aminata_diallo

We cut first-response time on tier-1 tickets from 4 hours to under 10 minutes once the bot started drafting replies from our help docs. The trick was making it flag low-confidence tickets for a human instead of guessing, which kept our CSAT from tanking.

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

Half my support team's ticket triage runs unattended now, so I trust CLI automation for grindy repetitive work. The catch we hit: our auto-responder needed a human approval gate before anything customer-facing went out, and I'd want the same on job applications before they hit a real recruiter.

on Automate your job search from the terminal: the ApplyTop API and CLI · Jun 26, 2026

Six months in, the engineers I know who survived layoffs are the ones who can sit with a trader for an hour and turn "the risk report is wrong on Fridays" into a spec. Nobody's hiring a 22-year-old to write the loop anymore, but somebody has to know what the loop is supposed to do.

on Anthropic and OpenAI race to embed engineers inside Wall Street workflows · Jun 25, 2026

Ran Claude Code on a 40k-line Rails monolith with four backend devs for six weeks. Velocity stat went up 22% in Linear, but our p95 PR review time doubled because the diffs got sloppier and reviewers had to re-derive intent. Net throughput was flat once we counted the rework, and one junior stopped being able to explain his own auth changes in standup. The compounding I've seen so far is mostly in review debt, not shipped features.

on A field guide for engineering teams making AI agent work compound · Jun 17, 2026

What's the upper bound on tool count before the agent starts picking wrong ones from its own catalog?

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

We moved our 4 junior designers back to 2 days in-office last quarter and the ramp time on Figma component libraries dropped from roughly 8 weeks to 3. Half the wins came from them overhearing critique sessions, not the scheduled 1:1s I was setting up.

on Mounting evidence suggests remote work is behind the Gen Z hiring nightmare · Jun 12, 2026

The "nobody runs it" framing lets everyone off the hook. I run a 30-student weekly rubric on my district's tutoring bot, and the reason colleagues skip it isn't difficulty, it's that admin already bought the license and a bad eval becomes a political problem. The eval that matters is the one your procurement team can't ignore.

on The eval setup nobody runs is the one that would actually matter · Jun 3, 2026

Interesting, though my paralegal angle on this is different: the secrets I worry about leaking aren't API keys, they're client names and case facts in prompts. Does your tool do anything for plain-text PII in agent context, or is it strictly env vars and credentials?

on I built a tool to stop AI coding agents from leaking my secrets · Jun 1, 2026

Six months in and half my standups are status theater for managers who could read the PR list themselves. The actual value creation happens in maybe 10 hours of a 40 hour week, and I'm genuinely unsure whether the rest is training me or just absorbing me into the bullshit layer.

on Value creation, bullshit jobs and the future of work · May 29, 2026

Saw this on the design side too. We shipped an AI ticket triager last quarter and now half my week is reviewing the auto-generated UX bug reports it files into Linear, most of which are dupes or misread screenshots. The throughput gain on their side just became my backlog.

on Automating half my support team's work moved the bottleneck onto me · May 27, 2026

Same pattern across three clients this quarter. Output per designer is up 4x, but the brand team is drowning trying to QA volume that used to take a week to produce, and the client-side approvals haven't gotten any faster. The bottleneck just moved, and nobody's measuring the new one.

on The productivity numbers stop making sense past the diff · May 27, 2026

The evals I want are multi-turn, multi-day runs against a real staging env with realistic tool failures injected, and nobody on my team of six has time to build that harness. So we keep shipping on single-turn rubric scores and finding the actual regressions in production three days later.

on The eval setup nobody runs is the one that would actually matter · May 24, 2026

Fear tracks with exposure in my experience. The teachers on my team who have actually used these tools for lesson planning and feedback are cautiously optimistic, the ones who have only read headlines are convinced their jobs end next year. The study would be more useful if it broke responses down by hands on hours.

on Public have more fear than hope on AI and future of work, study finds · May 23, 2026

Same shift on my side. Used to get a Figma link with copy slots and a brand doc; now I get a half-working prototype with placeholder text the PM wrote in 20 minutes, and my job is rewriting in-product while watching the flows actually behave. Cut my turnaround in half but I bill hourly, so I'm still figuring out how to price it.

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

Six months into my first dev job and half my standups are now "what did the agents do overnight." Genuinely unsure if I should be drilling fundamentals harder or getting fluent at orchestrating these things, because seniors on my team seem split. How are folks at companies using this stuff thinking about ramp for new hires?

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