> ## Documentation Index
> Fetch the complete documentation index at: https://docs.stackshift.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Current status and limitations

> Exactly what the AI agents and diagnosis can and cannot do today, and the guardrails that constrain them.

<Tip>
  **Live.** This area is documented as current, user-reliable behavior.
</Tip>

## Goal

Set accurate expectations for the AI features before you rely on them.

## Prerequisites

* Familiarity with the StackShift AI agents

## Workflow

<Steps>
  <Step>
    Use agents for the tasks listed as fully live below.
  </Step>

  <Step>
    Account for the current limitations before depending on an agent for production work.
  </Step>

  <Step>
    Keep human operational judgment and direct logs in the loop.
  </Step>
</Steps>

## What is fully live

* The deploy, database, debug, ops, and WordPress agents.
* Automatic build-failure diagnosis (pattern matching for everyone; LLM analysis on paid plans).
* The propose-then-confirm action model across every agent.

## Current limitations

* LLM-backed build diagnosis requires an active paid plan.
* Agents propose actions for you to confirm; they do not act autonomously except when you explicitly ask the deploy agent to run a project creation all the way through.
* Agents will not touch environment files, secrets, GitHub workflow files, or credentials.

## Operator-first by design

These limits are deliberate. The agents are built to accelerate real operational work while keeping a human in the loop for anything that changes infrastructure. When a diagnosis or proposal disagrees with the raw evidence, trust the evidence.

## Expected result

<Check>
  You rely on the AI features with accurate expectations and know where the guardrails are.
</Check>

## Related guides

<CardGroup cols={2}>
  <Card title="StackShift AI agents" href="/ai-features/ai-agents">
    StackShift runs specialized agents that can create projects, fix failed builds, manage databases, triage incidents, and operate WordPress — each one proposing a confirmable action before anything changes.
  </Card>

  <Card title="AI build diagnosis" href="/ai-features/ai-diagnosis">
    Automatic root-cause analysis for failed builds: a known-pattern matcher backed by Claude LLM analysis produces a categorized diagnosis with confidence and concrete fix steps.
  </Card>
</CardGroup>