Cluster

Agent engineering

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

Blog posts
55
Topic
AI and agents

Start with the cornerstone

Latest in this collection

Rust compiler graph connecting persistent declaration identities to verified semantic patches AI & Agents

Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust

A compiler engineering walkthrough of persistent IDs, checked HIR, deterministic graphs and replayable patches in the experimental SEMAPRAX language.

Kevin Riedl Kevin Riedl
Read
LangChain Deep Agents connects planning, subagents, files, approvals, sandboxes and production traces AI & Agents

LangChain Deep Agents Review: Is the Agent Harness Ready for Production?

A buyer-focused Deep Agents review covering architecture, v0.7 changes, security boundaries, operating costs and a measurable production pilot.

Kevin Riedl Kevin Riedl
Read
OpenViking filesystem connecting agent memory, RAG resources and skills through viking paths AI & Agents

OpenViking Review 2026: Is Filesystem Memory Production-Ready?

Buyer review of OpenViking for agent memory and RAG: architecture, AGPL risk, security controls, operating cost and a measurable two-week pilot.

Kevin Riedl Kevin Riedl
Read
Continuous verifier scores ranking several AI agent trajectories AI & Agents

LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit

A technical buyer guide to fine-grained LLM verification: how logprob scoring and pivot tournaments work, what the benchmarks prove, and how to pilot it safely.

Kevin Riedl Kevin Riedl
Read
TrueForge agent harness connecting models, MCP tools, subagents, approvals, sandboxed code and traces AI & Agents

TrueForge Review: Is the Open-Source Agent Harness Production-Ready?

A buyer-focused review of TrueForge, its agent loop, context controls, benchmark economics, deployment modes and enterprise production gaps.

Kevin Riedl Kevin Riedl
Read
One page served as HTML, as a Markdown mirror and as an llms.txt entry, with a build gate checking all three AI & Agents

Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks

Four surfaces decide whether an AI answer engine can read you, and every failure mode is invisible in a browser. Here is the list our own build gate has caught.

Kevin Riedl Kevin Riedl
Read

Complete article directory

  1. Why Agent Edits Need Semantic Identity: Building SEMAPRAX in Rust
  2. LangChain Deep Agents Review: Is the Agent Harness Ready for Production?
  3. OpenViking Review 2026: Is Filesystem Memory Production-Ready?
  4. LLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit
  5. TrueForge Review: Is the Open-Source Agent Harness Production-Ready?
  6. Agent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks
  7. Localized URLs Break hreflang: Keep One English Slug
  8. Can an AI Agent Use Your Product, or Only Read About It?
  9. Graft Review 2026: Do Agent Repo Maps Belong in Git?
  10. How Coding Agents Keep Token Bills in Check with Output Compression
  11. Smarter Token Usage with Your AI Coding Agent
  12. DeepSeek Harness Review: Is the Plugin Stack Production-Ready?
  13. OpenSandbox Review: Is Self-Hosting Worth It?
  14. Cloudflare Kitesurf Review: Cost, Limits and Production Fit
  15. GitHub Spec Kit Review: Is It Worth the Process?
  16. Internal AI Agent Marketplace: A 2026 Enterprise Build Guide
  17. Is Linux the Best OS for AI Agents? A 2026 Infrastructure Guide
  18. MCP Cloud vs Manufact Cloud: MCP Hosting Guide
  19. How to Make AI Writing Sound Human with Agent Skills
  20. NVIDIA NOOA Review: Are Object-Oriented Agents Production-Ready?
  21. Strix AI Pentesting: 30-Day Pilot and Buying Guide for 2026
  22. Hyperagent Review: Cloud AI Agents Without a Server
  23. Hark Handoff Review: The Agent That Actually Clicks
  24. Meta Muse Code Pricing: Is the Contributor Tier Safe for Client Code?
  25. PII Redaction Before LLM Prompts: A Practical Pipeline
  26. Agent Reach Review: Costs, Security and Real Limits
  27. Cloudflare Wallets for AI Agents: What Is Live?
  28. YC QM Agent Review: Is Quartermaster Ready for Work?
  29. jcode vs Claude Code: Is the Rust Harness Worth Switching To?
  30. Lightpanda Browser for AI Agents: Production Guide
  31. Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?
  32. Multi-Model AI Coding Agent Stack: A Team Buying Guide
  33. Is MCP Stateless Now? Your Server Migration Checklist
  34. MCP Is Not a Security Boundary: Protect Agent Data
  35. Can AI Agents Talk to Each Other? A Band Setup Guide
  36. LeanCTX Technical Field Report: 64.1% Less Context
  37. CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code
  38. Enterprise MCP Authorization Architecture
  39. OpenAI Eval Sandbox Escape: 12 Controls Before You Test a Cyber Agent
  40. Meterless Review 2026: Is This AI Agent Context Layer Ready?
  41. Claude Code vs OpenCode: Which Costs Less for a Team in 2026?
  42. Graphify Review 2026: Is a Codebase Knowledge Graph Worth It?
  43. AI Pilot Kill-or-Scale Scorecard: 12 Metrics to Check After 30 Days
  44. T3MP3ST Review 2026: Can It Replace a Penetration Test?
  45. Open Knowledge Format (OKF): The Enterprise Guide
  46. AI Agent Cost per Action: Why Agentic Workflows Blow Up Token Bills
  47. How to Use Claude Fable 5 in Claude Code
  48. What an Internal AI Assistant Actually Costs in the DACH Region (2026)
  49. The Bottleneck Was Never Intelligence. It Was Context.
  50. ChatGPT Enterprise vs Copilot vs Custom RAG
  51. MCP vs RAG vs Agent Skills vs Custom GPTs
  52. AI Agent Pilot in 30/60/90 Days
  53. Permissions-First RAG over SharePoint, Confluence, Drive
  54. RAG Production-Readiness Checklist for EU Companies
  55. Why 40% of AI Agent Projects Die