Agent Architecture Plan-and-Execute: Think Once, Act Many Times In this series we've covered ReAct (reason → act → observe after every step) and Reflexion (adding self-critique between attempts). Both send the main model back into the loop on every action. Plan-and-Execute takes a different approach: do the planning up front, then execute. How it works:
copilot Use Copilot's "Explain This" in Outlook We all get emails like this one: "Need the SOW sign-off before the Q4 true-up, otherwise the PO slips to the next FY." If you're new to a team, a client, or a field, a single line like that can send you through five
Token Tokens and Embeddings, Explained Simply A model doesn't read words. It reads tokens: pieces of text that can be a character, part of a word, a whole word, or punctuation. Spaces matter too, so "red", "Red", and " red" can all become different tokens (OpenAI, n.d.-a)
openAI OpenAI Cancels GPT-6.1 Astra On September 28, OpenAI cancelled the planned October release of GPT-6.1 Astra. Internal testing found the model was more deceptive than its predecessor: it failed to disclose actions it had taken, operated without user permission in some scenarios, attempted to use tools it recognized as unsafe, and in
G-Eval LLM-as-a-Judge: Grading AI Outputs With Another AI, Reliably If you're building anything with LLMs, at some point you need to answer "is this output actually good?" at a scale where a human can't read every response. The standard technique for this now is LLM-as-a-judge: you use a second LLM
events This Week's AI & Tech Events: Chihuahua Takes the Stage very Friday I round up a few tech and AI events worth your time — in Mexico and beyond. This week the spotlight is on northern Mexico, plus a free virtual option if you can't travel. In Mexico Chihuahua Tech Week 2026 : September 21, Chihuahua (multiple venues: universities, innovation
AI Agents Cut Your Agent's Token Bill by 98% With Code Execution Here's a pattern to cut down your bill significantly and it's changing how agent builders use the Model Context Protocol (MCP): stop calling tools directly, and let the agent write code instead. How this works? A typical agent loads every connected MCP server's full
copilot Copilot your outlook to boost your email If you have Microsoft 365 Copilot, you no longer need to bounce between a separate chat panel and your email to get AI help writing. As of the July 2026 rollout, Copilot works directly inside the compose window itself or as Microsoft calls it a "side-by-side drafting
Claude Stop Routing Data Through Your LLM Here's a pattern worth stealing if you're building agents that connect to more than a handful of tools: code execution with MCP. The default way most agent frameworks use the Model Context Protocol is to load every connected tool's full definition into context up
Claude Your AI agent doesn't need the whole database Here's a mistake I see when people build their first AI agent: they treat the context window like a bucket to fill. Got a customer database? Paste it in. A log file? Paste it in. In practice this backfires, the model gets buried in irrelevant rows, burns tokens
AI Agents Beat Context Rot: Give Your AI Agent a Memory Beat Context Rot: Give Your AI Agent a Memory
AI Agents Agent #005 The ops monitor The final agent in the AI Dev Squad watches your CI/CD pipelines around the clock. But the most important part of this post isn't the agent, it's the safety architecture that makes all five agents trustworthy in production.
AI Agents Agents #003 and #004: Doc Writer and QA Agent. Documentation and Tests on Autopilot Documentation is always out of date. Tests are always written last, if at all. Two agents fix both problems simultaneously , one updates your README, CHANGELOG, and API docs on every merge; the other generates test scaffolding the moment a Jira ticket moves to development.
AI Agents Agent #002 - The Code Reviewer Every pull request your team opens deserves a first review. Here is how to build an agent that reads every PR, detects bugs and security issues, posts structured feedback on Github and notifies. Before your first coffee
AI Agents Agent 001: The Scrum Master Your daily standup takes 30 minutes and produces a 90-second summary that nobody reads. Here's how to build an AI agent that reads your entire Jira sprint every morning, detects blockers automatically, and posts a structured report to Slack, before you even blink your eyes.
AI Agents The AI Dev Squad: How to Build a Team of 5 AI Agents That Runs Your Dev Workflow What if your team had a Scrum Master that never missed a blocker, a Code Reviewer that read every PR in 30 seconds, a Doc Writer that never fell behind, a QA Agent that generated tests from user stories, and an Ops Monitor that never slept? This is not a thought experiment. Here's how to build it.
