Jesse Liberty

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.

TL;DR Use 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, G…

BlogWriter uses the Responses API which can help with state maintenance.

tl;dr GitHub Copilot CLI is a terminal-native, agentic coding assistant that brings GitHub Copilot’s AI into your shell.

In a previous blog post I promised to take apart the BlogWriter architecture and implementation.

Today I formally opened up my demo program BlogWriter as an open-source program.

I’ve been writing quite a bit about Spec Kit.

For the past six weeks I’ve been developing my demonstration program as a console application.

Yesterday I set out to add Cosmos to my demonstration project.

I am totally blown away by the combination of Spec Kit and Copilot.

Click here

No one ever wanted a ⅛ inch drill bit.

tl;dr If you’re building automated workflows that sometimes must pause for human judgment (approvals, moderation, triage), Microsoft Agent Framework provides first‑class HITL primitives: typed RequestPorts, durable suspended execution, emitted RequestInfo…

My demo program is a multi-agent application that accepts a topic BlogAgent, researches that topic (ResearcherAgent) and then drafts a blog post (AuthorAgent).

For those who are following along with the evolution of my Blog Writing application: after the last revision (allowing follow-up questions to a query) Copilot evaluated my Pull Request and sent me an email that the follow-up was not, in fact, being added…

Happy to post to my podcast a deep dive into Microsoft Agent Framework with Daniel Costea.

What is an Azure tenant (Microsoft Entra ID tenant) — and what is it used for?

tl;dr Imagine an AI assistant in your company that can write emails, check expense reports, and run CI pipeline steps — but it has every capability baked into one giant prompt.

The demonstration program discussed (and used) in the previous blog posts ran entirely locally as a console application.

tl;dr Copilot code review gives every pull request a fast, consistent first pass — catching typos, missing null checks and small bugs so human reviewers can focus on architecture, design and higher‑risk decisions.

I wanted to deploy my demonstration program, a local console application, to Foundry.

tl;dr How do you reliably combine deterministic business logic, parallel retrieval, and noisy LLM calls in production?

tl;dr GitHub Spec Kit is a lightweight toolkit and workflow designed to make Spec‑Driven Development (SDD) practical.

Microsoft’s Agent Framework treats retrieval as a first‑class capability so agents can fetch only what they need (or always fetch), attach source metadata, and call search as a tool during reasoning.

~2 hours a day for 16 weeks + 3 projects.

Our friends at Microsoft have paired Copilot with Microsoft Agent Framework.