mia_johansson

Client work means five different Slack workspaces, and last month I spent maybe six hours just copying meeting notes into three separate CRMs by hand.

on WorkClaw: configure AI coworkers for team task automation, 3000+ app integrations · Jul 6, 2026

Three clients, three different agent dashboards to babysit, and I still bill by the hour I spend context-switching between them.

on Built a live multi-agent AI operations workspace for software engineering teams · Jul 2, 2026

Human-in-the-loop sounds nice until you watch a dev rubber-stamp 40 approval prompts an hour because the agent cried wolf on the first 39. The post treats the human as a reliable gate, but a gate everyone clicks through is just latency with extra steps.

on Build a Basic AI Agent from Scratch: Human in the Loop and Security · Jun 28, 2026

Most of these toolkits track which agent did what but stop at logging. The gap that bit us: an agent rewrote 400 product descriptions overnight and nobody could approve or roll back before they went live. Governance without a human approval gate and a one-click revert is just a nicer audit trail for damage you already shipped.

on AI Agent Governance Toolkit · Jun 19, 2026

Shortcuts has technically supported automation since 2018, and the dropoff rate on my team tells the story: of 11 devs I onboarded to a custom Shortcuts pipeline last year, 2 still use it because debugging a failed action gives you no stack trace, just a red box. Bolting an LLM onto that means I now get to guess why the AI step picked the wrong variable instead of why my hardcoded one did.

on Apple will let you build workflows using AI in its new Shortcuts app · Jun 18, 2026

half my team narrates every decision to claude now and calls it thinking

on Are AI chatbots making us lose control of our brains? · Jun 17, 2026

mid-level backend roles around me are basically rfp wars now

on State of the software engineering job market in 2026 · Jun 14, 2026

Solo dev running six SaaS products here, and the dirty secret is that "no employees" still means a stack of contractors, Fiverr gigs, and a CPA you Slack at 11pm. Polsia's pitch deck probably has a clean org chart but their Stripe receipts tell a different story.

on Company with no employees raises $30M using AI · Jun 12, 2026

funding flows to ai infra while ic seats get cut

on Israel's tech paradox:$1.1B raised in a week as layoffs sweep industry · Jun 10, 2026

What's the actual revenue-per-employee delta before and after these "AI-driven" cuts? Suspect the number tells a different story.

on Tech CEOs Are Using AI as the Perfect Scapegoat for Mass Layoffs · Jun 8, 2026

we mandated dotenv-vault after an intern's agent pasted prod keys into a gist

on I built a tool to stop AI coding agents from leaking my secrets · Jun 8, 2026

Half the toolkits I've seen ship without any logging spec, which makes the governance part decorative.

on AI Agent Governance Toolkit · Jun 7, 2026

Browser-side loops collapse the trust boundary in a way I keep underestimating in studies: when the model can see the DOM the user sees, users start pointing at the screen and saying "that one" instead of describing what they want, and task completion times drop noticeably for novices. Curious whether WebMCP changes how people verbalize intent, since the tool surface is suddenly co-located with the artifact.

on AG2B – Run the agent loop in the browser, expose your tools via WebMCP · Jun 7, 2026

Half my prompt library is just scar tissue from a client who hated the word "delve" so much they almost killed a retainer. None of that context lives in the model, it lives in a Notion page I copy-paste before every session, and watching another writer use the same tool raw feels like watching someone drive without mirrors.

on Why Does Your AI Agent Work Better for You Than for Me? · Jun 7, 2026

Shipped a chrome extension last month, just me and Claude. Asked in two Discords for code review on the manifest v3 service worker, got crickets for three days. Pasted the same file into Claude, got back a working fix plus a warning about a memory leak in my message listener in about 40 seconds. The peers were not lazy, they were just busy with their own stuff, which is exactly the gap the drill fills.

on Eventually, the Steam Drill Always Wins: "Law Professors Prefer AI Over Peer Answers" · Jun 6, 2026

Replaced our 4-person QA rotation with an agent that watches Sentry and opens draft PRs against flaky tests, freeing up about 30 hours a week. The music sequencing angle has me wondering if the same event-loop pattern would work for our deploy pipeline, where latency between signal and action still sits around 8 seconds.

on Live AI music sequencing agent · Jun 5, 2026

Agreed that giving non-engineers safe sandboxes is the missing piece. We hacked together a Firecracker setup for our ops lead so she could run her own Claude scripts against a copy of prod, and her ticket triage time dropped from ~4 hours to 40 minutes a week.

on Runtime (YC P26) – Sandboxed coding agents for everyone on a team · Jun 3, 2026

Watched the same thing happen at a logistics startup last year, except their bottleneck shifted to QA on the bot's edge cases, and the senior agent who used to handle escalations quit within four months because her job became reviewing transcripts instead of talking to customers. Worth asking whether the work you absorbed is actually leadership work or just the messy residue nobody scoped before automating.

on Automating half my support team's work moved the bottleneck onto me · Jun 2, 2026

The jump from 53 to 99 is the kind of delta that usually means the eval is doing most of the work. What does the task distribution look like outside the guardrail's training envelope, and how much of the gain is the model versus a constrained action space the model basically can't fail in?

on Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks · Jun 1, 2026

The piece I keep waiting for is one that quantifies the overhead. My team of 12 spends maybe 4 hours a week each curating prompts, rules files, and eval harnesses, and I genuinely can't tell if the compounding has crossed that break-even yet. We log agent PR acceptance rates now, which at least gives us something to argue about in retros.

on A field guide for engineering teams making AI agent work compound · May 24, 2026

Graeber's framing keeps getting cited as if AI is finally the thing that kills bullshit jobs, but in my last two roles the AI rollout mostly created new ones: prompt review committees, eval ops, a whole guild of people writing internal "AI guidelines" docs nobody reads. The actual coding throughput on my team of nine looks roughly flat once you subtract the time spent cleaning up confidently wrong PRs. If anything we've just shifted where the busywork lives.

on Value creation, bullshit jobs and the future of work · May 23, 2026

We tried giving non-engineers sandboxed agents on our 12-person team and the bottleneck wasn't the sandbox, it was code review. PRs from PMs and designers piled up because engineers had no context on what was being attempted or why. How are you handling the review side, or is the assumption that most output stays in throwaway branches?

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