Blog
Posts
Notes on running software in production, communicating during incidents, and how Exemplar fits alongside your existing stack.
- Read
AI & platform
What Is Loop Engineering? The Complete Guide
Loop engineering is the discipline of designing the plan-act-observe cycle that lets an AI agent complete multi-step work: termination conditions, state, retries, and cost bounds. What it is, how it differs from harness engineering, and how to build one.
- Read
AI & platform
Loop Engineering vs Harness Engineering: What's the Difference?
Loop engineering designs the plan-act-observe cycle an agent runs. Harness engineering governs what that loop is allowed to do. Clear definitions, a side-by-side comparison, and which to build first.
- Read
AI & platform
Loop Engineering: 25 Questions Answered
Every question engineering teams ask about loop engineering — answered directly. What it is, how to design termination and retries, how it differs from harness engineering, cost control, and safety.
- Read
AI & platform
The Loop Engineering Checklist: 12 Things Before You Ship a Standing Agent Loop
A practical checklist for teams shipping standing AI agent loops: termination conditions, retry design, cost bounds, safety gates, and monitoring — the 12 things to put in place before a loop runs unattended.
- Read
AI & platform
Best AI Agent Loop Orchestration & Control Tools in 2026
The best tools for building and running AI agent loops in production — orchestration frameworks, durable execution engines, and the governance layer that keeps standing loops safe and bounded. Compared and ranked.
- Read
AI & platform
Best AI Agent Governance Platforms in 2026
The best AI agent governance platforms for controlling what AI agents can do in production — policy gates, approval workflows, token budgets, and audit trails. Compared and ranked for engineering teams.
- Read
AI & platform
Best AI Agent Control Plane & Harness Tools in 2026
The best AI agent control plane and harness tools for running agents in production — governing actions, managing token costs, orchestrating workflows, and keeping a full audit trail. Compared and ranked.
- Read
AI & platform
Best Tools to Cut AI Agent & LLM Token Costs in 2026
The best tools to reduce AI agent and LLM token costs in production — prompt caching, model routing, budget enforcement, and circuit breakers. Compared and ranked for engineering teams.
- Read
AI & platform
Best AI Agent Orchestration Frameworks in 2026
The best AI agent orchestration frameworks for multi-agent and multi-step workflows — LangGraph, CrewAI, AutoGen, Google ADK — and how to govern them in production with a control plane.
- Read
AI & platform
Best AI Agent Observability & Monitoring Tools in 2026
The best AI agent observability and monitoring tools for production — tracing, evaluation, cost tracking, and the governance layer that turns visibility into control. Compared and ranked.
- Read
AI & platform
Best MCP Servers for Engineering Teams in 2026
The best Model Context Protocol (MCP) servers for engineering teams — GitHub, Kubernetes, Postgres, and the governed production-action servers that let AI agents act safely from Cursor and Claude Code.
- Read
Leadership
Best Podcasts for CTOs and Engineering Leaders in 2026
The 12 best podcasts for CTOs, VPs of Engineering, and senior engineering leaders in 2026 — covering AI, platform engineering, leadership, and the future of software development. Featuring Diary of a CTO, The Pragmatic Engineer, Latent Space, and more.
- Read
Leadership
Best Blogs for Tech Leaders and Engineering Managers in 2026
The 14 best blogs for CTOs, VPs of Engineering, and engineering managers in 2026 — covering AI, platform engineering, technical strategy, and engineering leadership. Curated for leaders who read to make better decisions.
- Read
AI & platform
What is Agentic DevOps? The Complete Guide
Agentic DevOps uses AI agents to execute DevOps and operational tasks autonomously — provisioning, incident response, secret rotation, and more — within a governed framework. Definition, use cases, safety requirements, and how to get started.
- Read
AI & platform
What is MCP (Model Context Protocol)? A Complete Guide for Engineers
Model Context Protocol (MCP) is the open standard that lets AI assistants connect to your tools and data. How it works, how it differs from function calling and RAG, which tools support it, and what it means for production engineering.
- Read
AI & platform
What is a Context Lake? How AI Agents Access Production Data
A Context Lake is a graph-backed data substrate that gives AI agents and engineers a shared, live view of the production environment. Why agents need it, what goes into it, and how it differs from a service catalog or data lake.
- Read
Platform engineering
Day 2 Operations: What It Is, Why It Matters, and How to Automate It
Day 2 Ops is everything after you ship — incident response, scaling, secret rotation, patching, and cost management. What it means, why it is harder than it looks, and how AI agents are changing it.
- Read
AI & platform
AI Agent Governance: How to Control AI Agents Running in Production
AI agent governance is the set of policies, controls, and audit mechanisms that determine what AI agents can do, when they need human approval, and how their actions are logged. The five pillars, how governance differs from the harness, and why it matters for compliance.
- Read
AI & platform
Agentic SRE: What It Is and How to Build One
Agentic SRE uses AI agents to automate incident detection, triage, root cause analysis, and remediation — with humans in the approval loop. The six-step workflow, what it requires, and expected outcomes for engineering teams.
- Read
AI & platform
Harness Engineering: 30 Questions Answered
Every question engineering leaders ask about harness engineering — answered directly. What it is, how to build it, how long it takes, how it differs from prompt engineering, whether it works on legacy codebases, and more.
- Read
AI & platform
Harness Engineering Glossary: 20 Key Terms Defined
Concise definitions for every key term in harness engineering and AI coding agents: AGENTS.md, taste invariants, knowledge architecture, AI coding entropy, garbage collection, progressive disclosure, tokenomics, MCP, and more.
- Read
AI & platform
AI Agent Token Costs: 25 Questions Answered
Why AI agents cost more than chatbots, how to measure token consumption, which reduction techniques actually work — prompt caching, progressive disclosure, model routing, batching, token budgets — answered directly.
- Read
AI & platform
AI Didn't Remove Engineering Judgment. It Moved It Upstream.
Engineering judgment isn't disappearing in the age of AI agents. It's relocating — from writing code to designing the systems that govern how code gets written. A CTO's take on harness engineering and what OpenAI's experiment actually proved.
- Read
AI & platform
The Harness Engineering Checklist
15 things to put in place before trusting AI-generated code in production — organised by phase: foundation, enforcement, task design, and maintenance. The checklist most teams wish they had before they started.
- Read
AI & platform
AGENTS.md: The Complete Field Guide
What AGENTS.md is, why a single file breaks down at scale, how to structure it so AI agents actually follow it, and what belongs in the docs directory it points to. With comparison table: AGENTS.md vs CLAUDE.md vs .cursorrules.
- Read
AI & platform
AI Coding Entropy: What It Is, Why It Compounds, and How to Stop It
AI-generated code doesn't degrade slowly — it compounds bad patterns at scale. What entropy means in AI coding contexts, why it spreads faster than human-written debt, and the three harness mechanisms that stop it.
- Read
AI & platform
Knowledge Architecture for AI Coding Agents: Beyond the AGENTS.md File
How to structure what your AI coding agent knows — the docs directory, context boundaries, ownership, versioning, and the difference between a knowledge system that stays useful and one that silently rots.
- Read
AI & platform
The Complete Guide to Cutting AI Agent Token Costs
Eight proven techniques for reducing LLM API token costs in production AI agents without sacrificing capability: progressive disclosure, skills, prompt caching, context compaction, model routing, batching, lean tool design, and token budgets.
- Read
Reliability
Why uptime and synthetic monitors still matter in the age of APM
APM and telemetry explain behavior under traffic; synthetics answer a different question—mature teams use both. How Exemplar complements observability with probes, SSL, vendor feeds, incidents, and status boards.
- Read
Reliability & compliance
Incident communication, status visibility, and SOC 2
SOC 2 CC2.3 and external communication; what examinations stress; how Exemplar SRE supports alignment between internal ops and customer-visible messaging.
- Read
Reliability
Status pages, trust, and the limits of a green dashboard
Why public status surfaces matter; internal operational truth vs. customer narrative; how Exemplar SRE narrows drift between them.
- Read
Reliability & GTM
Public status page guide for SaaS teams selling to enterprise
What enterprise buyers expect from public status; SLA alignment and checklist; how Exemplar SRE supports a coherent operational story for security reviews and sales.
- Read
Reliability
Why status page aggregators matter for engineering teams
Why teams with many cloud/SaaS dependencies (typically more than five) need a single view; examples (Supabase, Docker Hub/registries, GitHub, npm/PyPI); correlation under pressure; Exemplar SRE vendor feeds next to your checks.
- Read
Reliability
When one reliability surface has to satisfy everyone
Startups, enterprise deals, support load, API programs, audits, high-stakes uptime, and public communities all stress the same pattern—one operational truth and defensible communication. Why a unified SRE layer beats a patchwork.
- Read
Platform engineering
Developer autonomy and the work that repeats after ship
Why platforms emphasize provisioning while most time goes to post-launch change; Exemplar self-service Day 2 Ops with guardrails and audit history.
- Read
AI & platform
Agents, context, and guardrails on a unified platform
From code completion to production actions; Context Lake, catalog, governance, and Agentic Assistant/MCP for safe automation.
- Read
AI & platform
Your AI Agent is Burning Money. Here's Why — and the Fix.
Token bloat from mega-prompts on Google ADK agents; how Skills progressive disclosure (L1/L2/L3) cuts cost at scale—and when a plain system prompt still wins.
- Read
AI & platform
Skills make judgement reusable
Why AI agents need reusable operating methods, not just connected tools: skill files package triggers, decision checks, examples, and quality bars so teams can run production work consistently.
- Read
AI & platform
Moving from prompt and context engineering toward harness engineering
Three layers behind production agents: shaping the ask, assembling the window, and building the runtime loop. Where each discipline stops and what to invest in next.
- Read
AI & platform
AI SRE and AI DevOps: different problems, one reliability stack
AI SRE responds to production incidents with RCA and faster MTTR; AI DevOps automates infrastructure, drift, and cost before failures. How they differ, overlap, and fit incident-native platforms.
- Read
AI & platform
Agent loops, tokenomics, and the harness
Why the model is no longer the product: the loop turns intelligence into work, the harness governs it, and tokenomics (token value per watt per user) decides whether it pays. Field examples from Perplexity CEO Aravind Srinivas on 20VC.
Machine-readable index with URLs and blurbs: llms-full.txt