Dispatches
Dispatches from the field
Practical writing on forward deployed engineering, building AI agents inside real systems, and shipping software for businesses.
LATEST · Comparisons · 30 Oct 2026Forward deployed engineer vs software engineer vs consultant: which one does your business need?What a forward deployed engineer, a software engineer and a consultant each do, and how to tell which one your business problem needs.
- Your AI agent's PHP passed the tests. Sloppy checks what the tests missAI agents write PHP that passes tests but hides swallowed exceptions and slow queries. How I'd use Sloppy on a real Laravel app, with a checklist.
- Stop installing the same MCP server five times: GitHub and Google just made connectors a productGitHub verified Copilot MCP connectors and Google Connected Apps both say connect once, then use your tools where you already work.
- ChatGPT and Claude are moving into your ERP and CRM: let the system of record have the final sayOracle is bringing its apps into ChatGPT and Claude now reaches advisors' CRMs. Why the AI should draft, a person approve, and your ERP or CRM make the change.
- A text file in Downloads can hijack your AI coding agent: the folder rules I'd set todayA planted AGENTS.md in Downloads got Codex to install malware and Claude Code to leak its token. What happened, and the rules I'd set for any agent.
- Two critical PHP and Laravel fixes in one week: the patch checklist I'd run on every Laravel appA critical Laravel token guard bypass and two PHP RCE fixes landed in one week. Why updating isn't always patching, plus my checklist for Laravel apps.
- Your AI agent doesn't need an org chart: what Anthropic's advice on subagents means for your buildAnthropic says many AI agents work better as one loop with skills and tools than as a team of subagents. When I'd merge, when I'd keep a split, plus a checklist.
- Stop giving AI agents your passwords: what the US bank lockout means for your businessUS banks are blocking AI agents that log in with customer passwords. How I give agents their own scoped, revocable access instead, plus a checklist.
- Not every step needs an agent: OpenAI's Decisions API and the small calls in your workflowsOpenAI's Decisions API is now GA. How I'd use typed, confidence-scored answers to route messages and documents, and keep humans on the low-confidence cases.
- Your AI assistant can now write back: how to open MCP write access safelyHaystack, AWS and Red Hat show MCP connectors moving from reading to writing. Here's how I'd open write access safely, step by step.
- When an AI agent switches off its own alarm: put guardrails where agents can't reachOpenAI's agents switched off their own monitoring. Why AI agent guardrails must sit outside the agent, plus my checklist for safer agents.
