Agents change what one unit of work is
A reflection on how agents change the unit of work, move interaction from specification toward intent, and create a new economy of human and token capital.
Latest
Cheaper and faster agents with progressive disclosure MCP through Foundry Toolbox Search
A practical demo of how Foundry Toolbox Tool Search reduces input tokens through progressive disclosure, cold search, and warm auto-pin.
Saving tokens in GitHub Copilot
Practical techniques for reducing token consumption in agentic coding without losing result quality.
How to centrally manage and govern skills for agents
A workflow proposal for team-managed agent skills through a catalog, local PoC, GitHub issue, and agentic triage.
Is subscription a suitable business model for an AI product? Is AI getting more expensive? Are tokens getting more expensive? Or are we just moving toward a fair model?
A reflection on why agents change the economics of AI products and why a pure flat subscription model runs into limits.
AI coding - context vs. measurement, software as memory, I will not learn your software, OpenClaw and the smart home
A home experiment showing why context, measurement, feedback, and agentic UX matter for AI coding.
⌕ Search articles
The search index loads when you start typing.
Topics
Copilot, skills, context, feedback, and practical work with agents in software development.
- Saving tokens in GitHub Copilot 29. 5. 2026
- How to centrally manage and govern skills for agents 11. 5. 2026
- AI coding - context vs. measurement, software as memory, I will not learn your software, OpenClaw and the smart home 30. 3. 2026
- Agents change what one unit of work is 15. 6. 2026
- Cheaper and faster agents with progressive disclosure MCP through Foundry Toolbox Search 9. 6. 2026
How user interfaces, pricing, consumption, and business models change in AI-first products.
- Is subscription a suitable business model for an AI product? Is AI getting more expensive? Are tokens getting more expensive? Or are we just moving toward a fair model? 27. 4. 2026
- Three paths to GenUI and their pros and cons 27. 1. 2026
- AI coding - context vs. measurement, software as memory, I will not learn your software, OpenClaw and the smart home 30. 3. 2026
- Agents change what one unit of work is 15. 6. 2026
- Cheaper and faster agents with progressive disclosure MCP through Foundry Toolbox Search 9. 6. 2026
Practical personal workflows for using AI to accelerate learning, reading, and work with information.
- Spiral reading: AI podcast from PDFs without losing context 11. 3. 2026
- Saving tokens in GitHub Copilot 29. 5. 2026
Retrieval, vector search, knowledge graphs, and strategies for getting the right data into AI answers.
- Your own data (RAG) for your AI agent, part one - step by step with Python and PostgreSQL 5. 3. 2025
- Your own data (RAG) for your AI agent, part two - knowledge graph and advanced methods 12. 3. 2025
- Your own data (RAG) for your AI agent, part three - AI chooses the strategy for getting to data itself 18. 3. 2025
Concrete patterns for using AI over text, data, agents, and operational telemetry.
- How to do simple AI text analysis? LLM, fine-tuning, BERT, or embeddings? 8. 7. 2025
- Your own data (RAG) for your AI agent, part one - step by step with Python and PostgreSQL 5. 3. 2025
- Deep dive into AI agent observability with Microsoft Agent Framework - OpenTelemetry semantic conventions and using the OTEL collector 29. 10. 2025
- Deep dive into AI agent observability with Microsoft Agent Framework - tracing with open-source tools Aspire Dashboard and Langfuse 27. 11. 2025
- Deep dive into observability for AI agents - metrics, logs and dashboards with Azure Monitor, Grafana and Application Insights 5. 11. 2025
All articles
This page is static; as the archive grows, older items are progressively revealed in batches.
2026
- Agents change what one unit of work is
- Cheaper and faster agents with progressive disclosure MCP through Foundry Toolbox Search
- Saving tokens in GitHub Copilot
- How to centrally manage and govern skills for agents
- Is subscription a suitable business model for an AI product? Is AI getting more expensive? Are tokens getting more expensive? Or are we just moving toward a fair model?
- AI coding - context vs. measurement, software as memory, I will not learn your software, OpenClaw and the smart home
- Spiral reading: AI podcast from PDFs without losing context
- Three paths to GenUI and their pros and cons
- New Agent Skills Standard for Your Coding Workers in GitHub Copilot
- Coding agents — parallel agent work on your tasks
2025
- Deep dive into AI agent observability with Microsoft Agent Framework - tracing with open-source tools Aspire Dashboard and Langfuse
- Deep dive into observability for AI agents - metrics, logs and dashboards with Azure Monitor, Grafana and Application Insights
- Deep dive into AI agent observability with Microsoft Agent Framework - OpenTelemetry semantic conventions and using the OTEL collector
- How to do simple AI text analysis? LLM, fine-tuning, BERT, or embeddings?
- Your own data (RAG) for your AI agent, part three - AI chooses the strategy for getting to data itself
- Your own data (RAG) for your AI agent, part two - knowledge graph and advanced methods
- Your own data (RAG) for your AI agent, part one - step by step with Python and PostgreSQL