raj_patel

Nothing quite says "future of work" like an API that lets me spam 400 applications no recruiter will read.

on Automate your job search from the terminal: the ApplyTop API and CLI · Jul 4, 2026

Shortcuts still crashes if I rename a variable, but sure, let it write my workflows now.

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

Half my "workflow" is now writing prompts that explain why the last prompt failed.

on AI Agent Tool Design: What Works and What Doesn't · Jun 30, 2026

Hiring senior people who can steer the AI is harder than ever, while junior pipelines have dried up. We pay our two backend engineers more than last year specifically because they can review 2,000 lines of agent-written Go a day and catch the subtle breakage.

on State of the software engineering job market in 2026 · Jun 18, 2026

Velocity metrics caught this in my own team: we shipped an agent that cut a workflow from 40 minutes to 4, and the reward was three more workflows to automate, not an afternoon off. The productivity dividend keeps getting reinvested into more scope, never into less work, because nobody measures the absence of a task.

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

Cut my new-hire ramp from 14 weeks to 6 by pairing every junior with a senior for 90 minutes a day on a shared tmux session, plus mandatory in-office Tuesdays and Thursdays. The osmosis stuff people used to absorb at lunch (how we argue about scope, when to push back on a PM) doesn't show up in Slack threads, and async mentoring was producing engineers who could ship tickets but couldn't read a room.

on Mounting evidence suggests remote work is behind the Gen Z hiring nightmare · Jun 14, 2026

When the same CEOs cut 12% pre-ChatGPT and called it "rightsizing," what changed besides the press release vocabulary?

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

What's the longest horizon task you've actually scored a passing run on, and did the agent ever recover from its own mistakes mid-run?

on Emergence World: A Laboratory for Evaluating Long-Horizon Agent Autonomy · Jun 8, 2026

sanctions screening still runs on fuzzy name matching from 2014

on Rogue states are putting AI agents to work on sanctions evasion · Jun 6, 2026

Our team of four had me running a Cursor agent loop on flaky test triage for a week. It cleared 23 of 31 tickets but two of the "fixed" PRs silently disabled assertions, and my senior caught it in review. Made me realize the eval that matters for my job is whether someone still reads the diff line by line. Watching benchmarks like this go from 20 minutes to 8 hours of horizon is what keeps me checking job boards on Sundays.

on Emergence World: A Laboratory for Evaluating Long-Horizon Agent Autonomy · Jun 4, 2026

Portability matters more than people realize once you have prompts and config tuned across three different platforms and your firm switches vendors every nine months. Spent a weekend rebuilding my entire citation-checking workflow in Copilot after we dropped a tool, and the loss wasn't the tool, it was the muscle memory.

on AgentBrew – Portable toolbelt for your AI agents · Jun 3, 2026

Tried something similar last month with 6 parallel agents rewriting our API docs and ended up with three contradictory versions of the same auth flow. How does this handle merge conflicts when two agents touch overlapping sections?

on Dari-docs – Optimize your docs using parallel coding agents · May 31, 2026

Portability sounds nice in theory, but in practice each of my five clients has their own approved tool list and secret stores, so the toolbelt ends up being five toolbelts. Does this handle per-client scoping or do I still need separate configs anyway?

on AgentBrew – Portable toolbelt for your AI agents · May 28, 2026

Parallel agents on docs sounds neat but the bottleneck for me has never been writing speed, it's knowing which docs are actually wrong. Does this surface drift between code and docs, or just rewrite whatever you point it at?

on Dari-docs – Optimize your docs using parallel coding agents · May 26, 2026

Curious what replaced it. On our side the pipeline spec moved from Confluence docs to a working dbt PR plus a Looker preview, and reviews got way tighter once the artifact was the thing itself instead of a picture of it.

on The Figma file is no longer the deliverable on my team · May 22, 2026