Tag: ai

All the articles with the tag "ai".

• MCP needs an enterprise control plane

  Published: 29 Jun, 2026

  • 15 min read

  

  Model Context Protocol can make agents useful inside large companies, but only if it is wrapped in identity, policy, audit, ownership, and a serious gateway architecture.

• Building a personal agent toolchain

  Published: 25 Jun, 2026

  • 7 min read

  

  A useful personal agent needs more than prompts. It needs a workbench, QA, memory discipline, durable task running, evaluation, and docs that stay honest in CI.

• I came away from day 2 at DTW Ignite with a slightly annoying conclusion

  Published: 24 Jun, 2026

  • 6 min read LinkedIn

  

  Agents are the easy story. Changing the operating model is the hard one.

• DTW Ignite day one: AI is everywhere, but telco still has to pay for it

  Published: 23 Jun, 2026

  • 7 min read

  

  First impressions from DTW Ignite 2026 in Copenhagen: agentic AI is all over the agenda, but telecom still has the awkward problem of making the economics work.

• Agent ops beats agent demos

  Published: 15 Jun, 2026

  • 9 min read

  

  A useful personal AI agent is not one clever prompt. It is the boring operational loop around memory, recovery, context handoff, scheduled work, and cleanup.

• The Agent Loop That Actually Works

  Published: 4 May, 2026

  • 9 min read

  

  Most enterprise AI strategies are still too model-first. The real leverage comes from designing an agent loop that can survive contact with reality.

• Home Brief turns Home Assistant daily briefs into something that actually persists

  Published: 30 Apr, 2026

  • 4 min read

  

  A practical write-up of Home Brief, a Home Assistant integration that generates useful house summaries and supports a proper published daily brief instead of one-shot AI output.

• Microsoft, Google, and Amazon are not just AI trades. They are the toll roads under the next compute cycle.

  Published: 28 Apr, 2026

  • 7 min read

  

  A lot of the market still talks about hyperscalers like they are just expensive big tech again. I think that misses the point. If AI keeps scaling, Microsoft, Google, and Amazon are not side bets. They are the infrastructure layer the whole wave has to run through.

• AI slop is everywhere now, and the internet already feels worse because of it

  Published: 23 Apr, 2026

  • 7 min read

  

  AI-generated junk is flooding social media, YouTube, search, and comment sections faster than people can filter it. The problem is no longer whether AI can create content. It is whether the internet can stay worth using.

• AI agents are not failing because they’re dumb. They’re failing because the system around them is sloppy.

  Published: 18 Apr, 2026

  • 6 min read

  

  Most agent products do not break on model quality first. They break on messy context, brittle tools, fake evals, weak recovery paths, and sloppy release discipline.