Agentic Software Engineering
https://ase.tools
About
Agentic Software Engineering (ASE) is the opinionated companion
tooling of Dr. Ralf S. Engelschall for combining the approach of
Agentic AI and Software Engineering with the help of Agentic
AI Coding Tools like Claude Code. ASE primarily consists of a
Claude Code plugin and a Command-Line Interface (CLI) tool, including
an MCP service. ASE provides skills and commands to support
the most important, recurring work-steps in the primary disciplines
of Software Engineering, especially in the discipline Software
Development.
ASE is primarily motivated by the following statement of Dr. Ralf S. Engelschall:
"Software developers in the industrial Software Engineering context,
using the Agentic AI Coding tool Claude Code (or alternatively
Github Copilot CLI), in their daily recurring tasks, should leverage
from pre-manufactured skills which incorporate reasonable methodology
and automation aspects to boost their productivity."
Notices
[!NOTE]
TERMINOLOGY: The discipline of Agentic Software Engineering
in general is Software Engineering, supported by autonomous AI
Agents to perform tasks across the software development lifecycle.
This ASE product in particular is also agentic, but not
strictly based on autonomous agents. Instead, ASE focuses on
supporting the role of a Software Engineer with Agentic AI Coding
Tools towards multi-step operations and a plan/task-driven approach,
but still strongly focuses on Human-in-the-Loop.
[!NOTE]
TOOL SUPPORT FOCUS: The primary focus of ASE is on the Agentic AI Coding tool Claude
Code. The secondary focus is on the support
for GitHub Copilot CLI
(just set environment variable ASE_TOOL=copilot). In the future,
additional support could be provided also for alternative tools
— if their agent harness features (especially hooks, interactive
user dialog tool, etc.) realistically allow it.
[!CAUTION]
DEVELOPMENT STATE: ASE is still under active initial development and
somewhat incomplete. All existing functionality is already
stable and used on a daily basis in production. If you are not
a steadfast early adopter, it is perhaps better to visit this project
again once we have reached at least version 0.9.x! Otherwise, feel
free to join us on our journey towards Agentic Software
Engineering.
Unique Selling Points
Check out the following scenarios and corresponding ASE examples to
see whether ASE is right for you:
-
Boosted Sessions:
You want to speed up your interactive sessions and at the same time
reduce costs by reducing the amount of produced LLM output tokens?
→ /ase-meta-persona
engineer or even /ase-meta-persona
caveman
-
Alternative Approach Funnel:
You prefer a plan-driven approach, but the agent harness's
Plan Mode is too unstructured and too direct because you want to
leverage a funnel of alternative approaches first?
→ /ase-code-craft
hello: "ase hello" CLI command which prints a nice "Hello World" in red
-
Named and Persisted Plans:
You prefer a plan-driven approach, but the agent harness's Plan Mode is
regularly too weak, because you want named, persisted, cross-session
reachable, and strictly structured plans?
→ /ase-task-edit
hello
-
Plan Stress-Testing:
You have a task plan, but want to be relentlessly grilled about every
essential aspect of it until you and the agent reach a shared
understanding and no open decisions remain?
→ /ase-task-grill
hello
-
Implementation Preflights:
You prefer a plan-driven approach, but want to pre-flight the
implementation without later having to rewind artifacts via the version
control system or the agent harness's session history?
→ /ase-task-preflight
hello
|
