Agents with autonomy. Decisions with an owner.
How we govern a factory of agents: what they do on their own, what a person decides, and how we prove it with our own log.
Many say “agents”. Few can show how they govern them.
of agentic AI projects will be canceled by the end of 2027 due to costs, unclear value or weak risk controls, according to Gartner.
of the thousands of vendors calling themselves “agentic” are real, Gartner estimates. It calls the rest agent washing: chatbots and RPA renamed.
We don't ask you to take our word for it. We publish the cycle, the gates and our own factory's numbers, failure rate included.
Source: Gartner, 25 jun 2025
Agents research, rank and cost. A person decides what to build.
It's the agentic product cycle Endgame proposes, applied to our factory: every step has a named agent and every decision has a human owner.
-
Step 01 · Agents, 24/7
Gather every signal
Oráculo · market and pricingMentor · voice of the customerAtenea · portfolio and betsHefesto · tech debtArgos · usage and drop-offsMetrics · what the last release did -
Step 02 · Agents turn signals into one list
Rank the backlog
Strategic betCustomer requestTech debtData finding -
Step 03 · Cost · weeks · expected impact
Cost every option
Option A · MXN · wk · ΔOption B · MXN · wk · ΔOption C · MXN · wk · Δ -
Step 04 · Gate A · human decision
One person picks one
One-page spec approved (G0)
Shape the slice
Epic · stories · acceptance criteria as tests
Build and ship
Tests first (G1) and automated review (G2) · Minos gate · your approval on high risk (G4)
Measure the outcome
Usage · retention · margin → Gate B
Gate B checks whether the release moved the outcome, and that feeds step 1. Without Gate B, a factory measures how it builds, not what it achieves.
Priority = (V × F × C) ÷ (K × (1 + T/4))
V expected value (1–5) · F feasibility (1–5) · C confidence in the data (0–1) · K cost to build and run (1–5) · T weeks until users see it. Every month of waiting counts.
5 reviews before production
Nothing reaches production without passing these five reviews. A person makes two of the calls.
- 1 Idea approved (G0) A person approves the one-page spec: what gets built and how it is measured. Human in the loop
- 2 Tests first (G1) Tests are written before the code, from the acceptance criteria. Reviewed by agents
- 3 Automated quality, security and privacy review (G2) Quality, architecture, UX, accessibility, privacy and security. Reviewed by agents
- 4 Final review, the Minos gate An independent review before release. If it says STOP, nothing ships. Reviewed by agents
- 5 Your approval (G4) A person approves the move to production, with a rollback plan. Human in the loop
Every pillar has an owner and a status. No makeup.
| Pillar | How we cover it | Status |
|---|---|---|
| 01 · Agent identity | Every agent has least privilege; one writer of main; only Atlas writes migrations. | Partial |
| 02 · Runtime guardrails | Security, privacy and isolation are never feature flags. Per-agent circuit breaker. | In progress |
| 03 · Observability and audit | A log of every deploy, small traceable commits, external audit by Mentor. | Running |
| 04 · Agentic FinOps | Which model for which task; cost per delivered unit measured per agent. | In progress |
| 05 · Autonomy levels | 10 decisions reserved for a person: production, money, legal, data, brand, deletion, secrets. | Running |
| 06 · Gates and containment | 5 reviews before production (G0–G4): if the Minos gate says STOP, nothing ships. A rollback plan with every release. | Running |
| 07 · Data perimeters | One database per client. In SERENA, only averages of 5 or more people. | Running |
Underneath it all: entity governance. A person signs architecture decisions (ADRs) and contracts; agents propose.
Our log is the evidence.
commits in 6 days
logged deployments
to production, each with rollback
Minos STOP honored
reserved human decisions
written lessons