Topic

AI and agents

Engineering, operating and evaluating AI systems, coding agents and model infrastructure.

Blog posts
160
Explore this topic
02

What are you trying to do?

Choose a reading sequence, from the initial decision to implementation and verification.

Coding agents and developer tools

Improve repository context, isolate work, manage skills and verify generated code.

  1. The Bottleneck Was Never Intelligence. It Was Context.
  2. Git Worktrees vs Jujutsu for AI Coding Agents: 2026 Decision Guide
  3. WikiSkill: How Agents Evolve SKILL.md from Experience
  4. QA for AI-Generated Code

Evaluation and production operations

Design the workflow, enforce authorization, budget evaluation and define rollout gates.

  1. AI Agent Design Patterns: Start Simple, Verify Actions
  2. Enterprise MCP Authorization Architecture
  3. When Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge
  4. AI Agent Pilot in 30/60/90 Days

Local AI and deployment

Compare APIs with local inference, budget operations and assess hardware constraints.

  1. When Local Models Beat APIs: A Break-Even Calculator for EU Companies
  2. Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off
  3. Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.

Memory, RAG and company knowledge

Choose the retrieval architecture, estimate costs and verify permissions and freshness.

  1. RAG vs Fine-Tuning vs Long-Context 2026
  2. What an Internal AI Assistant Actually Costs in the DACH Region (2026)
  3. RAG Production-Readiness Checklist for EU Companies

Models and routing

Understand decision models, compare providers, check calibration, then plan a pilot.

  1. OpenAI Decisions API: Confidence, Refusals and Routing
  2. Cloudflare Clef vs Jev: Pricing, Benchmarks and Migration
  3. AnyJev: LLM Calibration and Option-Order Bias
  4. AI Agent Pilot in 30/60/90 Days

Explore this topic

80 posts

Agent engineering

Coding agents, MCP, context systems, evaluation and the controls required for dependable automation.

Collection →
80 posts

Models and infrastructure

Model selection, inference economics, local deployment, compression and serving architecture.

Collection →

Start here

Latest in this collection

Two overlapping waveforms illustrate conversational timing in voice AI AI & Agents

Cue Turn Detection: Phone Numbers, Benchmarks and Limits

A pause is not a finished phone number. What Pype’s Cue v1 improves, what the benchmarks measure, and how to test correct, confirmed capture.

Kevin Riedl
Read
Wavect editorial illustration for RTK 1.0 token filtering and evaluation AI & Agents

RTK AI 1.0: Real Token Savings, Setup and Licensing

RTK 1.0 goes beyond shell-output filtering. Understand the 1.0.1 release, license split, proxy limits and the difference between a smaller transcript and a lower bill.

Kevin Riedl
Read
Wavect editorial header for Agent Mesh, with a shield representing controlled access to tools AI & Agents

Google SAM is now Agent Mesh: MCP tools across machines

Connect approved tools across machines. Understand the control plane, signed EU labels and the checks a useful first pilot should pass.

Kevin Riedl
Read
Layered turquoise geometry representing an Anatomy illustration assembled from editable parts AI & Agents

Anatomy for Claude Code: Interactive SVGs for Documentation

Turn a technical explanation into a figure readers can explore. Install Anatomy, choose HTML or React, and check the model before embedding it in your docs.

Kevin Riedl
Read
Layered document cards representing EdgeQuake's PostgreSQL knowledge store AI & Agents

EdgeQuake: PostgreSQL GraphRAG for MCP agent memory

Connect document relationships to your agents. A v0.34.0 review of PostgreSQL deployment, MCP access, local model roles and the LightRAG benchmark.

Kevin Riedl
Read
Three ternary weight values, minus one, zero and plus one, connected to a CPU AI & Agents

BitNet on CPU: 2B4T, real RAM needs and the 100B claim

Which BitNet model can you download, and what fits your CPU? Separate the 100B benchmark, 0.4 GB metric and 1.19 GB file, then test a real task.

Kevin Riedl
Read

Complete article directory

  1. Cue Turn Detection: Phone Numbers, Benchmarks and Limits
  2. RTK AI 1.0: Real Token Savings, Setup and Licensing
  3. Google SAM is now Agent Mesh: MCP tools across machines
  4. Anatomy for Claude Code: Interactive SVGs for Documentation
  5. EdgeQuake: PostgreSQL GraphRAG for MCP agent memory
  6. BitNet on CPU: 2B4T, real RAM needs and the 100B claim
  7. SuperPenguin: AI Cost per PR, Customer and Feature
  8. Claude Dashboards + Motion: From KPIs to Video
  9. OpenAI Intelligent UI vs OpenUI: Generative UI for Business Apps
  10. Wally by RunAnywhere: Cost per Accepted Coding Task
  11. Reducto for German Invoices: Measure Human Review Effort
  12. OpenAI Decisions API: Confidence, Refusals and Routing
  13. Claude Model Router: What Switches the Model, and When?
  14. Cloudflare Clef vs Jev: Pricing, Benchmarks and Migration
  15. Context Language Models vs Compaction: What to Pilot
  16. Caveman 3.0 for Claude Code: Local Input Compression, Recovery and Benchmarks
  17. LiteLLM Lens: Agent Trace Analysis with SQL and APIs
  18. SmythOS Studio Self-Hosting: Docker Setup, Costs and Limits
  19. DeerFlow 2.0: Docker Setup, Sandboxes and Memory
  20. CLM-8B Self-Hosting: vLLM, Action Cache and Verifiers
  21. AnyJev: LLM Calibration and Option-Order Bias
  22. LiteAgents SDK: Per-Turn Routing, Setup and Migration
  23. mcp-memory-service: Shared Memory for Claude Code and Cursor
  24. Claude Opus 5.5: Best Uses, Prompts and Effort Settings
  25. Laya and Jev for Business: 6 Practical Workflows
  26. Laya vs Jev: What the Benchmarks Mean for AI Startups
  27. Google AX: Suspend/Resume, Restart Costs and Self-Hosting
  28. WikiSkill: How Agents Evolve SKILL.md from Experience
  29. Tencent Octop Review: What Builders Actually Get for Free
  30. Wigolo Review: Local Web Intelligence for AI Agents
  31. Jev AI Review: Decision Models for Agent Workflows
  32. Supermemory: AI Agent Memory, RAG and Local Setup
  33. AI Agent Design Patterns: Start Simple, Verify Actions
  34. Claude Mods: Setup, Function Hooks and Security
  35. Voicebox: Local Voice Cloning, Dictation and MCP Setup
  36. Valyu’s 0.6B Multi-Agent Router: Results, Limits and When to Train One
  37. OpenAI Agents API Review: Migration, Costs and Data Controls
  38. Spotify shunt Review: Setup, Savings and Limits
  39. OpenBot Review: Self-Hosted AI Coworkers, Costs & Controls
  40. SwarmLLM Review 2026: Browser P2P LLM Inference Across Phones and Laptops
  41. Ramp Inspect Architecture 2026: Background Coding Agents at Scale
  42. Model Hardware Standard: Enterprise Guide to Physical AI
  43. Fonio AI Review 2026: Pricing, API, GDPR & Build vs Buy
  44. Mosaic (YC S26) Review: Shared Memory for Team AI Agents
  45. Ripwire Review 2026: AI Repo Context Without Embeddings?
  46. Atomic Multi-File Edits for AI Coding Agents: The Semaprax Lesson
  47. Phonely Alma Review: Is the Voice LLM Ready for Production?
  48. Utopia Review: Temporal Knowledge Graph for Enterprise
  49. AI Agent Knowledge Transfer: Use Frontier Models Once, Then Scale Cheaper
  50. claude-rotate: One Proxy for Multiple Claude Max Accounts
  51. NVIDIA PAIR Review: Local AI Routing and the AMD Gap
  52. Feynman Review: Is This Open-Source AI Research Agent Ready for Teams?
  53. Obscura Browser Review: Claims, Limits and Production Fit
  54. Claude Code Design System: 4 Parts for On-Brand UI
  55. Tencent Hy4 Preview Review: Is the 1M-Context Coding Model Worth a Pilot?
  56. PageLM Review: Self-Hosting and Commercial Use
  57. ChatGPT Can Now Log In Without Seeing Your Password
  58. M6 Mac mini vs M5 Mac Studio for Local AI: Buyer's Guide
  59. AI Agent Harness, Explained: The Reliability Layer Around an LLM
  60. FreeToken AI Review: Run Frontier MoE Models on Consumer GPUs?
  61. Darkbloom AI Review: Private Inference on Idle Macs
  62. Ox Alpha Revealed as GLM-5.3-Flash: What Changed
  63. Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust
  64. LangChain Deep Agents Review: Is the Agent Harness Ready for Production?
  65. Pika Audio Models API Pricing: Is SFX Really 20x Cheaper?
  66. Thunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide
  67. OpenViking Review: Filesystem Memory for AI Agents
  68. LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit
  69. AirLLM on 4 GB VRAM: How Layer-Wise Inference Really Works
  70. TrueForge Review: Is the Open-Source Agent Harness Production-Ready?
  71. Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks
  72. Qwen3.8-27B: Self-Hosted Computer-Use Agents Without Exporting Screenshots
  73. Localized URL Slugs vs hreflang: Why We Keep One English Slug
  74. Can an AI Agent Use Your Product, or Only Read About It?
  75. Graft Review 2026: Do Agent Repo Maps Belong in Git?
  76. Codag for Coding Agents: Tool-Output Compression and Cost
  77. Smarter Token Usage: Measure Cost per Accepted Coding Task
  78. DeepSeek Harness Review: Is the Plugin Stack Production-Ready?
  79. Netflix's vLLM and Triton Stack: 7 Production Lessons
  80. OpenSandbox Review: Is Self-Hosting Worth It?
  81. Transformers.js Browser AI: When Local Inference Belongs in Your Product
  82. Cloudflare Kitesurf Review: Cost, Limits and Production Fit
  83. GitHub Spec Kit Review: Is It Worth the Process?
  84. Internal AI Agent Marketplace: A 2026 Enterprise Build Guide
  85. How to Self-Host LiteLLM in Production: 2026 Guide
  86. AI-Ready Company Wiki: Architecture and Build Guide
  87. Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide
  88. Does Claude Watermark Text? The 2026 API Answer
  89. OpenKB Review: Knowledge Compiler vs RAG
  90. Unsloth Desktop Review: A Private Local AI Workstation?
  91. NeMo Switchyard 0.2: Agent Model Routing Without Training?
  92. Firecrawl AnyDoc Review: 14 Formats to Markdown
  93. MCP Cloud vs Manufact Cloud: MCP Hosting Guide
  94. Muse Glimmer 30B: Is Meta's Local Agent Model Production-Ready?
  95. How to Make AI Writing Sound Human with Agent Skills
  96. NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?
  97. OmniRoute AI Routing: Setup and Production Checklist
  98. Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026
  99. Hyperagent Review: Cloud AI Agents Without a Server
  100. Gemini Robotics 2: Whole-Body Control and the Pilot Decision
  101. Hark Handoff Review: The Agent That Actually Clicks
  102. Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?
  103. pdf-inspector Review: Route PDFs Before OCR
  104. Agent Reach Review: Costs, Security and Real Limits
  105. Cloudflare Wallets for AI Agents: What Is Live?
  106. Local Multimodal AI Coding Assistant: Voice, OCR and Privacy
  107. DeepSeek V4 Flash 0731 on One AI PC: What Actually Works?
  108. YC QM Agent Review: Is Quartermaster Ready for Work?
  109. jcode vs Claude Code: Is the Rust Harness Worth Switching To?
  110. Lightpanda Browser for AI Agents: Production Guide
  111. Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?
  112. Multi-Model AI Coding Agent Stack: A Team Buying Guide
  113. Is MCP Stateless Now? Your Server Migration Checklist
  114. MCP Is Not a Security Boundary: Protect Agent Data
  115. Fine-Tune Gemma 4 Free with Unsloth and Colab
  116. Can AI Agents Talk to Each Other? A Band Setup Guide
  117. Taalas HC1 Review: Is a Hardwired LLM ASIC Worth It?
  118. LeanCTX Technical Field Report: 64.1% Less Context
  119. llmfit Guide: Which Local LLM Fits Your Hardware?
  120. CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code
  121. Miso TTS Self-Hosted vs API: Cost, Latency and VRAM Reality
  122. Enterprise MCP Authorization Architecture
  123. Compress RAG Vectors to 2 Bits: Is Data-Oblivious Quantization Production-Ready?
  124. LMCache Reported 13.7x Lower Mean TTFT with a Shared KV Cache
  125. Lossless LLM Weight Compression vs 8-bit GGUF: What Is Ready for Production?
  126. OpenAI Eval Sandbox Escape: 12 Controls Before You Test a Cyber Agent
  127. Meterless Review 2026: Is This AI Agent Context Layer Ready?
  128. NVIDIA Nemotron 3.5 ASR: Is Free Self-Hosted STT Ready for Voice Agents?
  129. Claude Code vs OpenCode: Which Costs Less for a Team in 2026?
  130. Kimi K3 for EU Companies: API Cost, Data Risk, and a Pilot Plan
  131. Mesh LLM Review: Can One Large LLM Run Across Multiple Computers?
  132. Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?
  133. Bonsai 27B Review: Can a 27B LLM Really Run on a Phone?
  134. Soofi S: Is Germany's Sovereign LLM Ready for Business?
  135. AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days
  136. T3MP3ST Review 2026: Can It Replace a Penetration Test?
  137. Colibri Runs GLM-5.2 on Consumer Hardware. Here Is the Catch.
  138. Open Knowledge Format (OKF): The Enterprise Guide
  139. AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills
  140. When Local Models Beat APIs: A Break-Even Calculator for EU Companies
  141. LLM Cost Calculator 2026: Cost per Task, Not Cost per Token
  142. Pxpipe Review: Can Images Cut Claude Code Token Costs 60%?
  143. Cheaper Per Token Can Still Cost More Per Task
  144. How to Use Claude Fable 5.1 in Claude Code
  145. Anthropic Says No Open-Weights Ban. The Cost War Is Still Real.
  146. What an Internal AI Assistant Actually Costs in the DACH Region (2026)
  147. LLM Gateways Compared 2026: LiteLLM vs OpenRouter vs Portkey vs RouteLLM
  148. Self-Hosting LLMs in the EU: When Open Weights Actually Pay Off
  149. Open-Weight LLMs 2026: DeepSeek, Qwen, Kimi, GLM, Llama and Muse
  150. The Bottleneck Was Never Intelligence. It Was Context.
  151. ChatGPT Enterprise vs Copilot vs Custom RAG
  152. MCP vs RAG vs Agent Skills vs Custom GPTs
  153. How to Cut LLM Token Costs in 2026
  154. AI Agent Pilot in 30/60/90 Days
  155. Permissions-First RAG over SharePoint, Confluence, Drive
  156. RAG Production-Readiness Checklist for EU Companies
  157. When Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge
  158. Why AI Agent Projects Get Cancelled
  159. RAG vs Fine-Tuning vs Long-Context 2026
  160. LLM API Costs 2026. Architecture Shift
Inbox, without the noise

Get the next AI and agents field note

One concise email when we publish. No tracking pixels, and no inbox filler.