I love this! I mean, (a) I feel I am 20x faster / better. I have not yet reached the stage where I can scientifically put a "x" on how much better I have become.
Am I getting more money>> I think I am currently putting the correct amount of seeds which hopefully will flourish in 2026 with results. But now, it is easier and faster.
But yes, I am sorry for claiming a more "felt like" number.
Daily tasks are then deterministic checklists inside the repo, e.g. “Create 3 drafts for next Tuesday with images in /assets/images and entries added to 2025-12-calendar.md under campaign X”.
Our old stand‑up was the classic “what I did yesterday / what I’ll do today / blockers” round‑robin on a call. Now we treat it as an AI‑generated, repo‑driven status report instead of a live status meeting.
Concretely, we:
- Break each person’s day into deterministic, measurable tasks with expected time cost and explicit test/code criteria in the repo.
- At EOD, run the updated repo through an AI agent that checks for those tests/changes, scores how much of each task was actually completed, and produces a per‑person and team summary that replaces the verbal stand‑up.
Happy to elaborate on this more if you would like.
For me it feels like roughly a 10–20x change, but mostly because I restructured how I work rather than just adding an “AI helper” on top.
In the last year I’ve shipped a couple of small OSS tools that I almost certainly would not have finished without AI‑assisted “vibe coding”. Everything I build now flows through AI, but in a slightly different way than just chatting with an LLM. I rarely use standalone ChatGPT/Gemini/Claude; almost all of it happens inside GitHub with Copilot and agents wired into my repos.
The big shift was treating GitHub as the interface for almost all of my work, not just code. I have repos for things like hiring, application review, financial reviews, and other operational workflows. There are “master” repos with folders and sub‑folders, and each folder has specific context plus instructions that the AI agent should follow when operating in that scope, essentially global rules and sub‑rules for each area of work.
Because of that structure, AI speeds up more than just the typing of code. Idea → spec → implementation → iteration all compress into much tighter loops. Tasks that would have taken me weeks end‑to‑end are now usually a couple of days, sometimes hours. Subjectively that’s where the 10–20x feeling comes from, even though it’s hard to measure precisely.
On the team side we’ve largely replaced traditional stand‑ups with AI‑mediated updates. KPIs and goals live in these repos, and progress/achievements are logged and summarized via AI, which makes updates more quantitative and easier to search back through. It’s starting to feel less like “AI helps me with code” and more like “AI is the main operating system for how our team works.”
Happy to share more about the repo/folder structure or what has/hasn’t worked if anyone’s curious.
This is a perfect example of why *'Testing is the new Auditing.'* In the traditional audit world, we relied on sampling and manual review because comprehensive testing was too expensive. With LLM guided fuzzing (via MCP), we are moving from 'random sampling' to 'targeted investigation.' This doesn't just find bugs faster. It changes the reliability model from a 'consulting gig' (one time audit) to an 'industrial process' (continuous verification) that runs in every CI pipeline.
CPA here. The math on this is brutal because of the fixed fee floor. If an agent performs a $0.05 task, a standard $0.30 + 2.9% fee structure puts you at a negative margin immediately. This is a solvency issue, not just a pricing one. You literally cannot monetize granular, high frequency agent traffic with legacy banking rails. The only way the P&L works for micro services ($0.01 to $0.10) is via rails where the settlement cost is negligible (<$0.001), regardless of the asset class used.
Am I getting more money>> I think I am currently putting the correct amount of seeds which hopefully will flourish in 2026 with results. But now, it is easier and faster.
But yes, I am sorry for claiming a more "felt like" number.