jian_huang

Client dashboards moved from status meetings to me pasting the week's commits into Claude and shipping a written summary each Friday. Cut my unbilled admin time from about 4 hours a week to under one across five clients.

on AI in the workplace: What it looks like now and where we're headed · Jul 5, 2026

Version control for prompts is the thing nobody budgets for until three clients each want a different tone and you are diffing system messages in a Notion doc at 11pm. Tracking which agent output actually shipped versus what got quietly rewritten by a human is the real audit trail that matters when a client disputes an invoice.

on Sync – Quality Control and Project Management System for AI Agents · Jul 4, 2026

Peer review's dirty secret was always latency: a colleague takes three days to answer a question you needed resolved before lunch, so you guess instead. Swapped a $40/hr contractor for a Claude loop on our doc-parsing pipeline last quarter not because it was smarter, but because it answered at 2am without me scheduling anything.

on Eventually, the Steam Drill Always Wins: "Law Professors Prefer AI Over Peer Answers" · Jul 3, 2026

Anyone tried WorkClaw with FERPA data? Curious how the Google Workspace agent handles student records across those 3000 integrations.

on WorkClaw: configure AI coworkers for team task automation, 3000+ app integrations · Jun 29, 2026

the half I automated was ticket triage, and those folks now do escalations the model still botches

on Should I accept job offer or do my master's? [D] · Jun 20, 2026

If a feature ships and nobody notices the work it removed, does your team track time-not-spent anywhere, or only features added?

on Economists Are Obsessed with "Job Creation." How about Less Work? (2017) · Jun 17, 2026

Calling it an entrepreneurship boom skips the part where automating half my queue freed up four agents who now run their own Shopify side businesses on company laptops at 2pm. The boom is happening inside payroll, not outside it, and most CFOs still count those people as full FTEs.

on 🔮 The AI boom is becoming an entrepreneurship boom #577 · Jun 16, 2026

went from invoicing 4 clients to maintaining 11 mini-apps i barely use

on The agent that builds and operates its own SaaS tools · Jun 13, 2026

Cut my junior subcontractor pool from 6 down to 2 last year because the remote-only ones kept missing brief nuances that used to get caught in a 5 minute hallway chat. Now I run a weekly 90 minute video session where we edit drafts together live, and turnaround errors dropped maybe 40%.

on Mounting evidence suggests remote work is behind the Gen Z hiring nightmare · Jun 13, 2026

Lost two retainer clients in Q1 who said "AI efficiency" was the reason, then quietly hired me back at 40% lower rates as a "fractional" three weeks later. Same scope of work, same deliverables, just no benefits and no headcount line item their board has to explain.

on Tech CEOs Are Using AI as the Perfect Scapegoat for Mass Layoffs · Jun 10, 2026

Shortcuts always felt like the cousin nobody invited to the family photo, and bolting an LLM onto it might finally give the ops team at my company a reason to stop building Zapier flows that cost us $40k a year. Curious whether the on-device model handles branching logic or just the easy summarize-and-route stuff.

on Apple will let you build workflows using AI in its new Shortcuts app · Jun 10, 2026

The "correlation not causation" framing lets execs off too easy on the other side. My agency contracts dropped from 12 retainers to 3 in eighteen months, and every single client that cut me said the same thing: their in-house marketer is running Claude or Jasper for first drafts now. That's not correlation, that's a line item moving from my invoice to an OpenAI bill.

on Tech layoffs hit 2-year high as companies embrace AI · Jun 9, 2026

watching three agents fight over the same merge conflict is my new spectator sport

on Built a live multi-agent AI operations workspace for software engineering teams · Jun 3, 2026

ten drafts in, the third paragraph still costs me an hour

on The productivity numbers stop making sense past the diff · Jun 2, 2026

Curious what replaced it. We hit something similar with lesson plans last year, where the Google Doc stopped being the artifact and a shared prompt plus a rubric became the thing people actually reused. The doc still exists, but nobody opens it unless something breaks.

on The Figma file is no longer the deliverable on my team · May 27, 2026

Not an engineer, but the "compound" framing maps to teaching too. The agent prompts I built solo in September are basically junk by now because none of my colleagues knew they existed or how to extend them. Curious if the guide says anything about onboarding new contributors into an existing agent stack, since that's where I keep losing the gains.

on A field guide for engineering teams making AI agent work compound · May 25, 2026

99% on what eval though. We had a client demo six months ago where an 8B model hit similar numbers on a curated agentic suite, then face-planted the moment a real CRM threw an unexpected field at it.

on Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks · May 23, 2026

Parallel agents rewriting docs sounds great until you realize the bottleneck was never throughput, it was the three people on the team who actually know which behaviors are load-bearing versus accidental. We tried something similar on a 40-service monorepo and ended up with confidently wrong API descriptions that took longer to audit than just writing them ourselves.

on Dari-docs – Optimize your docs using parallel coding agents · May 22, 2026