Six AI Coding
Workflows
Stop Treating AI Like a Slot Machine · June 22, 2026
AI CodingPrompt EngineeringWorkflowsCodexClaude CodeCursor
Provenance Labs · Generated by Gambit (Hermes) Medium-High Confidence
Executive Summary

Eric Michaud presents six structured prompts that transform AI coding agents from unreliable "slot machines" into consistent development partners. Only one step involves actually building — the rest is the surrounding discipline: context, planning, decomposition, verification, persistence, and knowing when to automate.

1. Interview Me

AI asks probing questions before building. One-time per project, reusable context. Biggest single impact.

2. Implementation Spec

Written plan before changing files. Goal, risky parts, verification, what "done" looks like.

3. Parallel Sub-Agents

Context-gatherer, fast-path finder, skeptic, verifier. Faster + diverse perspectives.

4-6. Verify, Save, Decide

Catch the 80% problem. Save to AGENTS.md. Automate only what you've mastered manually.

Source 1: Eric Michaud / Easy Machine AI (YouTube, June 18, 2026)
The "Slot Machine" Problem
It's Not the Model — It's the Prompt
"Most people treat AI like a slot machine: put in a prompt, pull the lever, hope for the best, then blame the model. The model hasn't been the bottleneck in a little while now."

Key insight: Only one of the six steps is actually building. Everything else is the professional discipline that surrounds the code.

Prompt 1: "Interview Me"
Eliminate Ambiguity in One Pass

The AI becomes the interviewer, asking only the questions needed to remove ambiguity:

This is a one-time-per-project exercise. The resulting context is reusable across the entire project lifecycle. Michaud says this single step has the biggest impact on output quality.

Prompt 2: Implementation Spec
Plan Before Touching Any Files

The AI must produce a written plan covering:

"What done looks like" is a win condition, not just task completion. AI agents check items off a list without achieving the goal. The explicit win condition prevents this.

Prompt 3: Parallel Sub-Agents
Faster Execution + Diverse Perspectives
Context Agent

Reads the codebase and reports back so you don't waste the main context window.

Fast-Path Agent

Finds the quickest route to completion — minimal implementation.

Skeptic Agent

Tries to break the workflow. Finds edge cases and failure modes.

Verifier Agent

Confirms correctness independently. Multiple agents = different answers, not self-confirmation.

CSV pattern: Launch one sub-agent per row — research hundreds of companies in parallel instead of sequentially.

Prompt 4: Verification
Catch the 80% Completion Problem

AI frequently says it completed something when it only did ~80% of the work. The verification prompt catches this gap.

Before building, the AI must specify:

Human handoff boundary: High-impact actions always require final human approval.

Prompt 5: Save Context
Persistent Standards That Compound

AI is non-deterministic: "It is possible to get a 10/10 perfect answer one time and never again." Capturing the configuration that produced the good result is essential for reproducibility.

This builds compounding confidence in the agent-workspace pairing over time.

Prompt 6: The Automation Ladder
Manual → AI-Assisted → Automated

The test: If a 7/10 output gets you yelled at, sued, fired, or divorced — do not automate it.

Good for automation: content research (low impact). Bad: AI trading bots (irreversible consequences).

Risks, Gaps & Uncertainty

Recommended Next Actions

Sources & Process Provenance
1 source · 1 Tier 1

Tier guide:  Tier 1 = Primary institutional source (official website or announcement)  ·  Tier 2 = Company-owned media or trade publication  ·  Tier 3 = Breaking news / single-source — verify independently

Sources: YouTube video content. Full transcript captured via Obsidian Web Clipper (Eric Michaud / Easy Machine AI). Verify key claims independently.

Generated June 22, 2026 · DeepSeek V4 Pro · research-rapid v1.0 · Gambit / brief-to-slides v2.0