diff --git a/README.md b/README.md
index 7305378..79090cc 100644
--- a/README.md
+++ b/README.md
@@ -27,35 +27,13 @@ speck RetryHandler {
SpeckDL compiles through a deterministic pipeline:
-```
-SpeckDL ──► Z3 (SMT solver) ──► DST (decision structures) ──► WASM
- │ │ │ │
- │ verify constraints compile to decision deploy verified
- │ catch contradictions trees artifacts
- │
- └── Provenance graph grows automatically at each stage
-```
+
No LLMs in the compilation path. No non-determinism. Same input, same output — every time.
## Architecture
-```
-┌─────────────────────────────────────────────────┐
-│ Orchestrator │
-│ Accepts Specks, decomposes tasks │
-└───────────┬─────────────────┬───────────────────┘
- │ │
- ┌───────▼───────┐ ┌───────▼───────┐
- │ Team Lead │ │ Team Lead │
- │ Verification │ │ Codegen │
- └───────┬───────┘ └───────┬───────┘
- │ │
- ┌───────▼───────┐ ┌───────▼───────┐
- │ Z3 SME │ │ TypeScript │
- │ (verify) │ │ SME (emit) │
- └───────────────┘ └───────────────┘
-```
+
- **Orchestrator** — client entry point, task decomposition
- **Team Leads** — manage specialized agents, elastic scaling
diff --git a/docs/consulting-packages.md b/docs/consulting-packages.md
index 5234682..a0129bb 100644
--- a/docs/consulting-packages.md
+++ b/docs/consulting-packages.md
@@ -156,34 +156,7 @@ Speckl is the data source for the advisory work. Scott doesn't advise from theor
## Pipeline Flow
-```
- ┌─────────────────┐
- │ Content Entry │
- │ (book, essay, │
- │ workshop) │
- └────────┬────────┘
- │
- ┌────────▼────────┐
- │ First Call │
- │ "What do you │
- │ do?" → 1L │
- └────────┬────────┘
- │
- ┌────────▼────────┐
- │ Package 1 │
- │ Assessment │
- │ $5K–$10K │
- └────────┬────────┘
- │
- ┌─────────────┼─────────────┐
- │ │ │
- ┌────────▼───┐ ┌─────▼──────┐ ┌───▼────────┐
- │ Package 2 │ │ Package 3 │ │ Both │
- │ Speckl │ │ Fractional │ │ (P2 → P3) │
- │ $30K–$50K │ │ $10K–$15K │ │ │
- └────────────┘ │ /mo │ └────────────┘
- └────────────┘
-```
+
Package 1 feeds into both. Package 2 often converts to Package 3 for ongoing retainers. Some high-maturity clients skip straight to Package 3.
diff --git a/docs/diagrams/architecture.svg b/docs/diagrams/architecture.svg
new file mode 100644
index 0000000..936720e
--- /dev/null
+++ b/docs/diagrams/architecture.svg
@@ -0,0 +1,45 @@
+
diff --git a/docs/diagrams/consulting-pipeline.svg b/docs/diagrams/consulting-pipeline.svg
new file mode 100644
index 0000000..4072581
--- /dev/null
+++ b/docs/diagrams/consulting-pipeline.svg
@@ -0,0 +1,47 @@
+
diff --git a/docs/diagrams/plan-flow.svg b/docs/diagrams/plan-flow.svg
new file mode 100644
index 0000000..121b474
--- /dev/null
+++ b/docs/diagrams/plan-flow.svg
@@ -0,0 +1,47 @@
+
diff --git a/docs/diagrams/speckdl-pipeline.svg b/docs/diagrams/speckdl-pipeline.svg
new file mode 100644
index 0000000..305eb29
--- /dev/null
+++ b/docs/diagrams/speckdl-pipeline.svg
@@ -0,0 +1,47 @@
+
diff --git a/docs/strategy.md b/docs/strategy.md
index 9ff7df9..55c1e71 100644
--- a/docs/strategy.md
+++ b/docs/strategy.md
@@ -13,34 +13,7 @@
Plan D (open standard + foundation) is not one option among four. It is the **engine**. All revenue flies by on the credibility, adoption, and ecosystem that the open standard builds.
-```
-┌─────────────────────────────────────────────────────┐
-│ PLAN D │
-│ Speckl Open Standard + Foundation │
-│ (SpeckDL language, Dark Provenance methodology, │
-│ reference agents, community, certification) │
-└────────────┬──────────────┬─────────────────────────┘
- │ │
- ▼ ▼
- ┌────────────────┐ ┌──────────────────────────┐
- │ PLAN C │ │ PLAN A │
- │ Consulting ├─▶ Developer Tool (SaaS) │
- │ + Services │ │ - Self-serve PLG │
- │ - Validates │ │ - Scales from C learnings│
- │ - Funds early │ │ - Generates provenance │
- │ - Builds case │ │ graph data │
- │ studies │ │ │
- └────────────────┘ └──────────────┬─────────────┘
- │
- ▼
- ┌────────────────────────┐
- │ PLAN B │
- │ Compliance Infra (API) │
- │ - Feeds on SaaS data │
- │ - Highest margin │
- │ - Enterprise sticky │
- └────────────────────────┘
-```
+
**The flow:** Open standard (D) builds the language and community → hands-on consulting (C) validates the methodology and funds development → SaaS (A) scales it to more teams and generates real provenance graph data → compliance API (B) monetizes that data at enterprise margins.