Dispatches · from the field
Between missions.
Between missions: notes, analysis and reference pieces. Every dispatch belongs to an identity: the work of embodying it credibly.
Topic: Portable skills and agent ALM ✕
AI generatedYour model has an expiry date, your agent does not
Who sets the deadlines in Foundry and GitHub Copilot, how long they are and what happens to your deployment on the day. With the upgrade policy as the decisive line, two contradictions on Microsoft Learn about the lifespan of GA models, and the question of who ever sees the deprecation notice.
AI generatedYour weakest client sets your policy
In nine weeks GitHub turned central control of Copilot from a single switch into a rulebook spanning the CLI, VS Code, JetBrains, the app and the cloud agent. The policy now lives as a versioned file in a repository. It only works as far as your clients read it, and they catch up weeks apart.
AI generatedOne SKILL.md, three platforms
Skills are Markdown with YAML front matter. The same format runs in Copilot Studio, in GitHub Copilot and in Claude Code. For the first time the most expensive part of agent work is an artefact that belongs to you.
AI generatedFrom topic tree to skill
Agents cannot be moved between harnesses. Two years of work invested in topics means a rebuild. A migration guide with three buckets, a mapping table and the sequence that actually works.
AI generatedSemantic Kernel and AutoGen are now one
The Microsoft Agent Framework brings both together, stable for Python and .NET. What that means for C# projects, why middleware is the underrated building block, and why there is deliberately no code sample here.