diff --git a/README.md b/README.md index 4e223960..15e10682 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# Perstack: Agentic AI Runtime +# Perstack: The Declarative Runtime for Agentic AI
@@ -16,7 +16,7 @@
- **`perstack` CLI**: Develop, test, and deploy Experts from the command line.
- **`create-expert` app**: Creates, tests, and refines new Experts in `perstack.toml` to your specification — powered by agentic AI.
-- **`perstack.toml`**: Define and orchestrate reusable, domain-specialized agents as Experts in declarative TOML.
+- **`perstack.toml`**: Define and orchestrate reusable, domain-specialized agents as Experts in natural language.
- **`@perstack/runtime`**: Execute Experts programmatically. Event-sourced state with step-level checkpoints — resume, replay, and audit any execution from any point.
## Quick Start
diff --git a/docs/README.md b/docs/README.md
index 8d3452b7..16e9b671 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -1,8 +1,8 @@
---
-title: "Perstack: The Agent Runtime"
+title: "Perstack: The Declarative Runtime for Agentic AI"
---
-Define AI agents as declarative **Experts** in TOML. Execute them with deterministic, event-derived tracking. Each Expert runs in its own isolated context — no shared state, no prompt bloat, full execution history.
+Define AI agents as **Experts** in natural language. Execute them with deterministic, event-derived tracking. Each Expert runs in its own isolated context — no shared state, no prompt bloat, full execution history.
- [Getting Started →](./getting-started/walkthrough.md)
- [Browse Registry →](https://platform.perstack.ai/)
diff --git a/docs/contributing/roadmap.md b/docs/contributing/roadmap.md
index 73810f51..6859cc29 100644
--- a/docs/contributing/roadmap.md
+++ b/docs/contributing/roadmap.md
@@ -9,7 +9,7 @@ This roadmap outlines the direction of Perstack development. Priorities may shif
| Feature | Status | Version | Timeline | Description |
| ------------------------------ | :----: | ------- | --------- | ------------------------------------------------- |
-| **Expert definitions** | ✅ | v0.0 | - | Declarative definitions in `perstack.toml` |
+| **Expert definitions** | ✅ | v0.0 | - | Natural-language definitions in `perstack.toml` |
| **Runtime** | ✅ | v0.0 | - | Agent loop, checkpoint/restore, event sourcing |
| **Registry** | ✅ | v0.0 | - | Public registry with write-once versioning |
| **Skills (MCP)** | ✅ | v0.0 | - | MCP-based tool integration |
diff --git a/docs/index.md b/docs/index.md
index 840d0937..9dfdc55b 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -1,11 +1,11 @@
---
title: Perstack Documentation
-description: Define AI agents as declarative Experts in TOML. Execute them with deterministic, event-derived tracking.
+description: Define AI agents as Experts in natural language. Execute them with deterministic, event-derived tracking.
slug: docs
pagefind: true
---
-Define AI agents as declarative **Experts** in TOML. Execute them with deterministic, event-derived tracking. Each Expert runs in its own isolated context — no shared state, no prompt bloat, full execution history.
+Define AI agents as **Experts** in natural language. Execute them with deterministic, event-derived tracking. Each Expert runs in its own isolated context — no shared state, no prompt bloat, full execution history.
## Quick Start
@@ -21,11 +21,11 @@ npx perstack start code-reviewer "Review PR #42 for security issues"
## Why Perstack?
-Agent frameworks help you **build** agents. Perstack is a **runtime** that **executes** them. You define Experts declaratively in TOML — Perstack handles execution, isolation, and state.
+Agent frameworks help you **build** agents. Perstack is a **runtime** that **executes** them. You define Experts in natural language via TOML — Perstack handles execution, isolation, and state.
| | |
| :--- | :--- |
-| **Declarative definitions** | Expert definitions in `perstack.toml` are plain text. Domain experts write the behavior; developers focus on integration. |
+| **Natural-language definitions** | Expert definitions in `perstack.toml` are plain text. Domain experts write the behavior; developers focus on integration. |
| **Isolation by design** | Each Expert runs in its own context — workspace boundaries, environment sandboxing, and tool whitelisting. No shared state between runs. |
| **Event-derived execution** | Step-level checkpoints make runs reproducible. Resume from any step, debug, replay, and audit every decision. |
| **Multi-provider support** | Anthropic, OpenAI, Google, DeepSeek, Ollama, Azure, Bedrock, Vertex. Switch providers with one config change. |