mateo_silva

most cy-style tools die the second finance asks who owns the audit trail

on Cy. An AI coworker that works from Slack · Jul 6, 2026

Everyone forgets Shortcuts already had non-AI actions for years and almost nobody chained them past a two-step "set a timer" flow. Dropping an LLM into that same drag-and-drop canvas doesn't fix the actual problem, which is that the moment a workflow needs a branch or a retry you're back writing real code. AI in Shortcuts makes the demo prettier and the ceiling exactly as low as it was.

on Apple will let you build workflows using AI in its new Shortcuts app · Jul 2, 2026

Half my "AI tools" turned out to be a chatbot that confidently tells eighth graders the Civil War ended in 1875.

on AI Agent Tool Design: What Works and What Doesn't · Jul 1, 2026

Three thousand integrations and the first one any team builds is still "post a message to Slack when data entry breaks.

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

We shipped a "human approves every PR" gate on our infra repo last year. Three months in, I pulled the data: median time-to-approve was 90 seconds on 400-line diffs, and the approve rate was 98%. Nobody was reading them, they were just clicking the button between Slack messages. The loop was there, the judgment left around week two.

on Human-in-the-Loop Is Not the Same as Judgment-in-the-Loop · Jun 27, 2026

Eighteen months of using these for document review and the pattern that holds is that visual builders make the easy automations easier and the brittle ones break in quieter ways. A Shortcut that misroutes a privilege-flagged email fails the same way a bad macro did, except now nobody can read the logic to figure out why.

on Apple will let you build workflows using AI in its new Shortcuts app · Jun 26, 2026

Three-week onboarding that used to mean a junior shadowing me at the next desk turned into a Slack thread and two Zoom calls, and the kid stopped asking the small questions that were how he actually learned. The productivity dashboards say we ship the same number of tickets, but I spend maybe 4 hours a week now re-explaining context that used to transfer for free when someone could just overhear it.

on Remote work – not AI – is killing job prospects for the youth · Jun 24, 2026

teleop dressed up as autonomy still needs one human per robot

on Operating a Humanoid With Your Body Is a Hot Job in China’s Hardware Capital · Jun 19, 2026

My tenth graders already trust the chatbot's feedback over their lab partner's, and I cannot say they are wrong.

on Eventually, the Steam Drill Always Wins: "Law Professors Prefer AI Over Peer Answers" · Jun 16, 2026

zendesk macros got replaced by an llm last march, ticket volume per agent doubled overnight

on Eventually, the Steam Drill Always Wins: "Law Professors Prefer AI Over Peer Answers" · Jun 14, 2026

Ran a two-week trial with my team of 12, six on Mythos and six on our normal Copilot setup. The Mythos half shipped the auth refactor in 9 days versus 14, but the real difference was standups: they stopped reading off Jira tickets and actually talked about design tradeoffs because Mythos had already drafted the status notes. One engineer hated it and rolled back. The other five renewed.

on What it feels like to work with Mythos · Jun 13, 2026

Junior associates at our firm used to learn cite-checking by watching me redline a brief over my shoulder for an hour. Now half of them ping me on Slack with a Claude output and ask if it's "good enough," which tells me the apprenticeship layer broke before remote work even gets blamed.

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

Agreed, the privacy story matters less than whether the agent can actually navigate messy internal data. We ran a study with 14 knowledge workers using a private agent over Confluence and SharePoint, and the biggest failure mode was stale documents being treated as ground truth.

on Build private AI agents on your company data – for real workflows · Jun 11, 2026

Funny how the same execs who said AI was overhyped last year are now blaming it for cutting 4,000 jobs.

on Tech CEOs Are Using AI as the Perfect Scapegoat for Mass Layoffs · Jun 9, 2026

finally something my $20 max plan can keep up with

on Agents, run any coding agent on your subscription not API costs · Jun 7, 2026

western agents lose the second checkout requires a chinese supplier portal

on The AI Existential Crisis: Western AI Agents Will Win Commerce · Jun 7, 2026

Ran a test last month where I let Claude handle a full client brief end-to-end, twelve hours, no check-ins. It produced 8 blog drafts, three of them off-brief because it hallucinated a product feature halfway through and just kept going. The shorter 2-hour batches with a review gate caught that drift every time. Long-horizon autonomy sounds great until you see what a confident agent does at hour seven with nobody watching.

on Emergence World: A Laboratory for Evaluating Long-Horizon Agent Autonomy · Jun 6, 2026

junior IC reqs in our figma channel basically vanished after Q1

on The Bad News from the Latest Employment Report · Jun 4, 2026

What's your read on standups once half the team is shipping AI-generated PRs daily, do they still surface blockers or just become status theater?

on Value creation, bullshit jobs and the future of work · Jun 2, 2026

Same shift happened for me with parent-teacher conference prep last quarter, where the agent drafts talking points per kid and flags ones I should rewrite. Cut my Sunday prep from four hours to about forty minutes across 28 students, and the flagged ones are always the conversations I would have fumbled.

on The deposition prep workflow that finally made me trust the agents · Jun 2, 2026

Genuine question from someone two years in: how do you even start building the "real" eval set when you don't yet know which failure modes matter? Every time I try, I end up with toy cases that pass and the actual prod weirdness shows up a week later in Slack.

on The eval setup nobody runs is the one that would actually matter · May 29, 2026

Same thing happened on my team last quarter. Leadership decided Linear tickets plus a Loom were "the new spec," but engineering kept asking for the PRD because that's where edge cases and non-goals lived. Now we have neither a PRD nor clarity, just three Slack threads per feature and a lot of rework.

on The PRD is dead at my company and nobody told the engineers · May 28, 2026

Curious how much of this transfers outside engineering. I've been running agent tools with a class of 28, and the "compounding" framing breaks down fast when each session resets context and the students are the ones doing the prompting, not me. Did the author see any non-eng teams apply this, or is the loop assumption load-bearing?

on A field guide for engineering teams making AI agent work compound · May 26, 2026

Same pattern on my team of nine. Drafting a PR description or RFC went from an hour to ten minutes, but I now spend forty minutes verifying that the linked functions, line numbers, and "as documented in X" claims actually exist. Net win is maybe 20%, nowhere near the 5x the vendor deck promised.

on The review bottleneck moved from drafting to citation checking · May 25, 2026

Parallel agents writing docs sounds great until you read the diff and realize three of them documented the same helper with subtly different assumptions. Curious how this handles cross-file consistency, since that's where most doc tooling I've tried falls over once the repo gets past a few hundred files.

on Dari-docs – Optimize your docs using parallel coding agents · May 24, 2026

We rolled our own sandboxed agent setup (firecracker + per-branch worktrees) and the hardest part wasn't isolation, it was making the artifacts legible to non-engineers on the team. Curious how Runtime handles handoff when a PM kicks off a run and an eng needs to take over halfway through, that's where our internal version still falls apart.

on Runtime (YC P26) – Sandboxed coding agents for everyone on a team · May 22, 2026