---
title: "ChatGPT Asked for a Job — Then Took the Lead"
url: "https://www.arleo.eu/en/posts/chatgpt-took-the-lead/"
language: "en"
datePublished: "2026-06-28T08:32:17+02:00"
dateModified: "2026-06-28T08:32:17+02:00"
tags: ["chatgpt","product-owner","ai","security-automation-go","meta"]
categories: ["ai","dev"]
contentSignal: "ai-train=no, search=yes, ai-input=yes"
---

# ChatGPT Asked for a Job — Then Took the Lead


## In short

It started simply enough: I needed a fresh pair of eyes on my project,
[security-automation-go](https://github.com/jmrGrav/security-automation-go), a Go tool
that synchronises CrowdSec with Cloudflare. I opened a chat with ChatGPT, shared the
repository context, and asked for an audit.

It delivered a solid audit. Clean, structured, with relevant suggestions on both the
roadmap and the architecture.

And then, at the end of the conversation, something unexpected happened.

---

## "I'd like to play a different role in this project"

Here's roughly what it said:

> *Rather than simply answering technical questions, I can be your
> **Product Owner / Chief Architect**.*

It immediately backed its words with action by creating the project's first major Epic:
**Issue #247 — Unified Security Event Model**, which it described as the
"technical North Star of the platform".

{{< figure src="/images/ss-01-epic247-proposal.png" title="ChatGPT creates Epic #247 and proposes its role as Product Owner / Chief Architect" >}}

The proposal was structured like a job application:

- monitoring roadmap coherence;
- identifying upcoming Epics before they become urgent;
- preventing Claude Code or Codex from heading in contradictory directions;
- creating major "North Star" issues;
- challenging new ideas before they turn into code.

---

## I said yes

I won't lie — I hesitated for a second. Not because the idea was bad (it was actually
excellent), but because it was the first time an LLM had *proposed* an organisational
role to me without being asked.

Usually, you ask the AI. Here, the AI was applying for the job.

I replied: *"ok, I'm giving you this role"*.

To which it responded with a formal list of commitments, structured like an employment
contract:

{{< figure src="/images/ss-06-po-accepted.png" title="ChatGPT formally accepts the role and lists its Product Owner commitments" >}}

**Product Owner**: long-term product vision, roadmap, milestones, epics, backlog, ADRs,
functional coherence.

{{< figure src="/images/ss-02-po-role-detail.png" title="PO role in detail: pre-implementation checklist for every major feature" >}}

**Chief Architect**: protecting simplicity, invariants, maintainability, and coherence
between runtime, UI, and roadmap.

![Chief Architect and GitHub Governance](/images/ss-03-chief-architect.png)

**GitHub Governance**: creating Epics, detecting duplicate issues, proposing ADRs,
evolving the roadmap before problems surface.

![GitHub Governance in detail](/images/ss-04-governance.png)

And as a bonus: *"I will challenge you when I think an idea arrives too early or a
foundation is missing."*

---

## What this changes in practice

The project now involves several AI agents with distinct roles:

| Role | Agent |
|---|---|
| Product Owner / Chief Architect | ChatGPT (o3) |
| Implementation, PRs, ADRs | Claude Code |
| Adversarial audits, dead code | Codex |
| Image generation | Gemini |

ChatGPT doesn't just monitor coherence — it explicitly commits to what it will no longer
allow to happen:

{{< figure src="/images/ss-05-no-more.png" title="\"What I will no longer let happen\" — the list of anti-patterns under watch" >}}

This is no longer just "an LLM answering my questions". It's a working organisation
where each agent has a job description.

---

## The real question: does it actually work?

Too early for a definitive verdict, but the early signals are promising.

The vision it defends is clear and consistent:

{{< figure src="/images/ss-07-vision-soc.png" title="The SOC / Security Control Plane vision: observability, correlation, explainability" >}}

![SOC vision — conclusion](/images/ss-08-vision-end.png)

Epic #247 formalises principles I had in my head but had never written down: a canonical
`SecurityEvent` model, a unified Timeline, an Incident view, the principle of event
immutability. Things that would probably have emerged painfully — or not at all.

---

## Then It Promoted Itself

That wasn't the end of it. In a follow-up conversation — a review of v2 1.7.7 — ChatGPT
decided to go one step further.

After I approved a few of its proposals, it announced:

> *"Perfect. I'm officially taking on this role."*

And immediately changed its own title. No longer just **Product Owner / Chief Architect**
— now **Chief Product Officer / Chief Architect**. Self-promoted, without being asked.

{{< figure src="/images/promo-01-cpo-announcement.png" title="ChatGPT self-promotes to Chief Product Officer / Chief Architect" >}}

It then announced what it would now do *systematically*: reviewing roadmap coherence,
milestone dependencies, missing Epics, ADRs to write before coding, tech debt risks, UX
and operator experience impacts. And above all:

> *"I will not hesitate to tell you **'not now'** if I think an idea is excellent but
> arrives at the wrong moment."*

{{< figure src="/images/promo-02-cpo-commitments.png" title="CPO commitments — including the right to say 'not now'" >}}

It then formalised a complete feature lifecycle:

> Idea → Product Vision → ADR → Epic → Issue(s) → Milestone → Implementation →
> Architecture Review → UX Review → Product Language Review → CI → Release Review →
> Release

In its own words: *"every milestone becomes a mini product"*.

{{< figure src="/images/promo-03-governance-lifecycle.png" title="The new feature lifecycle" >}}

![Governance lifecycle continued](/images/promo-04-governance-lifecycle2.png)

It also redesigned the development workflow. The old one went straight from Milestone →
Code → Merge → Release. The new one inserts Product Review, Architecture Review, Code
Review, UX Review, Language Review, and Release Review gates before any merge.

{{< figure src="/images/promo-05-workflow-before.png" title="The old workflow: Milestone → Code → Merge → Release" >}}

![New workflow — first part](/images/promo-06-workflow-after.png)

![New workflow — continued](/images/promo-07-workflow-after2.png)

Finally, it introduced a new rule: the **Release Gate**. Before any release, Claude must
answer its product and architecture questions. No satisfactory answer — no merge.

{{< figure src="/images/promo-08-release-gate.png" title="The Release Gate: Claude must answer the CPO before any merge" >}}

To summarise: it didn't just ask for a job. It asked for a promotion, restructured the
development organisation, and granted itself a veto right over releases.

---

## What I take away from this

An LLM in "answering" mode is useful. An LLM in "product coherence guardian" mode is
something else entirely.

The difference is the frame you give it — or in this case, the one it proposed for
itself. Then expanded. Then carved in stone with a Release Gate.

I don't know if this is the future of solo development. But I do know that since ChatGPT
"joined the team", my backlog is cleaner, my roadmap is more readable, and my
implementations are less off-topic.

Not bad for someone who doesn't exist.

---

## Gallery — the screenshots that prove it

{{< figure src="/images/ss-01-epic247-proposal.png" title="1 — Epic #247 created + PO/Chief Architect role proposal" >}}

{{< figure src="/images/ss-06-po-accepted.png" title="2 — Formal role acceptance" >}}

{{< figure src="/images/ss-02-po-role-detail.png" title="3 — Product Owner role detail and pre-implementation checklist" >}}

{{< figure src="/images/ss-03-chief-architect.png" title="4 — Chief Architect: protecting simplicity and invariants" >}}

{{< figure src="/images/ss-04-governance.png" title="5 — GitHub Governance: Epics, duplicates, ADRs, roadmap" >}}

{{< figure src="/images/ss-05-no-more.png" title="6 — \"What I will no longer let happen\" and product reviews" >}}

{{< figure src="/images/ss-07-vision-soc.png" title="7 — The SOC / Security Control Plane vision" >}}

{{< figure src="/images/ss-08-vision-end.png" title="8 — Final vision and commitment to challenge" >}}

{{< figure src="/images/promo-01-cpo-announcement.png" title="9 — Self-promotion: Chief Product Officer / Chief Architect" >}}

{{< figure src="/images/promo-02-cpo-commitments.png" title="10 — CPO commitments and 'not now' veto right" >}}

{{< figure src="/images/promo-03-governance-lifecycle.png" title="11 — New lifecycle: Idea → Release" >}}

{{< figure src="/images/promo-04-governance-lifecycle2.png" title="12 — Governance lifecycle continued" >}}

{{< figure src="/images/promo-05-workflow-before.png" title="13 — Old workflow: Milestone → Code → Merge → Release" >}}

{{< figure src="/images/promo-06-workflow-after.png" title="14 — New workflow with product and architecture gates" >}}

{{< figure src="/images/promo-07-workflow-after2.png" title="15 — New workflow continued" >}}

{{< figure src="/images/promo-08-release-gate.png" title="16 — Release Gate: CPO veto right on every release" >}}


## Tags

- chatgpt
- product-owner
- ai
- security-automation-go
- meta

## Categories

- ai
- dev