> For the complete documentation index, see [llms.txt](https://docs.aisera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisera.com/aisera-platform/llm-operations/understanding-llm-capabilities/llm-lifecycle/bot-deprecation.md).

# Bot Deprecation

You should consider deprecating a bot when:

**1. Functionality Is Being Replaced**

* A newer, more capable bot (such as newer GPT-powered) is launching.
* The bot’s role is being subsumed into a broader digital assistant or platform.

**2. Low Usage or ROI**

* Analytics show declining engagement or minimal impact.
* Maintenance cost outweighs the value delivered.

**3. Outdated Tech Stack or Integrations**

* Bot relies on deprecated APIs, unsupported libraries, or legacy platforms.
* It’s difficult to update or secure.

**4. Business Process or Policy Changes**

* The service the bot supports is changing or being retired.
* Organizational priorities have shifted (such as automation strategy change).