Formát špecifikácie agenta
Agenti Tajo sú definovaní v markdown súboroch. Každý súbor obsahuje YAML frontmatter (identita, nástroje, obmedzenia) a markdown telo (inštrukcie, stratégia, pravidlá). Tento formát je inšpirovaný produkčnými vzormi agentov používanými v systémoch multi-agent orchestrácie.
Štruktúra súboru
---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...Polia Frontmatter
Povinné polia
| Pole | Typ | Popis |
|---|---|---|
name | string | Jedinečný identifikátor v kebab-case (napr. cart-recovery-agent) |
description | string | Čo tento agent robí (max 160 znakov) |
version | string | Sémantická verzia (napr. 1.0.0) |
tools | array | Moduly Brevo MCP servera, ku ktorým má tento agent prístup |
Behaviorálne polia
| Pole | Typ | Predvolená hodnota | Popis |
|---|---|---|---|
temperature | float | 0.3 | Teplota LLM. Nižšia = deterministickejšia. Použite 0.1-0.2 pre dátové operácie, 0.3-0.5 pre návrh kampaní |
max_tokens | integer | 4096 | Maximálna dĺžka odpovede na jedno kolo |
model | string | claude-sonnet-4-6 | LLM model na použitie |
Polia spúšťačov
| Pole | Typ | Predvolená hodnota | Popis |
|---|---|---|---|
triggers | array | [] | Udalosti, plány alebo webhooky, ktoré aktivujú tohto agenta |
triggers[].event | string | - | Názov udalosti (napr. cart_abandoned, customer_created) |
triggers[].schedule | string | - | Cron výraz (napr. 0 9 * * * pre každý deň o 9:00) |
triggers[].webhook | string | - | Cesta webhooku (napr. /agents/cart-recovery/trigger) |
triggers[].conditions | array | [] | Podmienky filtrovania pre spúšťač |
triggers[].debounce | string | - | Okno debounce (napr. 5m, 1h) |
Polia oprávnení
| Pole | Typ | Predvolená hodnota | Popis |
|---|---|---|---|
permissions | array | [] | Požadované rozsahy oprávnení pre auditný záznam |
related_agents | array | [] | ID agentov, na ktorých môže tento agent delegovať úlohy |
escalation | string | - | Kam smerovať, keď je agent neistý (human, supervisor-agent) |
Nástroje: Mapovanie na Brevo MCP servery
Pole tools odkazuje na názvy modulov Brevo MCP servera. Každý modul mapuje na špecifický endpoint na 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
Používajte minimálnu sadu nástrojov, ktorú Váš agent potrebuje. Menej nástrojov = lepšie uvažovanie AI a rýchlejšie odpovede. Pozrite Brevo MCP Server pre všetky dostupné moduly.
Spúšťače
Spúšťače udalostí
Aktivujte agenta, keď sa niečo stane vo Vašom systéme:
triggers: - event: cart_abandoned conditions: - cart_value: "> 50" - items_count: ">= 1" - time_since_activity: "> 30m" debounce: 5mSpúšťače plánov
Spúšťajte agenta podľa opakujúceho sa plánu:
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 monthSpúšťače webhookov
Vyvolajte agenta cez HTTP:
triggers: - webhook: /agents/win-back/trigger method: POST authentication: api_keyTelo Markdown: Inštrukcie
Telo špecifikácie agenta sú inštrukcie v prirodzenom jazyku. Píšte ich tak, akoby ste zadávali brief skúsenému marketérovi:
Štruktúra
# 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.Písanie efektívnych inštrukcií
Buďte konkrétni ohľadom stratégie, nie len cieľov:
## 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 sequenceExplicitne definujte zábrany:
## 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 reviewMulti-agent reťaze
Pre komplexné pracovné toky skladajte viacerých agentov do reťaze. Každý agent spracuje jednu fázu a odovzdá kontext ďalšiemu:
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.Premenné reťaze
| Premenná | Popis |
|---|---|
{task} | Pôvodný cieľ/požiadavka |
{previous} | Výstup z predchádzajúceho kroku |
{step_N} | Výstup z kroku N (0-indexed) |
{artifacts_dir} | Adresár pre výstupy súborov |
Predpripravené špecifikácie agentov
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 weekNasadenie
Programové spustenie agenta
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 trackedSpustenie cez 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"Plánovanie s 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>&1Ďalšie kroky
- Brevo MCP Server, Dostupné nástroje a konfigurácia servera
- Budovanie prvého agenta, Praktický tutoriál
- Referencia Skills, Tajo Skills, ktoré sa skladajú s agentmi
- Prehľad MCP architektúry, Ako to všetko do seba zapadá