Category Archives: AI
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
Leave a comment
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?
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
BlogWriter Architecture Part 1
In a previous blog post I promised to take apart the BlogWriter architecture and implementation. I thought today I’d start with the architecture. The original design was to have 4 agents:* BlogWriter (orchestrates the other agents)* Researcher (searches the web … Continue reading
Posted in AI
Comments Off on BlogWriter Architecture Part 1
BlogWriter Goes Open-Source
Today I formally opened up my demo program BlogWriter as an open-source program. To do so, I added an MIT license and began taking contributions. Really that was about all there was to it, but it felt momentous.
Posted in AI, Essentials
Comments Off on BlogWriter Goes Open-Source
Spec Kit Phases
I’ve been writing quite a bit about Spec Kit. Mostly because I can’t get over how effective it is when combined with Copilot. Spec Kit essentially “forces” you into Spec Driven Development best practices. Spec‑Driven Development (SDD) flips the usual … Continue reading
Posted in AI
Comments Off on Spec Kit Phases
Writing A Front End
For the past six weeks I’ve been developing my demonstration program as a console application. Today I decided to give it a nice front end using Blazor (I don’t know Blazor). In the time it took to listen to Tommy … Continue reading
Posted in AI
Comments Off on Writing A Front End
