👑 PromptKing← All Insights
TECHNICAL ALIGNMENT BRIEFArchitecture · Engineering

12 Factor Agents: How PromptKing Scores 11/12

The open-source framework for reliable LLM-powered software has 23.4K GitHub stars. PromptKing implements 11 of 12 factors in production. One gap — Factor 9 — is spec'd for v4.11.0.

June 30, 2026 · @PromptKing32
11
Factors Implemented
1
Gap: Factor 9 Error Events
23.4K
GitHub Stars (humanlayer)
v4.11.0
Factor 9 Target Version

The Framework

12 Factor Agents is an open-source framework for building reliable LLM-powered software. Core thesis: the most reliable agents in production are mostly deterministic code with small LLM steps at specific decision points. PromptKing is built on exactly this principle.

The One Gap: Factor 9

Factor 9 asks: when a tool call fails with an error (not loops — fails), does the system compact the error into the context window with a consecutive failure counter and escalate to a human at a threshold? PromptKing has cycle detection (loops). The named error event type with consecutive failure threshold is v4.11.0.

The v4.11.0 Fix

error_type on trajectory_nodes (tool_failure / timeout / rate_limit / schema_violation / policy_rejection). consecutive_error_count per graph. containment_threshold configurable per org (default: 3). When threshold hit → same containment signal as cycle detection → Approval Required.

Why This Matters for M&A

An 11/12 score with a documented, scoped, imminent fix on the one gap is a stronger diligence story than a vague claim of full compliance. The scorecard is the argument. The v4.11.0 spec closes it.

SCORECARD SUMMARY

11
of 12 factors implemented in production
Factor 9 (consecutive error events) → v4.11.0

SEE IT LIVE

View Trajectory Governance →

👑 PromptKing Inc. · promptking32.com · @PromptKing32 · info@promptking32.com

12 Factor Agents: How PromptKing Scores 11/12 | PromptKing | PromptKing AI FinOps