intersection of mathematics and physical systems, street photography, riding his motorcycle where he shouldn't, and enjoying time with his family.
Area of Expertise
Topics
Agentic Self-Correction: Closing the Loop on Structured Outputs
Structured output from agents is easy to generate and hard to trust. Field types, nesting, formatting, interaction rules, and semantic expectations all have to line up—and when they don't, the failure modes are grim: silent degradation, an engineer patching it after the fact, or a customer seeing the breakage. None of that is acceptable once agents sit in real execution paths.
Sharper prompts and richer templates do not solve the problem. The answer is to close the loop—expose validation that matches actual system constraints, return violations in a form the model can act on, and let the agent revise until the output satisfies the rules or a defined fallback takes over. It moves agents from one-shot probabilistic generation toward constraint-satisfying systems that converge without a human in the execution loop.
That pattern is agentic self-correction.
The heart of agentic self-correction is a validation loop: generate, validate against a programmatic authoritative source, receive structured feedback on what failed, where, and why, and correct using that signal. Repeat until the output is valid or a maximum-attempts ceiling triggers predictable fallback behavior. The same shape applies wherever outputs must adhere to an acceptance criteria: UI definitions, configs, code, workflows, diagrams, and other structured artifacts.
Structural validity is only the first bar. Self-correction can extend into experience quality. Experiential constraints—readability, information density, interaction clarity, cognitive load, task alignment—sit alongside structural ones such as schema correctness, formatting validity, and required fields. The extended loop is generate, validate, evaluate, correct, and repeat. Validation enforces correctness; evaluation guides improvement. Shifting from strictly correcting invalid outputs to optimizing them as well.
Advocating for Agents: How Developer-Agent Dynamics are Rewriting the Rules of Enablement
The way developers interact with your platform is changing. Increasingly, they aren't working alone—they're working alongside agents that scaffold apps, read documentation, call APIs, and generate UI as part of the development process.
These agents create a new “shadow persona”: a second consumer of your platform that interprets documentation, invokes APIs, and often becomes the first interface between your platform and the developer.
Yet most platforms aren't designed for this new developer-agent dynamic.
This creates a new challenge for developer enablement. When a software architect asks an agent to explain the value proposition and concepts of your platform, can it access the context necessary to provide an accurate and relevant answer? When a developer asks an agent to implement an integration, does your ecosystem provide the tooling needed for the agent to produce a reliable outcome?
This talk explores how platforms can support the developer–agent pair through non-intrusive improvements along the developer journey. We’ll look at approaches such as turning documentation into agent-accessible context, enabling agent actions with specialized tooling, designing validation APIs for agent self-correction, capturing agent-specific friction in feedback loops, and redefining success metrics around the developer–agent workflow.
If you aren’t advocating for the agent, you’re no longer fully enabling the developer.
Kurtis Kemple
Developer Strategy @ Slack (Agentic AI & Platform XP)
Virginia Beach, Virginia, United States
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top