syntaxai/tdd.md · commit 0a58850

Homepage: add stack diagram showing SAMA as the architecture layer (#5)

Visualises the "compose, don't replace" frame as a four-layer stack so
readers see the layers as complementary before they parse the table:

- SWE-bench    grades the agent
- Factory.ai   scores the repo
- SAMA  ★      shapes the code   ← the only layer with a binary CI gate
- AGENTS.md    instructs the agent

Closes the last sub-deliverable of #5.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

author: syntaxai <[email protected]>
date: 2026-05-22 08:41:10 +01:00
parent: 1e56e71
commit: 0a58850afe42b45ff80a0921e6cb5a6521fa2972

1 file changed · +12 −0

modified content/home.md +12 −0

@@ -19,6 +19,18 @@ Read the full discussion in [/sama](/sama). The standalone, language-agnostic [v
19	19
20	20	SAMA composes with the tools you already use. Use AGENTS.md to instruct the agent and SAMA to shape the code; use Factory's scorecard for breadth and SAMA for depth on the architectural pillar; run SWE-bench to grade the agent and SAMA to grade what the agent left behind.
21	21
	22	+```
	23	+ SWE-bench · grades the agent
	24	+ ─────────────────────────────────────────────────────────
	25	+ Factory.ai Readiness · scores the repo (8 pillars)
	26	+ ─────────────────────────────────────────────────────────
	27	+ SAMA ★ · shapes the code (4 pillars, CI-gated)
	28	+ ─────────────────────────────────────────────────────────
	29	+ AGENTS.md · instructs the agent
	30	+```
	31	+
	32	+★ SAMA is the architecture layer — the only one with a binary CI gate. The others assess, grade, or instruct; SAMA constrains.
	33	+
22	34	\| \| What it does \| SAMA's role alongside it \|
23	35	\|---\|---\|---\|
24	36	\| [SWE-bench](https://www.swebench.com/) \| Scores agents on real GitHub issues \| SAMA scores codebases, not agents \|

raw .diff