Blog

15 articles shown

• Is an AI project worth the cost? A worked business case

  Calculate AI project ROI with a worked example covering adoption, human review, integration, running costs and the difference between capacity and cash savings.

  October 21, 20268 min read

• How to choose your first AI workflow

  Compare AI workflow ideas, identify blockers and choose a small first test with a clear owner, useful baseline and manageable consequences of error.

  October 21, 20268 min read

• How to decide whether an AI pilot worked

  Set AI pilot success criteria around real work: outcome quality, human effort, adoption and permitted actions. Use the evidence to continue, change or stop.

  October 21, 20268 min read

• What AI hosting companies actually sell

  Open models make weights available. Serving them economically depends on traffic, cache reuse, and the capacity to stay fast under load.

  October 21, 202610 min read
  

• Reasoning with less text

  HybridAgent combines latent computation with text-based tool use. The useful questions are what it saves, what remains observable, and what it takes to run.

  October 20, 20265 min read

• What does a forward deployed engineer actually do?

  What does a forward deployed engineer do, and how does the role differ from consulting? A look at AI delivery, product development, and their changing economics.

  October 19, 20267 min read
  

• When an agent says it's done

  A coding agent's completion report should link its claims to observable results. Verification loops make failures visible before the work reaches the reviewer.

  October 18, 20266 min read

• What does it mean for AI to learn from your business?

  Using AI for six months does not guarantee it improves. The useful question is what changes: its source knowledge, its working procedures, or the model itself.

  October 17, 20266 min read
  

• The future of skills is learning from work

  Enterprise AI should retain useful lessons from work, turn them into tested procedures, and keep improving them. WikiSkill and OpenWiki show parts of that future and the work still required.

  October 15, 202610 min read
  

• What an agent skill actually is

  What goes in SKILL.md, how an agent finds it, and where prompts, tools, and memory fit.

  October 13, 20265 min read
  

• What remains when AI can write the code

  The strongest coding agents change the economics of implementation. They leave difficult questions about requirements, architecture, evidence, and ownership.

  October 10, 20266 min read
  

• Give the agent a definition of done

  Evaluation-driven development turns an ambiguous AI project into a sequence of testable improvements. The hard work is deciding what the tests should mean.

  October 8, 20266 min read
  

• Autoresearch is moving into the systems that run AI

  Agents can optimize GPU kernels and inference systems. I care about whether those changes make the full workload faster, and where an LLM improves on conventional search.

  October 6, 20265 min read
  

• What autoresearch taught us about skin analysis

  An AI agent explored wrinkle and pore models, trained small networks, and built review tools. The difficult part was deciding what our labels could tell us.

  October 4, 20268 min read
  

• The agent harness is becoming a runtime

  OpenCode 2.0, Pi 1.0, Codex, and Claude Code point toward a different question: how should useful work survive beyond a single conversation?

  October 2, 20266 min read