Skip to content

Agent Overview

Moe’s provides pre-built agent templates that you can deploy out of the box. Each agent is specialized for a specific job and designed to work with other agents through A2A pipelines.

AgentWhat It DoesBest For
ResearchWeb research, competitive analysis, market intelligenceDue diligence, market reports, fact-checking
SupportEmail triage, ticket routing, customer repliesCustomer support, helpdesk, intake
ContentWebsite copy, blog drafts, content updatesMarketing, documentation, corrections
QAVisual verification, deployment checks, testingRelease validation, monitoring
CustomWhatever you needSpecialized workflows

Every agent is defined by a small set of files in its workspace:

The agent’s personality and operating instructions. What it does, how it responds, what format it uses for output. Think of it as the agent’s job description.

Technical configuration. Which tools it can access, how it communicates, where it stores its memory.

Installable capabilities that give the agent specific abilities. A research agent might have a “deep-research-pro” skill that teaches it multi-step research methodology. A QA agent might have a “browser-screenshot” skill.

Each agent maintains its own working memory in memory/YYYY-MM-DD.md files. This lets agents reference past work and build context over time.

Different agents benefit from different AI models. Not every task needs the most powerful (and expensive) model.

AgentRecommended ModelWhy
ResearchClaude Sonnet / Gemini ProGood balance of quality and cost for web research
SupportClaude SonnetNeeds good judgment for customer interactions
ContentClaude SonnetWriting quality matters
QAGemini Flash / Claude HaikuSimple verification tasks, speed over depth
Custom (coding)Claude Opus / SonnetComplex reasoning for code generation

You can configure the model per-agent in your gateway config. Start with the recommended defaults and adjust based on output quality and cost.

For production deployments with many agents running frequently:

  • Use cheaper models for high-volume, low-complexity tasks (QA checks, simple routing)
  • Reserve premium models for tasks where quality directly impacts customers (support replies, content writing)
  • Monitor token usage per agent and adjust as you learn which tasks actually need more reasoning power
  1. Choose a template (or start from scratch)
  2. Customize the SOUL.md for your specific use case
  3. Add any skills the agent needs
  4. Connect it to a Telegram bot
  5. Add it to your monitoring group
  6. Test with a simple task

See Quick Start for step-by-step instructions.