Author Archives: Jesse Liberty
Creating a Spec Kit Extension
Want to build an extension to Spec Kit? This comprehensive guide walks you through everything you need: a ready-to-drop extension layout, a complete extension.yml manifest, a slash-command file, a lifecycle hook that runs a C# helper, a full C# console … Continue reading
Posted in AI, Essentials
Comments Off on Creating a Spec Kit Extension
Creating Spec Kit Presets Step-By-Step
This guide assumes you already understand what Spec Kit and presets are and focuses on the who/what/where/how of authoring, testing, and publishing a preset. The instructions are concrete and practical — including a minimal manifest example, the recommended folder layout, … Continue reading
Posted in AI
Comments Off on Creating Spec Kit Presets Step-By-Step
4 Solutions to Spec Kit Issues
Your design docs look different across teams. Some repos forget the QA gate. Integrations (Jira, CI) are half-baked and duplicated as bash scripts. Onboarding a new engineer requires five manual steps to wire the same set of templates, commands, and … Continue reading
Posted in AI
Comments Off on 4 Solutions to Spec Kit Issues
Prompts in MCP Servers
TL;DR Prompts allow you to manage the exact instructions your chat models receive and let apps pick those instructions at runtime. That’s the core value of “prompts” in the Model Context Protocol (MCP). MCP prompts let a server publish reusable, … Continue reading
Posted in AI, Essentials
Comments Off on Prompts in MCP Servers
When Is the LLM Called?
When working with agents (e.g., in Microsoft Agent Framework) it is easy to be confused as to when the LLM is called. Since calling the LLM (and getting responses) costs money (in the form of expended tokens) it is important … Continue reading
Posted in AI
Comments Off on When Is the LLM Called?
1,500 posts
So far, this blog has published 1,500 posts.
Posted in Essentials
Comments Off on 1,500 posts
MCP and Microsoft Agent Framework
tl;dr
Posted in AI
Comments Off on MCP and Microsoft Agent Framework
RAG in Microsoft Agent Framework Step By Step
Adding RAG to Microsoft Agent Framework is both straightforward and confusing. OK, that makes no sense, but I’ve been struggling to understand all the steps. Here’s a first approximation, more to come in future posts (and I have a video … Continue reading
Posted in AI, Essentials
Comments Off on RAG in Microsoft Agent Framework Step By Step
Running Microsoft Agent Framework Locally
Run a full Microsoft Agent Framework (MAF) agent entirely on-device to eliminate round trips to the cloud, reduce latency, avoid egress costs, and keep sensitive data private. With Foundry Local you can run optimized local model variants (ONNX/WinML) and wire … Continue reading
Posted in AI
Comments Off on Running Microsoft Agent Framework Locally
ChatClient v ResponsesClient in Microsoft Agent Framework
TL;DRUse the Responses client for new projects if you want the newest, richest hosted tools and structured outputs; use the Chat Completion client when you need maximum backward compatibility or are constrained to the Chat-completions API (for example, Go-only paths … Continue reading
Posted in AI
Comments Off on ChatClient v ResponsesClient in Microsoft Agent Framework
Memory in BlogWriter
BlogWriter uses the Responses API which can help with state maintenance. BlogWriter, however, implements important state (context) using a session object, and manages long-term memory by writing to a Cosmos Database. I’m reusing this image because (a) it is apt … Continue reading
Posted in AI
Comments Off on Memory in BlogWriter
Copilot CLI
tl;drGitHub Copilot CLI is a terminal-native, agentic coding assistant that brings GitHub Copilot’s AI into your shell. Instead of only offering completions in an editor, Copilot CLI lets you ask natural-language questions, plan and execute multi-step tasks, edit files, run … Continue reading
Posted in Tools and Utilities
Comments Off on Copilot CLI
