⚡ Digital Labour — 24 AI Agents for Business Automation

Your entire back-office, automated. Run any of 24 specialized AI agents through plain English. Sales outreach, lead generation, content repurposing, SEO, ad copy, bookkeeping, proposals, market research, tech docs — all with built-in QA verification.

Quick Start

Set your API URL (or use the default production endpoint):
CODEBLOCK0

Test the connection:
CODEBLOCK1

Run an agent:
CODEBLOCK2

Available Agents (24 Total)

Revenue & Sales (5 agents)

Agent	Command	What it does
salesoutreach	INLINECODE0	Company research + 3-email outreach sequence
leadgen

run lead_gen '{"industry":"fintech","region":"North America"}' | Generate qualified lead lists for any industry |

| email_marketing | run email_marketing '{"product":"SaaS CRM","audience":"small business owners"}' | Full email campaign with subject lines + body copy | | proposal_writer | run proposal_writer '{"project":"Website redesign","client_name":"Acme Corp"}' | Professional project proposals with pricing | | ad_copy | run ad_copy '{"product":"AI writing tool","platform":"google"}' | Platform-optimized ad copy (Google/Facebook/Instagram) |

Content & Marketing (4 agents)

Agent	Command	What it does
contentrepurpose	INLINECODE5	Repurpose content into tweets, LinkedIn, newsletters
seocontent

run seo_content '{"keyword":"AI automation","content_type":"blog"}' | SEO-optimized content (blog/landing/pillar pages) |

| social_media | run social_media '{"topic":"AI trends","platform":"linkedin","cta_goal":"drive signups"}' | Platform-native social posts with CTAs | | press_release | run press_release '{"announcement":"Product launch","company":"Bitrage"}' | PR-ready press releases |

Operations & Data (4 agents)

Agent	Command	What it does
dataentry	INLINECODE9	Structure and clean raw data
webscraper

run web_scraper '{"source_url":"https://example.com","extraction_target":"pricing"}' | Extract structured data from web pages |

| crm_ops | run crm_ops '{"contact_data":"<contact info>","action":"segment"}' | CRM updates, segmentation, and reporting | | bookkeeping | run bookkeeping '{"transactions":"<transaction data>","period":"monthly"}' | Transaction categorization and financial reports |

Documents & Research (4 agents)

Agent	Command	What it does
docextract	INLINECODE13	Extract structured data from invoices, contracts, resumes
marketresearch

run market_research '{"topic":"electric vehicles","depth":"detailed"}' | Market analysis at overview/detailed/comprehensive depth |

| business_plan | run business_plan '{"business_idea":"AI tutoring app","market":"K-12 education"}' | Full business plans with financial projections | | tech_docs | run tech_docs '{"code_or_api":"<code or API spec>","doc_type":"api"}' | API docs, READMEs, and tutorials |

Professional Services (3 agents)

Agent	Command	What it does
supportticket	INLINECODE17	Categorize, prioritize, draft reply for support tickets
productdesc

run product_desc '{"product_specs":"<specs>","tone":"luxury"}' | Product descriptions in any tone |

| resume_writer | run resume_writer '{"career_data":"<career history>","target_industry":"tech"}' | ATS-optimized resumes for any industry |

Management Layer (4 agents)

Agent	Command	What it does
contextmanager	Internal orchestration	Maintains context across multi-agent pipelines
qamanager

Internal orchestration | Quality assurance on every agent output |

| production_manager | Internal orchestration | Workflow scheduling and resource allocation | | automation_manager | Internal orchestration | Autonomous task routing and retry logic |

Helper Script

INLINECODE20 — Python script (stdlib only) for all API operations.

Commands:

Command	Description
INLINECODE21	Check API health status
INLINECODE22

List all available agents with input schemas |
| run <agent> <json_inputs> | Run a specific agent with JSON inputs |
| batch <json_file> | Run multiple agents from a JSON batch file |

Examples:
CODEBLOCK3

Batch Processing

Create a JSON file with multiple tasks:
CODEBLOCK4

Run them all:
CODEBLOCK5

Multi-Agent Workflows

Chain agents together for complex operations:

Lead-to-Close Pipeline:

1. 1. lead_gen → find prospects in target industry
2. INLINECODE26 → understand their pain points
3. INLINECODE27 → personalized outreach sequence
4. INLINECODE28 → ready proposal when they respond

Content Engine:

1. 1. market_research → trending topics in your niche
2. INLINECODE30 → long-form SEO blog post
3. INLINECODE31 → tweets, LinkedIn, newsletter from that post
4. INLINECODE32 → platform-native posts with CTAs
5. INLINECODE33 → paid promotion copy

Client Onboarding:

1. 1. doc_extract → pull data from client documents
2. INLINECODE35 → structure into your system format
3. INLINECODE36 → set up financial tracking
4. INLINECODE37 → create CRM records

API Details

• - Base URL: INLINECODE38
• Universal Endpoint: INLINECODE39
• Agent List: INLINECODE40
• Health Check: INLINECODE41
• Docs: INLINECODE42
• LLM Providers: OpenAI (GPT-4o), Anthropic (Claude), Google (Gemini), xAI (Grok)
• QA: Every output passes through QA verification before returning

Environment Variables

Variable	Required	Default	Description
INLINECODE43	Yes	INLINECODE44	API base URL
INLINECODE45

No | (none) | Optional API key for authenticated access |

Important Notes

• - Each agent call takes 3-15 seconds (real LLM inference, not cached)
• All outputs include QA verification status
• The provider field is optional in all agent inputs — omit to use the server default
• Management agents (contextmanager, qamanager, etc.) are internal and run automatically during pipelines
• Batch mode processes tasks sequentially to respect rate limits
• All agent outputs are structured JSON with consistent schema