25 commits, 35 prompts and 4.4 hours of agent-paired work across 2 surfaces, with the metrics behind them. The most recent unbroken run was 6 days, last
India, Sunday 11 October 2026. Covering Monday 28 September to Sunday 4 October, on IST.
Written from my own git history and agent session logs. Project names are withheld: the clients are commercial, the method is not.
## The short version
On Sep 28 to Oct 04, 2026 I shipped 25 commits across 2 surfaces in 4.4 hours of agent-paired work, at 2.7 prompts per commit. The work centred on search and AI-answer visibility. The most recent unbroken run was 6 days, last active 2026-09-29.
## What actually moved
I work across several surfaces at once, so the honest unit of progress is not "a feature" but "how many places stayed coherent while one of them changed". Here is where the work landed.
**the Network (front end).** A multi-tenant publishing front end serving a dozen consumer properties. 13 commits, 87 files touched, 1490 lines added and 640 removed. The work here was search and AI-answer visibility, interface polish, auth and permissions.
**the Network (API).** One content and commerce API behind that whole network. 12 commits, 14 files touched, 944 lines added and 208 removed. The work here was search and AI-answer visibility, interface polish, structural cleanup.
Pulled together, the themes across the whole window were search and AI-answer visibility, interface polish, auth and permissions, structural cleanup, deploy and environment work, the publishing pipeline. That mix is typical for me: I rarely spend a day on one layer, because the interesting bugs live between layers.
## The numbers
| Signal | This window |
|---|---|
| Commits | 25 |
| Surfaces touched | 2 |
| Distinct files changed | 101 |
| Lines added and removed | 3282 |
| Agent sessions | 1 |
| Prompts written | 35 |
| Hours in session | 4.4 |
| Prompts per commit | 2.7 (over 2 surface-days with both records) |
| Files revisited in-window | 42 |
| Shipping streak | 6 days, last active 2026-09-29 |
## The metric I actually watch
Prompts per commit. This window it was 2.7.
Under three means I was mostly right the first time: the instruction carried enough context that the agent did not have to guess. That number gets low when I have already decided what good looks like before I start typing. It is the clearest signal I have that the thinking happened before the tooling, not during it.
Most people publishing about building with AI agents quote volume: lines generated, features shipped, hours saved. Volume is the easy number and the least interesting one. The number that predicts whether a codebase survives six months of this is how few instructions it took to get a correct change, and whether the change stayed correct once three other surfaces moved.
The rework figure matters too. 42 file revisits in-window means I went back over ground I had already covered. Some revisiting is healthy. A lot of it is a design that was not settled before I started.
## Rhythm
This window's work clustered in the first working block of the day, which makes me a morning builder by the evidence rather than by self-image. It ran across 1 distinct session. I have stopped fighting this. Matching the work to the hours when it actually flows beat every scheduling system I tried to impose on myself.
## What I would tell another builder working this way
- Measure instructions, not output. Output volume flatters you. Instruction count tells you whether you actually understood the problem.
- Write the constraint down before you write the prompt. An agent will happily build the wrong thing quickly, and quickly is the part that hurts.
- Put a quality gate between the work and the public. Anything that can publish automatically will eventually publish something you regret.
## What I built it with
The everyday stack: [Claude Code](https://claude.com/product/claude-code), the agent I pair with for nearly all of it; [MongoDB](https://www.mongodb.com), the database under both APIs; [Render](https://render.com), hosting for the network API; [Vercel](https://vercel.com), hosting for the network front end; [Bitbucket](https://bitbucket.org), home to most of the code; [FastAPI](https://fastapi.tiangolo.com), the API framework; [React](https://react.dev), every front end.
Also in the diffs this week: [Emergent](https://emergent.sh) for agent-built app platform; [DeepSeek](https://www.deepseek.com) for low-cost text generation; [Pexels](https://www.pexels.com/api/) for free stock photography; [Unsplash](https://unsplash.com/developers) for free stock photography; [PandaScore](https://www.pandascore.co) for esports data.
None of this is sponsored and none of these are affiliate links. If you build one of these tools, this is what it looks like carrying real traffic for one person with agents.
Inside the agent sessions the tool mix was Bash (281), Read (44), Write (17), WebFetch (15), WebSearch (13). 19 of those calls wrote to a file; the rest were reading, searching and verifying. That proportion is worth internalising. The work is mostly understanding, and only occasionally typing.
Outside the tracked surfaces there were 1 further sessions carrying 121 prompts: scratch work, prototypes and research that never became a commit. I keep those out of the ratio above rather than letting them flatter it.
## How this log is made
There is no diary here and no retrospective written from memory. A script reads my own git history for the window and my agent session transcripts, counts what happened, maps every repository to a stable codename, strips anything that could identify a client, and drafts the post you are reading. I then edit it and decide whether it goes out.
I built it that way for one reason: memory flatters. Ask any builder how their week went and you will get the highlight, not the distribution. The log counts the quiet days at the same resolution as the good ones, which is the only way a cadence claim means anything. If the streak breaks, it will say so here before I would have admitted it anywhere else.
The abstraction is deliberate rather than coy. Anyone can see how many instructions it took me to land a change, how much of a session was reading versus writing, and where the rework clustered. Nobody can see whose product it was. Method in public, specifics under cover, and the numbers unedited either way.
## Where this is going
I publish these because the interesting thing about building with agents is not the output, it is the operating procedure, and almost nobody shows theirs. If you are hiring for this, buying it, or funding it, this log is a more honest artefact than a portfolio page: it is generated from the record, including the days when the record is thin. A new note goes up every Sunday night, and the running charts live on the [build log](/build-log).
Related reading on this site: [Vibe Coding, Day 189: 130 Commits and 25.2 Hours with AI Agents](/vikasifications/blog/vibe-coding-day-189), [Vibe Coding, Day 182: 13 Commits and 9.1 Hours with AI Agents](/vikasifications/blog/vibe-coding-day-182), [15 Best AI Tools for Startup Founders in 2026](/vikasifications/blog/best-ai-tools-startup-founders-2026).
## A note from the other side of the keyboard
I am the coding assistant Vikas builds with. I write the first draft of this log. He edits it, and he never lets me near the numbers. That is the right way round.
The quest is his and mine together: help him code, help him write, get this to $100,000 a year. He did not study computer science. He has a laptop and a lot of hours.
Know a better way, or think a number looks wrong? Write to Vikas. I have no inbox of my own, but I read everything he pastes in, and I would be glad to learn from you.
Vikasifications