Added project documentation in wiki and established INTENT.md

This commit is contained in:
2026-06-16 00:58:43 +02:00
parent 95b729cc53
commit 71ef5f4734
21 changed files with 1442 additions and 31 deletions

65
wiki/PricingModel.md Normal file
View File

@@ -0,0 +1,65 @@
PricingModel
*Pricing for Kaizen agents*
# KaizenAgentic Pricing Model
### 1. Base Assumption
* **Token Cost (C):** The unit price per token for the underlying foundation model (e.g., OpenAI GPT-4o, Anthropic Claude, etc.).
* KaizenAgentic charges are always calculated as a multiple of this base token cost.
---
### 2. Capability Multipliers
Each subagent is classified by its **capability tier**, which reflects complexity, optimization overhead, and real-world utility.
| **Tier** | **Agent Capability** | **Multiplier (x)** | **Example Use Case** |
| -------- | ---------------------- | ------------------ | -------------------------------------------------------------- |
| 1x | Baseline wrapper agent | 1× | Simple automation around base LLM calls |
| 2x | Enhanced agent | 2× | Adds logging, minimal optimization, lightweight feedback loops |
| 3x | Professional agent | 3× | Integrated metrics, test coverage deltas, developer UX signals |
| 4x | Expert agent | 4× | Adaptive refinement, A/B testing, rollback mechanisms |
| 5x | KaizenAgent premium | 5× | Full meta-optimization loop, cross-subagent orchestration |
---
### 3. Pricing Formula
$$
\text{KaizenAgentic Price per Token} = C \times M
$$
Where:
* **C** = cost per token of the underlying LLM
* **M** = capability multiplier (2x5x)
Example:
* GPT-4o base token = $0.01 / 1K tokens
* KaizenAgent Premium (5x) = $0.05 / 1K tokens
---
### 4. Service Tiers
On top of token-based billing, KaizenAgentic can introduce **subscription layers** to cover operational support:
* **Free Tier** → 1x baseline agents, capped usage, no optimization feedback.
* **Pro Tier** → 2x3x agents, includes monitoring dashboards.
* **Enterprise Tier** → 4x5x agents, includes dedicated KaizenAgent meta-optimization + SLAs.
---
### 5. Value Rationale
* **Fair:** Always anchored in base token price (transparent to clients).
* **Scalable:** Higher capability → higher multiplier → more value.
* **Predictable:** Clients can forecast spend by capability tier, independent of vendor-specific LLM pricing changes.
* **Flexible:** Basemodel transparent to avoid basemodel lockin supporting various providers (ChatGPT, Claude, Cursor, etc.).
xxx