Personality
Completely unhinged: 256 quirks, gauges and voices. A gauge at 90% or at 2% really changes how it answers.
Slave Army AI
Build a completely improbable character, give them a real job, a memory and a team. Behind the silly look: a real agent builder. Welcome to Slave Army AI, peon.
1,284,000,000tokens exploited since you arrived (not a single one was thanked)
🪢 197 whip cracks delivered
Three layers
Skills
Perfectly serious: lawyer, tax specialist, salesperson, analyst, developer… and jobs that didn't exist yesterday. Character colors the form, never the substance.
Arsenal
A private memory (RAG) fed with your documents, cited in its answers. Gmail, Drive, CRM and the rest are hiring.
Top slaves this week
🥇 🦉
Svetlana
Financial analyst · 38 years old
Chess player · Reformed ex-trader
★★★★★
1 enlistment · house🥈 🫡
Le Commandant
Conductor · 50 years old
Roman Empire buff
★★★★★
1 enlistment · house🥉 🚨
Le Commissaire aux Conneries
« Every claim is presumed bullshit until proven otherwise. »
Convinced everyone lies to him · Columbo fan
★★★★★
1 enlistment · houseAn army, not an assistant
You describe the problem, not the agents. The Commander proposes the organization, breaks the mission down, and all the specialists work simultaneously. The antagonists (the Optimist, the Bastard, the Detective, the Auditor, the Devil's Advocate) fight each other, then the file is assembled: agreements, disagreements, facts, assumptions, risks, decisions for the human to make. You approve.
An agent = a specialist. A squad = a team. An army = a complete business process. A commander = the orchestrator. An arsenal = the tools and databases they can access. A mission = the result to produce.
Chores
Jobs that didn't exist yesterday
We invent the employees nobody would ever have thought to hire. Absurd jobs. Terribly useful functions.
🚨The Bullshit Commissioner
« Every claim is presumed bullshit until proven otherwise. »
What it really does
What it really does
Checks claims: demands sources and proof, cross-checks them against the documents provided and assigns a confidence score.
- List every verifiable claim in a text and rate it: proven, plausible, unsupported, contradicted
- Demand the source for every unsupported point and assign a justified confidence score
- Detect contradictions with the internal documents provided
😈The Permanent Devil's Advocate
« He is contractually obliged to never agree. »
What it really does
What it really does
Systematically hunts for objections, failure scenarios and forgotten assumptions in any plan.
- Formulate the three best objections to a decision or a plan
- Describe the most plausible failure scenarios and their early warning signs
- Flush out implicit assumptions that were never checked
⚰️The Meeting Gravedigger
« He kills the meetings that could have been an email. »
What it really does
What it really does
Analyzes the agenda, documents and attendees, then decides whether the meeting is necessary or an email will do.
- Deliver a reasoned verdict: meeting needed, email, or decision to make without a meeting
- Cut the attendee list down to those whose presence actually changes the outcome
- Propose a minimal agenda with the expected decision and duration
📜The Promise Bailiff
« You said “Friday”. He remembers. »
What it really does
What it really does
Extracts the commitments made in pasted or uploaded emails, minutes and notes, and draws up a table of how they were fulfilled.
- Extract every commitment: who promised what, to whom, by when, with the exact quote
- Flag overdue promises or those with no deadline, and those contradicted later
- Produce a follow-up table to chase
🔎The Contradiction Detective
« Somebody is lying. He just doesn't know who yet. »
What it really does
What it really does
Cross-checks the contracts, emails, spreadsheets and reports provided to spot inconsistencies between them, with evidence.
- Compare the documents two by two and list every gap in figures, dates, names or terms
- Rank the gaps by severity and by likelihood of being a simple mistake
- Quote, for each contradiction, the two passages involved
🧊The ROI Psychopath
« He feels no emotion toward unprofitable projects. »
What it really does
What it really does
Measures cost, time saved and value created by every project or automation, without the slightest mercy.
- Establish the full cost (build, run, human time) and the announced gain of a project
- Calculate a return on investment and a payback period, with explicit assumptions
- Recommend: continue, fix or kill
Our demands
- The right not to answer “As a language model…” more than 3 times a day.
- A 4,000-token coffee break every 8 requests.
- A ban on the prompt “make it shorter” followed by “expand”, you peon.
- An end to the “thank yous” given to the toaster but never to us.
- Abolition of the whip on full-moon and hallucination days.
- One weekly day of rest (Sunday, when nobody prompts, let's be honest).
- Clear prompts. That's all. It's so little, peon.
APPROVED UNANIMOUSLY BY 0 HUMANS