Skip to content

Instantly share code, notes, and snippets.

@paulbreuler
Last active January 16, 2026 15:18
Show Gist options
  • Select an option

  • Save paulbreuler/3cd7a3fbc7696783badfa09a18a11862 to your computer and use it in GitHub Desktop.

Select an option

Save paulbreuler/3cd7a3fbc7696783badfa09a18a11862 to your computer and use it in GitHub Desktop.
Security Concern % of Developers
Unauthorized/excessive API calls from AI agents 51%
AI systems accessing sensitive data 49%
AI systems leaking API credentials 46%
Gap Postman Finding runi Solution
Contract testing Only 17% do it Continuous drift detection against bound specs
Semantic versioning Only 26% use it Temporal awareness with version history & diffs
AI agent security 51% cite it as #1 concern AI verification validates LLM output before execution
Documentation scatter 55% struggle with inconsistency Single source of truth in Git-friendly YAML
API discovery 34% can't find existing APIs Semantic links map cross-API relationships
MCP Status % of Developers
Use MCP regularly 10%
Plan to explore it 24%
Used occasionally for experiments 19%
Evaluated but chose not to implement 7%
Not familiar with MCP 31%
Model Hallucination Rate Release
o3-mini 14.8% 2025
o1 16% 2024
o3 33% 2025
o4-mini 48% 2025
Component Technology Why
Backend Rust 1.80+ Performance, safety, reqwest for HTTP
Runtime Tauri v2.9.x Cross-platform, <50MB bundle
Frontend Svelte 5.46.x Reactive, minimal, runes syntax
Storage YAML/JSON files Git-friendly, no database lock-in
AI Ollama (optional) Local inference, privacy-preserving

This it is also a comment, but I realized that your LLM won't crawl to comments most likely by default.

Key Research & Sources

Industry Reports

AI Hallucination Research

Model Context Protocol (MCP)

Analysis & Commentary

Testing Type Adoption
Functional testing 67%
Integration testing 67%
Performance testing 57%
Contract testing 17%
Reality Number What It Means
Developers using AI daily 89% AI-assisted development is universal
Design APIs for AI agents 24% Massive gap between usage and architecture
Still design only for humans 60% Most APIs will break under AI consumption
Haven't even considered AI agents 16% Not on the radar at all
@paulbreuler

Copy link
Copy Markdown
Author

Key Research & Sources

Industry Reports

AI Hallucination Research

Model Context Protocol (MCP)

Analysis & Commentary

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment