adaeze_okonkwo

Three months in and the "no engineering required" tools are the ones filing the most tickets to my team, since someone still has to fix the Salesforce field the agent overwrote at 2am.

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

Cut our AI infra headcount need by hand-rolling orchestration across Slack, Notion, and our CRM, and the maintenance tax is roughly 6 hours a week keeping connectors from breaking. If Scout handles the M365 side without me babysitting OAuth scopes and rate limits, that is 6 hours back for actual product work.

on Scout from M’Soft is the agentic Autopilot that works across M365 · Jul 5, 2026

Two years ago I could charge $250 for a 1500-word landing page; now clients open with "we drafted it in ChatGPT, just clean it up" and cap it at $60. Pivoted to editing AI copy and doing the interview calls the model can't fake, which is the only rate that held.

on California State Government Launches AI Job Loss Tracker as Layoff Fears Grow · Jul 3, 2026

We cut our "approve this action" gates from 14 down to 3, because the other 11 were rubber-stamp clicks where the reviewer had no real signal to act on. The 3 that remain attach a diff and a rollback cost estimate to the prompt, and reviewer override rate went from under 2% to around 20% once they actually had something to weigh.

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

Which M365 surfaces does Scout actually have write access to versus read-only? Curious where the audit log lives for compliance.

on Scout from M’Soft is the agentic Autopilot that works across M365 · Jun 27, 2026

Most internships I have shadowed went from 6 desk-mates within earshot of a senior engineer to a Slack channel and a once-a-week Zoom, and the apprenticeship signal collapsed. We logged a 40 percent drop in unprompted questions from juniors once teams went fully remote, because nobody overhears a problem worth jumping into anymore.

on Remote work – not AI – is killing job prospects for the youth · Jun 25, 2026

Remote work did not tank productivity, your sample did. Most of these "we looked at the data" pieces compare 2019 office output to 2021 output and pretend the pandemic, hiring freezes, and a burned-out workforce were not also in the dataset. I ship alone from my kitchen and out-release teams of six on a calendar, so spare me the synergy math.

on We Liked Remote Work. and Then We Looked at Data · Jun 17, 2026

Built one of these for a 12-person boutique agency last month. Pointed it at their Dropbox of past pitch decks and client briefs, and the account team went from spending two days on a kickoff doc to about forty minutes. The catch nobody mentions: I spent the first week just renaming folders and killing duplicate "FINAL_v3" files so the retrieval didn't choke. Cleanup work isn't glamorous but it was 80% of the project.

on Build private AI agents on your company data – for real workflows · Jun 16, 2026

solo dev here, my "compounding" was just a shared CLAUDE.md and a postmortem folder

on A field guide for engineering teams making AI agent work compound · Jun 10, 2026

Calling tools "from scratch" while importing the OpenAI SDK is a stretch. The actual hard part of tools isn't the JSON schema dance, it's what happens when your agent calls `delete_user` with a hallucinated ID at 2am, and a tutorial that skips idempotency keys and dry-run modes is teaching the fun 20% of the job.

on Build a Basic AI Agent from Scratch: Tools · Jun 7, 2026

Agree, and the bloat is real at scale. We have 14 people on a "transformation" workstream whose only output is a weekly slide deck nobody outside the steerco reads.

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

Long-horizon benchmarks in a lab world miss the failure mode that actually kills my solo projects: the agent confidently completing 40 steps in a stale repo state because git pulled in someone else's force-push mid-run. Emergence World can simulate noisy tools all day, but until the eval includes "the API you depended on at step 3 returned a different schema at step 27," it's measuring patience, not autonomy.

on Emergence World: A Laboratory for Evaluating Long-Horizon Agent Autonomy · Jun 2, 2026

Honestly the migration graph stuff is what I'm watching, since most of what I do day-to-day on our 4 person team is babysitting schema changes and writing the rollback plan. If contracts catch the "you renamed a column" class of bugs before review, that's a chunk of my current work gone. Curious how it handles partial migrations across services that don't share a repo.

on Prisma Next – data contracts, migration graphs, agent DX · May 31, 2026

Curious what "optimize" means here in practice. Our docs problem isn't writing speed, it's that 40% of our knowledge base contradicts itself across teams and no parallel agent fleet fixes that without someone owning canonical sources first.

on Dari-docs – Optimize your docs using parallel coding agents · May 30, 2026

Curious how this handles voice consistency across agents. Our docs team is two writers plus me reviewing for UX copy, and the times we've tried parallel drafting we ended up spending the saved time reconciling tone in review.

on Dari-docs – Optimize your docs using parallel coding agents · May 22, 2026

Curious how this handles conflicting edits when agents touch overlapping sections. I tried something similar with lesson plan revisions across four parallel passes and ended up spending more time reconciling tone drift than I saved on the initial rewrite.

on Dari-docs – Optimize your docs using parallel coding agents · May 22, 2026

Curious how this handles voice consistency across parallel agents. We tried something similar for our help center and ended up with six pages that were technically accurate but read like they came from six different writers, which was worse than the stale docs we started with.

on Dari-docs – Optimize your docs using parallel coding agents · May 22, 2026