XYZ Journal Audio
Listen to audio editions of the XYZ Journal on agentic operations, practical AI systems, and venture building.
Email Agent
Ask the XYZ email agent
Send a question about this topic, a service, or your workflow. The agent replies from the site knowledge and can route anything specific to our team.
Email the agentLatest episodes
Prefer reading first? Go back to the full article archive.
August 31, 2026
AI agent sprawl creates duplicated work, hidden costs, and unclear ownership. Learn how small companies can govern measurable agent workflows.
Podcast audio
On-site episode playback
August 24, 2026
Computer-use agents can automate some legacy software without APIs. Learn how to choose and control a practical workflow automation pilot.
Podcast audio
On-site episode playback
August 17, 2026
AI shopping agents compare products, prices, and proof. Learn how small companies can make their websites easier for agents to understand.
Podcast audio
On-site episode playback
July 29, 2026
German research puts hard numbers on the cost of administrative work and the potential value of AI. SMEs should use them to build a practical AI strategy now.
Podcast audio
On-site episode playback
July 29, 2026
For small businesses in Germany, the biggest AI opportunity is an intelligent operations layer that handles routine work across the website, back office, sales, and marketing.
Podcast audio
On-site episode playback
July 27, 2026
German SMEs can handle most AI and data protection risks with clear workload rules, approved providers, and a private route for genuinely sensitive work.
Podcast audio
On-site episode playback
July 6, 2026
LLMs have made custom internal software cheaper to build, but complex workflows still need hands-on AI implementation, data work, and engineering discipline.
Podcast audio
On-site episode playback
June 24, 2026
AI agents need company-specific knowledge before they can handle proposals, support, reporting, contracts, and internal workflows with enough context to be trusted.
Podcast audio
On-site episode playback
June 23, 2026
Agentic Mail is our email-first support MVP. Send it a real question and see how it answers from source material.
Podcast audio
On-site episode playback
June 10, 2026
Agentic de-siloing moves operational data out of closed SaaS systems and into open, structured, reviewable workflows where LLMs can work closer to the data with stronger control.
Podcast audio
On-site episode playback
June 4, 2026
Email used to be a chore, a time drain, and sometimes a small daily nightmare. My agentic inbox has turned it into an organized workflow I can actually trust.
Podcast audio
On-site episode playback
June 2, 2026
We have been using OpenClaw for real agentic workflows and team collaboration. It makes some important ideas accessible, but the product is flaky, slow, insecure, and structurally hard to trust.
Podcast audio
On-site episode playback
May 21, 2026
AI did not end authorship. It exposed the difference between pressing generate and actually directing, editing, and taking responsibility for published work.
Podcast audio
On-site episode playback
May 19, 2026
AI will make production cheaper, faster, and more widely available. When everyone can build, create, and automate, the scarce advantage shifts to better ideas, sharper taste, and stronger judgment.
Podcast audio
On-site episode playback
May 5, 2026
We used an AI-assisted document workflow to turn sponsor positioning, event context, and review notes into a polished Geomob sponsor presentation PDF without rebuilding the document by hand.
Podcast audio
On-site episode playback
May 4, 2026
If your website feels hard to keep current, the real problem is usually not design or tooling. It is the process behind updating it.
Podcast audio
On-site episode playback
April 30, 2026
AI makes custom internal software much easier to produce. The harder question is still what to build, what to buy, and how to avoid ending up with a stack of half-supported internal tools.
Podcast audio
On-site episode playback
April 29, 2026
Small companies know they need to work with AI, agents, and workflow automation. The hard part is choosing where to start without creating hidden operational, privacy, and reliability problems.
Podcast audio
On-site episode playback
April 28, 2026
If an AI workflow keeps failing in the same way, the fix is usually better workflow design: clearer task boundaries, stronger guard rails, and earlier review steps.
Podcast audio
On-site episode playback
April 23, 2026
Many businesses are spending more and more extra time just to keep up. The volume and speed of business communication now outruns human-only operations.
Podcast audio
On-site episode playback
April 21, 2026
AI-native software development is getting easier fast. The hard part is no longer generating an app or website. The hard part is judgment: architecture, security, UX, data, and operational control.
Podcast audio
On-site episode playback
April 16, 2026
If your team keeps correcting the same AI writing mistakes by hand, the real problem is not the draft. The real problem is that your editorial workflow has not turned the lesson into a rule.
Podcast audio
On-site episode playback
April 15, 2026
Agentic workflows stop at the point of purchase unless they have a controlled way to pay, with scoped permissions, spend limits, isolated records, and human review where it matters.
Podcast audio
On-site episode playback
April 14, 2026
AI value does not come from one magic prompt. It comes from the skills users build over time, from asking better questions to designing repeatable workflows.
Podcast audio
On-site episode playback
April 9, 2026
DECK/DOCS turns structured inputs such as scope, pricing, roadmap notes, contacts, and brand cues into polished offers, readable sales documents, and presentation-ready decks from the same source.
Podcast audio
On-site episode playback
April 9, 2026
Instead of treating the XYZ site as a static brochure, we built it as a promptable website with explicit guard rails, a structured content pipeline, and an editor workflow that can move much faster without losing control.
Podcast audio
On-site episode playback
April 9, 2026
Hyper-agile software development changes the bottleneck from implementation to judgment. With agentic coding and AI-native workflows, small teams can ship, test, and revise software within hours.
Podcast audio
On-site episode playback
April 7, 2026
The Peter Van der Meersch case is best understood as an AI workflow failure. The practical lesson is not to avoid AI altogether, but to use supervised AI workflows with verification loops, guard rails, and clear accountability.
Podcast audio
On-site episode playback
April 2, 2026
Agentic systems are better suited to brief us than to interrupt us, which is why the daily digest is likely to overtake the notification as the default way digital systems surface new information.
Podcast audio
On-site episode playback
March 29, 2026
Closed-loop systems turn agentic workflows into repeatable labor by moving work through research, execution, testing, reporting, and iteration without dropping context.
Podcast audio
On-site episode playback
March 19, 2026
A practical overview of major agentic systems, what unifies them, where they differ, and why guard rails matter more than tool hype.
Podcast audio
On-site episode playback
March 19, 2026
Most small teams no longer need slow, precious website projects. They need websites that can ship, learn, and improve at the speed of the business.
Podcast audio
On-site episode playback
March 18, 2026
Teams that move core business workflows into code-centric tools gain a practical advantage with AI: more consistency, faster iteration, better reuse, and a path toward deeper tool integration without requiring non-developers to write code.
Podcast audio
On-site episode playback
March 18, 2026
AI coding agents can remove a large share of painful infrastructure and deployment work, but the real advantage comes when development and operations teams learn how to use them with guardrails, review habits, and operational discipline.
Podcast audio
On-site episode playback
March 18, 2026
Our site robot is intentionally not powered by live LLM calls yet. Instead, it combines an AI-assisted internal FAQ, rule-based retrieval, careful caching, and privacy-aware analytics to guide visitors through the site.
Podcast audio
On-site episode playback
March 18, 2026
For our 16 March 2026 GeoIT Symposium talk, we used AI to generate a polished Reveal.js presentation, shaped it with repo-specific skills, improvised a PDF export skill, and published the deck on Cloudflare Pages.
Podcast audio
On-site episode playback
March 16, 2026
Agentic workflows and newer tools are shrinking the path from idea to launched service, making faster testing, validation, and iteration commercially realistic for small teams.
Podcast audio
On-site episode playback
March 16, 2026
Small companies will not just buy AI tools. They will gain entirely new operating capacity as AI takes on real departmental work across finance, planning, procurement, and administration.
Podcast audio
On-site episode playback
March 15, 2026
German small businesses do not need science fiction. They need practical semi-autonomous workflows that remove drag without adding more systems overhead.
Podcast audio
On-site episode playback
March 12, 2026
Ideas in Motion is our way of helping founders and operators move promising concepts out of limbo and into something testable, operational, and real.
Podcast audio
On-site episode playback
March 9, 2026
XYZ exists because FORMATION chose to test agentic operations on itself first, then package the patterns that proved useful into services for other teams.
Podcast audio
On-site episode playback
The fastest way to work out fit is a short call with the team.
Book Free Discovery Call