Automatically generating our API docs using Effect Schema + OpenAPI
How we leverage Effect Schema and OpenAPI to create beautiful, interactive API documentation with zero maintenance overhead.
Introducing our white-labeled Slack integration
A fully white-labeled AI assistant that handles support directly in Slack, escalating cases to your support queue when needed.
Elliot speaking at Effect Days 2025
Elliot Dauber is giving a talk at the Effect Days conference on March 19-21.
From prompting to coding
Building reliable LLM-powered systems inevitably requires evolving from prompting to coding.
What Palantir gets right
On Palantir's approach to building a product that can scale to a wide customer base.
How do AIs “think”?
How reasoning traces can help AI agents be more transparent and engaging.
Building tailored RAG pipelines
How we built tailored RAG pipelines in close collaboration with a flagship customer for our Agent Assist drafting functionality.
Introducing email auto-replies
Our email auto-reply agents autonomously solve support tickets before they hit your queue.
Hiring our founding team
We don't hire fast, but when we do, we go all in.
Measuring customer effort score
Moving beyond traditional metrics to gain deeper insights into support quality and customer experience.
Introducing policy violation detection
Introducing real-time policy violation detection to help enterprises maintain compliance and build trust in their AI customer support agents.
Why we love whiteboards
The physicality of the medium makes the small wins all the more tangible and worth the daily grind.
How we mitigate downtime when LLM providers go offline
How Markprompt ensures uninterrupted service through robust fallback mechanisms and multi-provider redundancy when LLM providers experience outages.
Elliot’s talk at the Effect conference in San Francisco
Our founding engineer Elliot Dauber shares his experience using Effect to build reliable AI systems at Markprompt in his first conference talk.
Introducing voice agents
Voice agents bring the same intelligence and capabilities of text-based agents to voice interactions.
Evolving with model capabilities
Exploring how we balance optimizing LLM architectures for today's capabilities while staying adaptable to rapid model improvements.
Welcome Elliot!
Welcome to our Founding Engineer Elliot Dauber!
How Vercel decreased tickets by 31%
Vercel integrated AI into their support workflow. Their AI agent reduced human-handled tickets by 31%, allowing them to maintain high support standards while serving a growing customer base.
On building versus buying
Why the future of software isn’t about choosing between building or buying, but finding the right partner to build with.
On knowledge base debt
Like technical debt in code, knowledge base debt accumulates when support documentation becomes outdated, inconsistent, and difficult to maintain.