Speeding up AI Coding Assistants using Deterministic Feedback
Every engineering leader has seen it: a senior developer is “in the zone”…then Slack pings, CI fails, or an AI suggestion derails everything.
Posts by Matt LeRay
Co-founder and CTO of Speedscale, expert in Agentic AI and cloud data warehousing. • 9 posts published
5 Tips for Agent-to-Model Mocking
The near-ubiquity of LLM systems in 2025 has changed the game in many ways. While Large Language Models have been around for some time...
Take Control of Your AI Routing: Mocking Claude, Gemini, and GPT-4
A few short years ago, the idea of using a Large Language Model was relegated to some specific models and implementations for a given industry or use case.
Catch Prompt Misfires Before They Burn Trust in LLM
Large Language Models (LLMs) are incredibly powerful, but they are also incredibly fragile.
AI Code: How AI Is Changing How We Write and Test It
As a software engineer, I’ve always leaned on a solid foundation of code reviews, unit tests, and CI pipelines to ensure quality.
4 Tips for Developing Model Context Protocol Server
The Model Context Protocol (MCP) is rapidly becoming the connective tissue for agentic AI systems and IDE tooling.
Six Lessons from Production gRPC
In the half-decade since gRPC became part of our production ecosystem, we’ve encountered a range of challenges and discovered a few hidden pitfalls that.
Modernize Test Data Management with Traffic Replay
In software testing or platform engineering, having realistic data is crucial. For years, teams have relied on Test Data Management (TDM) to copy entire...
Graphql vs GRPC : Key Differences
APIs have never had more connections and requests for data. With variable data types, changing programming languages, and a demand for high performance...
Try Speedscale free
Choose the desktop proxymock or the hosted cloud trial to get started.