Asoba Zorora Documentation
Home Insights Contact Us

Slash Commands Reference

Complete reference for all Zorora slash commands and workflows.

Overview

Slash commands force specific workflows, bypassing automatic routing. Use them when you want to ensure a particular workflow is executed.

Workflow Commands

Force deep research workflow with multi-source synthesis

/search <query>

What it does:

  1. Fetches newsroom headlines (if available, filters by relevance)
  2. Searches the web (Brave Search API + DuckDuckGo fallback)
  3. Searches academic databases (7 sources: Scholar, PubMed, CORE, arXiv, bioRxiv, medRxiv, PMC)
  4. Synthesizes findings from all sources with citations
  5. Returns comprehensive answer with source URLs

When to use:

Examples:

/search latest developments in renewable energy policy
/search bitcoin vs gold price movements in 2025
/search major AI trends in South America

Output format:

Configuration:

/ask

Force conversational mode without web search

/ask <query>

What it does:

When to use:

Examples:

/ask can you explain that more simply?
/ask what did you mean by "virtual power plant"?
/ask how would I implement that in Python?

Model used: Reasoning model (qwen2.5:32b or configured alternative)

Note: Model knowledge cutoff may be outdated for current events. Use /search for time-sensitive queries.

/code

Code generation or file editing with specialist model

/code <prompt>

What it does:

For new code (no existing file detected):

For existing files (auto-detected in prompt):

File Detection Patterns:

/code update script.py from "goodbye" to "hello"  → detects script.py
/code fix the typo in utils.py line 15            → detects utils.py
/code change config.json to use port 8080         → detects config.json

When to use:

Examples:

# New code generation
/code write a function to parse JSON files with error handling
/code create a REST API endpoint for user authentication

# File editing (v2.5+)
/code update main.py to add logging
/code fix the typo in config.py line 42
/code change api.py to use async/await

Model used: Coding specialist (model-agnostic in v2.5+)

Workflow Comparison (v2.5+):

Command Scope Phases Best For
/code Single file/snippet 1-2 (plan + generate/edit) Quick edits, snippets
/develop Entire codebase 5 (preflight → explore → plan → execute → lint) Features, refactoring

Saving output:

> /code write a CSV parser
[Code generated...]
> /save csv_parser.py
Saved to: csv_parser.py

/develop

Multi-step code development workflow

/develop <development request>

What it does:

Phase 0: Pre-flight Checks

Phase 1: Codebase Exploration

Phase 2: Planning

Phase 3: User Approval

Phase 4: Execution

Phase 5: Lint & Validate

When to use:

Examples:

/develop Add user authentication to my Flask app
/develop Refactor the API to use async/await
/develop Add unit tests for the user service

Requirements:

/image

Generate image with FLUX (text-to-image)

/image <prompt>

What it does:

When to use:

Examples:

/image a futuristic solar farm at sunset
/image minimalist logo for an AI research company
/image detailed technical diagram of a battery storage system

Model used: black-forest-labs/FLUX.1-schnell

Output:

Tips:

/vision

Analyze image with vision model (OCR and content extraction)

/vision <image_path> [optional task]

What it does:

When to use:

Examples:

/vision screenshot.png
/vision chart.png describe the trends shown
/vision diagram.jpg extract all labels and annotations
/vision receipt.png convert to structured data

Default task: “Convert this image to markdown format, preserving all text, tables, charts, and structure. Use OCR to extract any text.”

Model used: Vision-language model (qwen/qwen3-vl-4b)

Supported formats: PNG, JPG, JPEG, GIF, WebP

Output:

/deep

Terminal deep research (v2.5+)

/deep <query>

What it does:

When to use:

Examples:

/deep What are the latest developments in transformer architectures?
/deep How do mRNA vaccines work?
/deep Latest renewable energy policy changes in South Africa

Output:

Note: This command provides full feature parity with Web UI research.

ONA Platform Commands (v2.5+)

Remote commands for interacting with ONA platform ML model observation workflows. These commands require ONA platform integration configured via environment variables.

/ml-list-challengers

List challenger models for a customer

/ml-list-challengers <customer_id>

/ml-show-metrics

Show evaluation metrics for a model

/ml-show-metrics <model_id>

/ml-diff

Compare challenger vs production model

/ml-diff <challenger_id> <production_id>

/ml-promote

Promote challenger model to production

/ml-promote <customer_id> <model_id> <reason> [--force]

Requires confirmation unless --force flag is used.

/ml-rollback

Rollback production model to previous version

/ml-rollback <customer_id> <reason>

Requires confirmation.

/ml-audit-log

Get audit log for a customer

/ml-audit-log <customer_id>

ONA Platform Configuration

Set environment variables before running Zorora:

# Option 1: Retrieve from AWS SSM Parameter Store (recommended)
source <(./scripts/get-global-training-api-credentials.sh)

# Option 2: Manual configuration
export ONA_API_BASE_URL="https://your-api-endpoint.amazonaws.com/api/v1"
export ONA_API_TOKEN="your-api-token-here"
export ONA_USE_IAM="false"

Environment Variables:

System Commands

/models

Interactive model selector

/models

What it does:

When to use:

/config

Show current routing configuration

/config

What it does:

When to use:

/history

Browse saved conversation sessions

/history

What it does:

When to use:

/help

Show available commands

/help

What it does:

When to use:

exit, quit, q

Exit the REPL

exit
quit
q

What it does:

Natural Language Queries

Zorora automatically routes natural language queries to appropriate workflows:

Research queries (automatically routed to deep research):

What are the latest developments in LLM architectures?
Why do solar panels degrade over time?
How does battery storage work?

Code queries (automatically routed to code generation):

Write a function to validate email addresses
Create a REST API endpoint
Refactor this code to use async/await

Development queries (automatically routed to /develop):

Add user authentication to my Flask app
Refactor the API to use async/await
Add unit tests for the user service

Command Priority

Commands are processed in this order:

  1. Slash commands - Highest priority, force specific workflows
  2. File operations - Save, load, list, show, delete
  3. Code generation - Write, create, generate + code keywords
  4. Research queries - What, why, how, tell me keywords
  5. Simple Q&A - Fallback to conversational mode

Tips & Best Practices

Use Slash Commands When:

Use Natural Language When:

Command Combinations:

# Research then code
/search latest Python async patterns
/code implement async pattern from research

# Code then develop
/code create user model
/develop add authentication using this model

# Image then vision
/image technical diagram of API architecture
/vision flux_output_*.png extract all labels

Troubleshooting

Command Not Recognized

Problem: Slash command not working

Solution:

Workflow Not Executing

Problem: Command runs but wrong workflow executes

Solution:

Command Hangs

Problem: Command takes too long or hangs

Solution:

See Also