AI Chinwag

Appearance

🤖 Building with Agents ​

Harnesses, agent workflows, orchestration, loop engineering.

VideoWes Bos

Browsers and UIs are dead. Everything is chat (Wes Bos)

Wes Bos's JS Nation Amsterdam 2026 talk on agentic interfaces and Web MCP — pushing back on "chat replaces all UI".

  • Frames the "clicks vs clankers" tension: build AI into your site, or build your site so agents can use it directly.
  • Covers Web MCP as the mechanism letting agents use a site's existing capabilities instead of a bespoke chat UI.
  • Argues chat won't replace everything, but it reshapes the UI landscape.
View ↗
🤖 Building with Agents🎨 Design & UX

added by Adam Tomat • 25th Jun 2026

BlogDecoding AI • Alejandro Aboy

How Evaluation-Driven Development (EDD) Works for AI Agents

A pre-merge evaluation gate for AI agent changes, using simulated inputs run through the real agent.

  • An offline gate answering "does it work / did anything regress".
  • Simulate inputs (drawn from real traces), not outputs.
  • Rejects always-on prod eval as too costly; runs targeted branch experiments with calibrated binary judges.
View ↗
✅ Testing & Quality🤖 Building with Agents

added by Adam Tomat • 23rd Jun 2026

BlogAddy Osmani

Cognitive Surrender

Distinguishes healthy cognitive offloading from "surrender" — accepting AI output without judgement.

  • Research cited: 73% accepted incorrect AI answers, with inflated confidence.
  • Code that "looks correct" hides comprehension debt.
  • Calibration habits: form your expectation first, treat AI code like a junior's, add friction.
View ↗
🤖 Building with Agents👥 Teams & Ways of Working

added by Adam Tomat • 18th Jun 2026

BlogAddy Osmani

Loop Engineering

The shift from prompting agents one-off to designing self-running "loops".

  • Designing the loop, not the prompt, is the real unit of work.
  • Self-running agent loops pair execution with verification.
  • Mirrors Addy's broader agentic-engineering thesis.
View ↗
🤖 Building with Agents

added by Adam Tomat • 18th Jun 2026

VideoAI Native DevCon

AI Native DevCon London 2026 (playlist)

The full talk playlist from AI Native DevCon London 2026 (1–2 June, The Brewery, London).

  • Guy Podjarny — "Skills are the New Code": agent instructions/context are becoming a software unit needing intent, review, testing and versioning.
  • Birgitta Böckeler — "State of Play: AI Coding Assistants": field data on which adoption patterns work vs. create tech debt.
  • Patrick Debois — "The Rise of Agent Enablement": frames agent enablement as a new org function alongside DevOps/Platform Engineering.
View ↗
🤖 Building with Agents🧩 Skills & Plugins👥 Teams & Ways of Working

added by Tom Harper • 17th Jun 2026

VideoChatPRD • Claire Vo

How to write AI agent loops in Claude Code and Codex

A walkthrough (paired with a Lenny's Newsletter / ChatPRD piece) of designing recurring and autonomous agent loops in Claude Code and Codex.

  • Four loop types: Heartbeat (recurring schedule), Cron (fixed time), Hook (event-triggered), and Goal (runs until a validated outcome).
  • Building blocks: automation trigger, isolated worktrees, reusable skills, tool plugins/connectors, sub-agents, and state tracking.
  • Concrete examples: a daily aging-PR reviewer, and a weekly skills-identification loop using goal-based subagents that self-validate.
View ↗
🤖 Building with Agents

added by Adam Tomat • 17th Jun 2026

BlogLangChain • Sydney Runkle

The Art of Loop Engineering

LangChain on stacking agent / verification / event / outer loops.

  • Multiple loop layers compose a single agent system.
  • The verification loop is treated as first-class, not an afterthought.
  • Event and outer loops handle long-running work.
View ↗
🤖 Building with Agents

added by Adam Tomat • 17th Jun 2026

Curated from the AI Chinwag Slack community.

The good stuff, kept.