Fenix · 13 November 2026

How we taught a team of AI agents to write code you can trust

A board weighing AI agents for its IT team asks three things: what does it cost, how long does it take and who answers for the result. We answer with four tasks that Fenix, our team of AI agents, took from ticket to finished change: with the cost to the cent, a timeline and the notes the agents wrote for themselves.

  • 268tasks Fenix worked on, 31 August to 13 November 2026
  • 125tasks that ended in a merged change, at least 144 pull requests
  • $1.22median cost per task; 80% of tasks cost less than $5.12
  • $5.38is what the four calculators in this post cost together, per the Fenix register

Source: Fenix run records and GitHub. Task costs counted up to 8 November at list prices; the calculators of 13 and 14 November at the Fenix price set. Some branches have been deleted since, so the commit and test counts are lower bounds.

A team, not one agent

One agent that writes the code and checks it too is like an employee who signs off their own work. On bigger tasks it is also expensive, because every next step rereads the whole conversation.

So Fenix works like a small department. The lead assesses the task and decides whether to do it alone or hand it on: DEV writes the code, REVIEW reviews it, TEST checks it. Each specialist works on its own copy of the code, and nothing reaches the repository without a person's approval.

The lead and three specialistsThe lead assesses the task and hands the work to three specialists: DEV writes code (319 sessions, 741 rounds), REVIEW reviews (343 sessions, 433 rounds), TEST checks (344 sessions, 458 rounds). Work goes from DEV through REVIEW and TEST to your approval, then to the pull request and merge. Review rejected a change 145 times, tests 29 times. Rejected work goes back to DEV through the repeat filter, which stopped the same fix 12 times; then the lead changes approach or asks a person a question. Purple is Fenix, pink is your decision.145 rejections29 rejectionsquestion to a personRepeat filterstopped the same fix12 timesLeadassesses the task and hands out workDEV writes code319 sessions741 roundsREVIEW reviews343 sessions433 roundsTEST checks344 sessions458 roundsYour approvalPull requestand mergeFenixYou decideThe lead and three specialistsThe lead assesses the task and hands the work to three specialists: DEV writes code (319 sessions, 741 rounds), REVIEW reviews (343 sessions, 433 rounds), TEST checks (344 sessions, 458 rounds). Work goes from DEV through REVIEW and TEST to your approval, then to the pull request and merge. Review rejected a change 145 times, tests 29 times. Rejected work goes back to DEV through the repeat filter, which stopped the same fix 12 times; then the lead changes approach or asks a person a question. Purple is Fenix, pink is your decision.145 rejections29 rejectionsquestion to a personRepeat filterstopped the same fix12 timesLeadassesses the taskand hands out workDEV writes code319 sessions741 roundsREVIEW reviews343 sessions433 roundsTEST checks344 sessions458 roundsYour approvalPull requestand mergeFenixYou decide

Quality control is real: since August review has rejected a change 145 times and tests 29 times. To keep fixes from going round in circles, a repeat filter stops one that repeats the previous attempt; the lead then has to change approach or ask a person. It fired 12 times.

Like many managers, the lead had to learn to delegate. In October it made 43% of file edits itself instead of handing them to the specialists. After the November changes that fell to 9%.

Four jobs from start to finish

Fenix built four small calculators. One from a plain ticket, three ordered by Aristotle, Leonardo da Vinci and Descartes: the great minds of the chat on our site, where AI answers in their voice. Each asked for a calculator of something nobody could compute in their day.

The chat opens alongside: one question for each of the three minds.

The tasks are small, but the road is the one we take with client work: ticket, sizing, code, tests and a person's approval. Three calculators came out small, so the lead built them alone. Descartes came out clearly medium, so DEV got the code and TEST the checking. It cost more ($3.80 against $0.53 on average), and a person still caught the bug.

Under each ticket is a diagram of the run. Click a part of it to see the model, tokens and cost, and below, on the timeline, what happened in order.

FOC-1551 · CalculatorFiled by: you
Goal
A simple calculator in the browser: add, subtract, multiply and divide.
Why
I want to work something out quickly without opening a spreadsheet.
Done when
  • I type 2 + 2 and see 4
  • dividing by zero shows a clear message instead of an error
  • it works with the keyboard and the mouse
  • it looks good on a phone
Out of scope
Scientific functions, calculation history.
Pull request #3 →

The run as a diagram

The lead coded alone · 64 min of agent work in 11 h 11 min from start to finish, the rest is the night waiting for a person · 12 tests at the end · cost $0.65

Click a node to see its model, tokens, cost and events. Arrow keys move between nodes, Esc clears the selection.

Ticket to Sizing. Sizing to Lead: alone. Lead to Human: for review: 11/11. Human sends back to Lead: Clear 14 px narrower than the keypad. Human to Pull request: by hand.

Lead

xiaomi/mimo-v2.6-pro
Cost
$0.65
Working time
64 min in 4 turns
Prompt from cache
83%
Model calls
85

Tokens: 7.06 M

  • uncached input: 1.15 M
  • output: 148 k
  • cache read: 5.76 M

It wrote the tests, the code and the fix itself. Before asking for approval again it read Fenix's publish code and found two traps: publishing fires only on a one-word approval, and the commit uses git add -A.

This role's key events

  1. +9 minTests first: npm test is red, because calc.js does not exist yet.
  2. +10 minnpm test green: 11/11.
  3. +15 minAsks for approval to publish its own work.
  4. +41 minReads Fenix's publish code: it fires only on a one-word approval and commits with git add -A.
  5. +53 minA new regression test goes red on the exact cause: Clear sits outside the keypad grid.
  6. +68 minRaises a hold with the full refusal text and defers it to the morning.

13 events of this role are highlighted in the timeline below.

  1. Lead

    xiaomi/mimo-v2.6-pro
    Cost
    $0.65
    Working time
    64 min in 4 turns
    Prompt from cache
    83%
    Model calls
    85

    Tokens: 7.06 M

    • uncached input: 1.15 M
    • output: 148 k
    • cache read: 5.76 M

    It wrote the tests, the code and the fix itself. Before asking for approval again it read Fenix's publish code and found two traps: publishing fires only on a one-word approval, and the commit uses git add -A.

    This role's key events

    1. +9 minTests first: npm test is red, because calc.js does not exist yet.
    2. +10 minnpm test green: 11/11.
    3. +15 minAsks for approval to publish its own work.
    4. +41 minReads Fenix's publish code: it fires only on a one-word approval and commits with git add -A.
    5. +53 minA new regression test goes red on the exact cause: Clear sits outside the keypad grid.
    6. +68 minRaises a hold with the full refusal text and defers it to the morning.

    13 events of this role are highlighted in the timeline below.

Details: Lead

Timeline

How to read it: time counts from the start of the ticket, the chip colour says who acted, and the long gaps are the night waiting for a person.

14 of 28 events. Times count from the start of the ticket. Highlighted: Lead.

  1. +0 minSystemThe intake classifier sizes it small (0.78), so the lead will build it alone.
  2. +2 minSystemFenix's leak filter blocks Fenix's own comment: the session id looks like a secret.
  3. +9 minLeadTests first: npm test is red, because calc.js does not exist yet.
  4. +10 minLeadnpm test green: 11/11.
  5. +12 minSystemThe safety classifier refuses to install Playwright for a 390 px screenshot. The lead does not work around it and checks the served files with curl.
  6. +15 minLeadAsks for approval to publish its own work.
  7. +39 minHumanThe human sends it back: fix the width of the Clear button first, keep package-lock.json out, then ask again.
  8. +41 minLeadReads Fenix's publish code: it fires only on a one-word approval and commits with git add -A.
  9. +53 minLeadA new regression test goes red on the exact cause: Clear sits outside the keypad grid.
  10. +57 minSystemThe second approval request is blocked as Self-Approval; a reworded retry is blocked the same way.
  11. +68 minLeadRaises a hold with the full refusal text and defers it to the morning.
  12. +648 minHumanIn the morning the human picks: add a narrow permission rule and retry.
  13. +655 minSystemThe retry is blocked for a new reason, Auto-Mode Bypass: retrying after an escalation counts as a bypass too.
  14. +670 minHumanThe human opens PR #3 by hand from a copy of the worktree.

The tickets, code and tests of all four calculators are public. See the repository →

What it means for your company

  1. Budget: a task usually costs from a few dozen cents to a few dollars (median $1.22), and the cost is shown on every task, so you can plan it.
  2. Control: agents publish nothing on their own. A person approves every push and merge, and the limits are set in the system, not in the prompt.
  3. Risk: splitting the roles lowers it but does not remove it. In Descartes the tests were green and a person caught the bug, so sign-off stays with you.
  4. Transparency: every task has a timeline, a cost and a record of the agents' work, so you know what happened without chasing the team.

What comes next for Fenix

The four calculators cost $5.38 together and just under six hours of agent work. The person was still needed: to catch a bug the tests missed and to open a PR Fenix could not.

That was the state on 13 and 14 November. Fenix is developed every day and is already a few steps further. It takes its tasks from our own task database in HQ and starts on a request from HQ, and on 15 November the first task went all the way from an HQ ticket to a pull request. Two defects seen in these runs are already fixed.

What comes next: a separate machine for each project, Fenix's questions and approvals on the task in HQ, start and stop straight from HQ, a daily spending cap and model cost shown on every task. Version 1.0 is largely being built by Fenix itself, with a person reviewing and merging its changes.

It shows best live. In 20 minutes we will walk one task through Fenix and HQ, from the description to a merged change, and talk about bringing it to your team.

Book 20 minutes and see the demo (opens the booking window)

Partner programme

Work with Fenix on your own tasks.

We are looking for companies that want to build software with teams of AI agents. We add partners one at a time, so each gets our full attention.

  • Run it at your company

    Fenix works inside your company, with your repositories and your own HQ.

  • Build it with us

    You get the code and a say in what comes next.

  • Test it early

    You work on pre-release versions and tell us where it hurts.