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

# Context / Costs optimization

> Using dx --llm flag for seamless AI agent automation and non-interactive workflows

The `--llm` flag tries to contribute to solve **context optimization** problem for AI agents. Instead of manually writing hundreds of lines describing available tools, agents just run `dx --llm` and automatically discover what they can do in any project.

## Context Optimization Problem

**Before dx --llm**: Manual context files that get outdated

```markdown theme={null}
<!-- agents.md - manually maintained -->
Available tools in this project:
- Build: cargo build --release
- Test: cargo test
- Deploy: kubectl apply -f k8s/
- Lint: cargo clippy
- Format: cargo fmt
<!-- Gets outdated when commands change -->
```

**With dx --llm**: Dynamic, always-current context

```bash theme={null}
# Agent runs this at start of every task
$ dx --llm
Use dx non-interactively. No TUI.
- dx aliases  # list alias table
- dx <alias>  # run leaf cmd; returns exit code
Rules: do not expect prompts; check exit codes.

# Then discovers actual available commands
$ dx aliases
ALIAS    NAME           TYPE  DETAILS
build    Build Release  cmd   cargo build --release
test     Run Tests      cmd   cargo test --all
deploy   Deploy K8s     cmd   kubectl apply -f k8s/
lint     Code Quality   cmd   cargo clippy -- -D warnings
```

**Result**: Agent always knows current project capabilities without manual context management.

## Context & Cost Optimization

### The dx --llm

Dynamic context discovery in minimal tokens:

```bash theme={null}
# Agent workflow (4 commands, ~50 tokens total)
1. dx --llm                     # Get usage instructions
2. dx aliases                   # Discover commands
```

# Agent starts each task with 2 commands:

**After dx --llm:**

```bash theme={null}
$ dx --llm && dx aliases
# Gets current, accurate list of ALL available commands
```

### Auto-Updated Context

```bash theme={null}
# When project evolves, dx context updates automatically:

# Developer adds new command to dx.yaml:
- name: "Deploy with Rollback"
  alias: "deploy-safe"
  cmd: "kubectl apply -f k8s/ && kubectl rollout status"

# Next time agent runs:
$ dx aliases
# Automatically includes new deploy-safe command
# No manual context file updates needed!
```

## Agent-Friendly Design

<CardGroup cols={2}>
  <Card title="No TUI Required" icon="terminal">
    Commands run directly in shell, perfect for automated environments
  </Card>

  <Card title="Exit Code Aware" icon="check-circle">
    Proper exit codes enable AI agents to detect success/failure
  </Card>

  <Card title="Stdio Inheritance" icon="arrow-right">
    Commands inherit stdin/stdout for seamless pipeline integration
  </Card>

  <Card title="Recording Built-in" icon="video">
    AI can record sessions for debugging and analysis
  </Card>
</CardGroup>

## AI Safety & Verification

### Command Safety Check

```bash theme={null}
# Verify if command/script is safe for AI execution
dx ai verify ./deploy.sh
dx ai verify "rm -rf /"           # Obviously unsafe
dx ai verify "cargo build"        # Generally safe
```

**AI analyzes:**

* **Destructive patterns** - `rm -rf`, `dd`, `format`, etc.
* **Network operations** - External API calls, data uploads
* **File system risks** - Writing to system directories
* **Permission escalation** - `sudo`, `su`, privilege requests
* **Resource consumption** - Infinite loops, fork bombs

**Output examples:**

```bash theme={null}
$ dx ai verify "cargo build --release"
✅ SAFE: Standard build command, no destructive operations

$ dx ai verify "./deploy.sh"  
⚠️  REVIEW NEEDED: Deploys to production, requires manual confirmation

$ dx ai verify "curl -X POST api.com/delete-all"
❌ UNSAFE: Destructive API operation detected
```

### Safety Configuration

```toml theme={null}
# config.toml
[ai.safety]
auto_verify = true              # Check all commands before execution
block_unsafe = true             # Block obviously dangerous commands  
require_confirmation = ["deploy", "delete", "rm"]  # Always confirm these
whitelist_patterns = ["cargo", "npm", "git"]       # Always allow these
```

<Warning>
  **AI safety is improving rapidly but not perfect.** Always review AI recommendations, especially for:

  * Production deployments
  * Data deletion operations
  * System configuration changes
  * External API calls with side effects

  Use AI verification as a **first line of defense**, not the only one.
</Warning>

<Tip>
  AI agents work best when dx aliases are semantically meaningful (`build`, `test`, `deploy`) rather than cryptic (`cmd1`, `run-x`).
</Tip>