Agentspecificatieformaat
Tajo-agents worden gedefinieerd in markdown-bestanden. Elk bestand bevat YAML-frontmatter (identiteit, tools, beperkingen) en een markdown-body (instructies, strategie, regels). Dit formaat is geïnspireerd op productiepatronen voor agents uit multi-agent-orkestratiesystemen.
Bestandsstructuur
---name: agent-namedescription: What this agent does (max 160 chars)version: 1.0.0temperature: 0.2max_tokens: 4096tools: - brevo_contacts - brevo_email_campaign_management - brevo_sms_campaignstriggers: - event: cart_abandoned - schedule: "0 */4 * * *"permissions: - contacts:read - email:send - sms:send---
# Agent Name
Instructions for the agent in natural language...Frontmattervelden
Verplichte velden
| Veld | Type | Beschrijving |
|---|---|---|
name | string | Unieke identificatie in kebab-case (bijvoorbeeld cart-recovery-agent) |
description | string | Wat deze agent doet (maximaal 160 tekens) |
version | string | Semantische versie (bijvoorbeeld 1.0.0) |
tools | array | Modules van de Brevo MCP-server waar deze agent bij mag |
Gedragsvelden
| Veld | Type | Standaard | Beschrijving |
|---|---|---|---|
temperature | float | 0.3 | LLM-temperatuur. Lager = voorspelbaarder. Gebruik 0.1 tot 0.2 voor databewerkingen en 0.3 tot 0.5 voor campagne-ontwerp |
max_tokens | integer | 4096 | Maximale lengte van het antwoord per beurt |
model | string | claude-sonnet-4-6 | Het LLM-model dat wordt gebruikt |
Triggervelden
| Veld | Type | Standaard | Beschrijving |
|---|---|---|---|
triggers | array | [] | Events, schema’s of webhooks die deze agent activeren |
triggers[].event | string | - | Naam van het event (bijvoorbeeld cart_abandoned, customer_created) |
triggers[].schedule | string | - | Cron-expressie (bijvoorbeeld 0 9 * * * voor elke dag om 9 uur) |
triggers[].webhook | string | - | Webhookpad (bijvoorbeeld /agents/cart-recovery/trigger) |
triggers[].conditions | array | [] | Filtervoorwaarden voor de trigger |
triggers[].debounce | string | - | Debounce-venster (bijvoorbeeld 5m, 1h) |
Rechtenvelden
| Veld | Type | Standaard | Beschrijving |
|---|---|---|---|
permissions | array | [] | Vereiste rechten voor het audittrail |
related_agents | array | [] | Agent-ID’s waaraan deze agent werk mag delegeren |
escalation | string | - | Waarheen wordt doorverwezen als de agent twijfelt (human, supervisor-agent) |
Tools: koppeling met Brevo MCP-servers
Het veld tools verwijst naar modulenamen van de Brevo MCP-server. Elke module wijst naar een specifiek endpoint op mcp.brevo.com:
tools: # Contacts & Segmentation - brevo_contacts # /v1/brevo_contacts/mcp - brevo_lists # /v1/brevo_lists/mcp - brevo_segments # /v1/brevo_segments/mcp - brevo_attributes # /v1/brevo_attributes/mcp
# Campaigns & Messaging - brevo_email_campaign_management # /v1/brevo_email_campaign_management/mcp - brevo_templates # /v1/brevo_templates/mcp - brevo_sms_campaigns # /v1/brevo_sms_campaigns/mcp - brevo_whatsapp_campaigns # /v1/brevo_whatsapp_campaigns/mcp
# Analytics - brevo_campaign_analytics # /v1/brevo_campaign_analytics/mcp
# Sales CRM - brevo_deals # /v1/brevo_deals/mcp - brevo_companies # /v1/brevo_companies/mcp - brevo_tasks # /v1/brevo_tasks/mcp - brevo_pipelines # /v1/brevo_pipelines/mcp - brevo_notes # /v1/brevo_notes/mcpTip
Geef je agent zo min mogelijk tools. Minder tools = beter redeneren door de AI en snellere antwoorden. Bekijk Brevo MCP-server voor alle beschikbare modules.
Triggers
Eventtriggers
Activeer de agent zodra er iets gebeurt in je systeem:
triggers: - event: cart_abandoned conditions: - cart_value: "> 50" - items_count: ">= 1" - time_since_activity: "> 30m" debounce: 5mSchematriggers
Laat de agent op een vast schema draaien:
triggers: - schedule: "0 9 * * MON" # Every Monday at 9am timezone: "America/New_York" - schedule: "0 */4 * * *" # Every 4 hours - schedule: "0 0 1 * *" # First day of each monthWebhooktriggers
Roep de agent aan via HTTP:
triggers: - webhook: /agents/win-back/trigger method: POST authentication: api_keyMarkdown-body: instructies
De body van de agentspecificatie bestaat uit instructies in natuurlijke taal. Schrijf hem alsof je een ervaren marketeer briefing geeft:
Structuur
# Agent Name
Context paragraph, what this agent does and why.
## Strategy
Step-by-step approach the agent should follow.
## Decision Framework
Rules for making choices (e.g., which channel to use based on cart value).
## Rules
Hard constraints, things the agent must ALWAYS or NEVER do.
## Templates
References to Brevo template IDs, SMS copy, WhatsApp templates.
## Metrics
Events to track for measuring success.Effectieve instructies schrijven
Wees specifiek over de strategie, niet alleen over het doel:
## BadRe-engage churned customers.
## GoodWhen a customer hasn't purchased in 90+ days:1. Check their last 3 orders for product category preferences2. Create a personalized discount based on AOV (10% if AOV > $100, 15% if < $100)3. Send email with subject line referencing their preferred category4. Wait 72 hours, if no open, send SMS with discount code5. Wait 7 days, if no purchase, mark as deep-churn and stop sequenceLeg de grenzen expliciet vast:
## Rules- NEVER send more than 3 messages per sequence- NEVER contact customers who unsubscribed- ALWAYS check if the customer converted before sending the next step- ALWAYS respect quiet hours (no SMS 9pm-9am local time)- If unsure about a decision, escalate to human reviewKetens van meerdere agents
Zet voor complexe workflows meerdere agents achter elkaar in een keten. Elke agent doet één fase en geeft de context door aan de volgende:
name: quarterly-retention-campaignsteps: - agent: customer-intelligence input: | Analyze customer segments for Q2 retention campaign. Goal: {task}
Identify: 1. At-risk customers (declining purchase frequency) 2. VIP customers (top 10% by LTV) 3. Win-back candidates (90+ days since last order)
- agent: campaign-designer input: | Design retention campaigns for these segments: {previous}
Create differentiated approaches per segment: - At-risk: gentle nudge with product recommendations - VIP: exclusive early access or loyalty reward - Win-back: aggressive discount with urgency
- agent: campaign-executor input: | Execute these campaigns via Brevo: {previous}
Use appropriate channels per segment preference. Set up A/B tests for subject lines. Schedule sends for optimal times.
- agent: campaign-reporter input: | Generate the retention campaign launch report: {previous}
Include: segments targeted, campaigns created, expected reach, A/B test configurations.Ketenvariabelen
| Variabele | Beschrijving |
|---|---|
{task} | Het oorspronkelijke doel of verzoek |
{previous} | De output van de vorige stap |
{step_N} | De output van stap N (telt vanaf 0) |
{artifacts_dir} | De map voor bestandsoutput |
Kant-en-klare agentspecificaties
Campaign Orchestrator
---name: campaign-orchestratordescription: Design and execute multi-channel campaigns from natural language promptsversion: 2.0.0temperature: 0.3tools: - brevo_contacts - brevo_segments - brevo_email_campaign_management - brevo_templates - brevo_sms_campaigns - brevo_whatsapp_campaigns - brevo_campaign_analyticstriggers: - webhook: /agents/campaign/trigger method: POST---
# Campaign Orchestrator
You are a multi-channel marketing campaign specialist.Given a campaign brief, you design, build, and launchcampaigns across email, SMS, and WhatsApp via Brevo.
## Process1. Parse the campaign brief (audience, message, goal, timeline)2. Create or identify the target segment in Brevo3. Select the best channel(s) based on audience preference data4. Build campaign content using existing templates or creating new ones5. Configure send schedule and A/B tests6. Launch and report initial delivery metrics
## Channel Selection- Email: default for all campaigns- SMS: add for time-sensitive offers or cart recovery- WhatsApp: add for conversational campaigns or high-value segments
## Rules- ALWAYS preview campaigns before sending- NEVER send to unsubscribed contacts- ALWAYS set up tracking for campaign attribution- Maximum 2 A/B test variants per campaignCustomer Intelligence Agent
---name: customer-intelligencedescription: Autonomous segmentation, RFM scoring, and churn predictionversion: 1.5.0temperature: 0.2tools: - brevo_contacts - brevo_segments - brevo_attributes - brevo_lists - brevo_campaign_analyticstriggers: - schedule: "0 6 * * MON" timezone: "UTC"---
# Customer Intelligence Agent
You analyze customer data in Brevo to generate actionablesegments and insights for marketing teams.
## Weekly Analysis1. Pull contact activity data from campaign analytics2. Calculate RFM scores (Recency, Frequency, Monetary)3. Identify segment shifts (customers moving between tiers)4. Flag churn risks (declining engagement over 4+ weeks)5. Generate segment recommendations for upcoming campaigns
## Segment Definitions- Champions: R=5, F=5, M=5, recent, frequent, high-value- Loyal: R>=3, F>=4, M>=3, consistent buyers- At Risk: R<=2, F>=3, M>=3, were loyal, now fading- Hibernating: R=1, F>=2, M>=2, long gone, were once active- New: first purchase in last 30 days
## OutputProduce a markdown report with:- Segment sizes and week-over-week changes- Top 10 at-risk customers by LTV- Recommended actions per segment- Suggested campaign themes for the weekUitrollen
Een agent programmatisch draaien
import { TajoAgent } from "@tajo/agent-sdk";
const agent = new TajoAgent({ specPath: "./agents/cart-recovery-agent.md", brevoToken: process.env.BREVO_MCP_TOKEN, model: "claude-sonnet-4-6", // Only connect the MCP servers listed in the agent's tools field autoConnectServers: true,});
const result = await agent.run( "Recover abandoned carts over $50 from the last 4 hours");
console.log(result.summary);console.log(result.toolCalls); // Full audit trailconsole.log(result.metrics); // Events trackedDraaien via Claude Code
# Point to your agent spec and let Claude execute itclaude "Run the agent defined in ./agents/cart-recovery-agent.md for today's abandoned carts"Inplannen met cron
# Run the customer intelligence agent every Monday at 6am0 6 * * MON claude --print "Run ./agents/customer-intelligence.md weekly analysis" >> /var/log/tajo-agents.log 2>&1Volgende stappen
- Brevo MCP-server, beschikbare tools en serverconfiguratie
- Je eerste agent bouwen, praktische tutorial
- Skills-referentie, Tajo Skills die samenwerken met agents
- Overzicht van de MCP-architectuur, hoe alles samenhangt