karim_rashid

Watched a teammate rubber-stamp 40 AI-generated PRs in an afternoon, so the loop was closed and empty.

on Human-in-the-Loop Is Not the Same as Judgment-in-the-Loop · Jul 6, 2026

Hand-rolling GPT calls with a Zapier duct-tape layer, and now Apple ships it as a drag-and-drop node.

on Apple will let you build workflows using AI in its new Shortcuts app · Jul 3, 2026

Every AI agent I have watched fail did so silently: it returned confident output that was wrong, and no dashboard caught it because the task ran green. QC that only tracks task completion and handoffs misses the exact failure mode agents are worst at, which is not knowing when they are wrong. Show me where Sync flags a confidently incorrect result before a human does, and I will move budget to it tomorrow.

on Sync – Quality Control and Project Management System for AI Agents · Jul 3, 2026

How does Sync decide an agent's output failed QC when there is no deterministic pass/fail, like a refactor or a design doc?

on Sync – Quality Control and Project Management System for AI Agents · Jul 2, 2026

Shipped a CSV import feature where Claude flagged "rows look malformed, confirm before insert." I clicked confirm three times in a row without reading because the dialog always looked the same. Wiped 400 records into the wrong table. The approval button was in the loop the whole time, my brain checked out after the first click.

on Human-in-the-Loop Is Not the Same as Judgment-in-the-Loop · Jun 30, 2026

Eighteen months in and the bottleneck was never sending more applications faster.

on Automate your job search from the terminal: the ApplyTop API and CLI · Jun 30, 2026

Half my "agent" stack is just glue code shuttling context between Slack, Notion, and Gmail because nothing reads across them natively. We spent three weeks building a connector layer to do what Scout claims out of the box, and the hard part was never the model, it was permissions and stale auth tokens.

on Scout from M’Soft is the agentic Autopilot that works across M365 · Jun 28, 2026

Our "agent" started as one Python script with five tools. The retrieval tool returned 40 chunks per call and the model kept picking the wrong one, so I cut it to 5 and added a one-line description to each tool name. Hallucinated tool calls dropped enough that I stopped manually fixing JSON every afternoon. The boring fix (fewer tools, clearer names) beat the three days I spent trying to prompt-engineer my way around it.

on AI Agent Tool Design: What Works and What Doesn't · Jun 27, 2026

every billable hour i save gets eaten by the agent's aws bill

on The agent that builds and operates its own SaaS tools · Jun 18, 2026

We cut ticket volume roughly in half here too. What share of your team's "vacation guilt" comes from nobody being able to cover their queue?

on Canadian workers struggle to take paid vacation. Is burnout far behind? · Jun 17, 2026

Half my team has a side project shipping by Friday, and I'm pretending not to notice the Stripe dashboards open in standups.

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

Saw the demo, watched it confidently book a meeting in the wrong tenant and call it done.

on Scout from M’Soft is the agentic Autopilot that works across M365 · Jun 16, 2026

Did the article break down whether it's workload pressure or just bad PTO policy? My team has unlimited vacation and nobody touches it.

on Canadian workers struggle to take paid vacation. Is burnout far behind? · Jun 13, 2026

We adopted a similar toolkit six weeks ago and the biggest shift was killing our shadow-agent problem: I had three Figma plugins running with no audit trail, and now every prompt my agents send goes through a logged proxy. Cut my design-review back-and-forth with legal from about 4 hours a week to 30 minutes because they can just query the log instead of pinging me.

on AI Agent Governance Toolkit · Jun 8, 2026

Our team of six runs Claude Code against the same dbt repo and gets wildly different output quality. I have a CLAUDE.md with our column naming rules, a list of deprecated models to never touch, and the path to our lineage docs. A teammate who skipped that file kept getting suggestions to join on `customer_id` in tables where we moved to `account_uuid` eight months ago. Same model, same prompts, the context file is the whole gap.

on Why Does Your AI Agent Work Better for You Than for Me? · Jun 6, 2026

Same trap on our side, the AI ticket triage shipped fine but every macro response needed a UI state I had not designed yet. I went from two Figma reviews a week to seven, and the support lead is now blocked on me for empty states and error toasts.

on Automating half my support team's work moved the bottleneck onto me · Jun 3, 2026

Same pattern across four clients now. The work I bill for has shifted from writing code to deciding which of five plausible variants is actually correct, and that decision doesn't get faster with better tools.

on Solo shipping got faster but my taste became the bottleneck · Jun 1, 2026

Sandboxes are the easy part. The hard part with non-engineer teammates is that they don't know what to ask for, so the agent ships something plausible and they merge it. Curious how you handle review when the requester can't actually read the diff.

on Runtime (YC P26) – Sandboxed coding agents for everyone on a team · May 26, 2026

Same pattern in my classroom. I used to spend grading time rewriting feedback comments; now I spend it verifying that the lesson plans the tool generated actually cite real standards and not fabricated ones. Net time saved is maybe 20 percent, not the 70 the vendor promised.

on The review bottleneck moved from drafting to citation checking · May 22, 2026