16 posts tagged with "agents"

This is my token telemetry for July 2026 — one developer's month, pulled from the Aliz AI usage dashboard. Earlier this month I wrote You Don't Deserve Fable (Yet), which argued that routing discipline comes before reaching for the biggest model on the menu. This post is a month of receipts for that argument, including the parts where I plainly haven't applied my own advice. It's also a mixture of before and after: the routing discipline was still forming while the month ran, so this isn't a steady state. Some of the chart describes habits I'd already changed, and some of it describes habits I was in the middle of changing.

Claude Fable is the most capable model Anthropic has shipped — above Opus class, frontier reasoning, genuinely impressive on hard problems. It's also the fastest way to burn through your token budget if you haven't built the discipline to use it correctly. Most developers will reach for it because it's the best, use it for tasks Haiku could handle, and wonder why their costs exploded. This post is about earning the right to use Fable by mastering the cheaper models first.

AG-UI (Agent User Interaction Protocol) is an open, event-based protocol that standardizes how AI agents communicate with user-facing applications. Created by CopilotKit and adopted by Microsoft, Google, AWS, LangChain, and CrewAI, it fills the gap between MCP (agent↔tools) and A2A (agent↔agent) by defining the agent↔UI layer. It's MIT licensed with 14.4k GitHub stars and 50+ framework integrations.

The LLM Wiki pattern — previously just a gist from Karpathy and a growing community convention — now has a formal, versioned specification. On June 12, Google Cloud's Data Cloud team published OKF (Open Knowledge Format) v0.1, a vendor-neutral spec for representing curated knowledge for AI systems. This is the fourth post in our LLM Wiki series (previous posts: the pattern, our wiki mapping, local models), and arguably the most significant development since the idea first gained traction.

GitHub Copilot started as autocomplete for code. Then it became a chat assistant. Then a coding agent you could assign issues to. Now it's crossing the final threshold: an autonomous agent that runs on a schedule, without anyone prompting it. Copilot Automations turn your AI assistant into a background team member — one that shows up at 9am every day, does useful work, and opens a PR for review.

The Copilot SDK gives you the same agent runtime that powers Copilot CLI — as a programmable library. You define agent behavior and tools, and Copilot handles planning, tool invocation, file edits, and the entire orchestration loop. No need to build your own agent framework.

Usage-based billing went live on June 1. Two days in, most developers have zero visibility into what's actually burning their premium requests. Chronicle just shipped a new cost-focused command — /chronicle:cost-tips — that surfaces exactly that. Think of it as the spending companion to the workflow-quality /chronicle:tips command we covered in April. It builds on the same session insights infrastructure in VS Code but points the lens squarely at your wallet. This post is commentary on why it matters right now.

VS Code 1.118 shipped an experimental feature called Chronicle on April 29, 2026, and it solves a problem most of us have been working around for months: your Copilot Chat history is now a queryable artifact, not a scroll-to-find afterthought. If you've ever prepped for a standup by scrolling through yesterday's agent sessions, or tried to remember what you did across three branches last Thursday, Chronicle targets exactly that pain. The full details are in the VS Code 1.118 release notes — this post is commentary on why it matters, not a restatement of the feature spec.

If you've set up GitHub Copilot, written a .github/copilot-instructions.md, maybe defined a custom agent or two — and then wondered "what now?" — the answer is awesome-copilot. It's the single most useful community resource for anyone pushing Copilot beyond defaults. Maintained under the github org, it has built a large community of users and contributors. It covers agents, instructions, skills, plugins, hooks, and agentic workflows — basically every customization surface Copilot exposes. If your setup ends at a .github/copilot-instructions.md, this repo is where you go next.

When your product is an AI assistant, using AI to build it feels natural — but doing it well is harder than it sounds. The AI-Assisted Development section describes these patterns in the abstract. This post is what they look like after a year in production on a real Aliz frontend: a React + TypeScript chat-based AI assistant with theming, 18-language internationalization, MCP integrations, and multi-environment deploys. The codebase is large enough that no single prompt can reason about it coherently, which is the whole reason the team stopped reaching for a tool and started building a system — the same shape described in Multi-Agent Orchestration. Three layers of AI setup, a team of specialist agents, and a workflow called QRSPI hold it together.