Format specifikacije agenta
Tajo agenti definiraju se u markdown datotekama. Svaka datoteka sadrži YAML frontmatter (identitet, alati, ograničenja) i tijelo u markdownu (upute, strategija, pravila). Taj je format nastao po uzoru na produkcijske obrasce agenata koji se koriste u sustavima za orkestraciju više agenata.
Struktura datoteke
---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...Polja u frontmatteru
Obavezna polja
| Polje | Vrsta | Opis |
|---|---|---|
name | string | Jedinstveni identifikator u kebab-caseu (npr. cart-recovery-agent) |
description | string | Što ovaj agent radi (najviše 160 znakova) |
version | string | Semantička verzija (npr. 1.0.0) |
tools | array | Moduli Brevo MCP poslužitelja kojima ovaj agent smije pristupati |
Polja ponašanja
| Polje | Vrsta | Zadano | Opis |
|---|---|---|---|
temperature | float | 0.3 | Temperatura LLM-a. Niže znači determinističnije. Koristite 0.1-0.2 za operacije s podacima, a 0.3-0.5 za osmišljavanje kampanja |
max_tokens | integer | 4096 | Najveća duljina odgovora po potezu |
model | string | claude-sonnet-4-6 | LLM model koji se koristi |
Polja okidača
| Polje | Vrsta | Zadano | Opis |
|---|---|---|---|
triggers | array | [] | Događaji, rasporedi ili webhookovi koji aktiviraju ovog agenta |
triggers[].event | string | - | Naziv događaja (npr. cart_abandoned, customer_created) |
triggers[].schedule | string | - | Cron izraz (npr. 0 9 * * * za svaki dan u 9 sati) |
triggers[].webhook | string | - | Putanja webhooka (npr. /agents/cart-recovery/trigger) |
triggers[].conditions | array | [] | Uvjeti filtriranja za okidač |
triggers[].debounce | string | - | Prozor za sprječavanje ponavljanja (npr. 5m, 1h) |
Polja dopuštenja
| Polje | Vrsta | Zadano | Opis |
|---|---|---|---|
permissions | array | [] | Opsezi dopuštenja potrebni za trag revizije |
related_agents | array | [] | ID-jevi agenata kojima ovaj agent smije delegirati posao |
escalation | string | - | Kamo usmjeriti slučaj kada agent nije siguran (human, supervisor-agent) |
Alati: preslikavanje na Brevo MCP poslužitelje
Polje tools upućuje na nazive modula Brevo MCP poslužitelja. Svaki se modul preslikava na određenu krajnju točku 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
Koristite najmanji skup alata koji vaš agent treba. Manje alata znači bolje zaključivanje AI-ja i brže odgovore. Sve dostupne module pogledajte na stranici Brevo MCP poslužitelj.
Okidači
Okidači događaja
Aktivirajte agenta kada se u vašem sustavu nešto dogodi:
triggers: - event: cart_abandoned conditions: - cart_value: "> 50" - items_count: ">= 1" - time_since_activity: "> 30m" debounce: 5mOkidači rasporeda
Pokrenite agenta prema ponavljajućem rasporedu:
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 monthWebhook okidači
Pozovite agenta putem HTTP-a:
triggers: - webhook: /agents/win-back/trigger method: POST authentication: api_keyTijelo u markdownu: upute
Tijelo specifikacije agenta upute su na prirodnom jeziku. Napišite ih kao da dajete zadatak iskusnom marketinškom stručnjaku:
Struktura
# 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.Pisanje učinkovitih uputa
Budite konkretni u pogledu strategije, ne samo ciljeva:
## 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 sequenceIzričito odredite zaštitne mehanizme:
## 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 reviewLanci s više agenata
Za složene tijekove rada složite više agenata u lanac. Svaki agent obrađuje jednu fazu i prosljeđuje kontekst sljedećemu:
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.Varijable lanca
| Varijabla | Opis |
|---|---|
{task} | Izvorni cilj ili zahtjev |
{previous} | Rezultat prethodnog koraka |
{step_N} | Rezultat koraka N (indeks počinje od 0) |
{artifacts_dir} | Direktorij za izlazne datoteke |
Gotove specifikacije agenata
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 weekImplementacija
Programsko pokretanje 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 trackedPokretanje putem Claude Codea
# 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"Raspoređivanje pomoću crona
# 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>&1Sljedeći koraci
- Brevo MCP poslužitelj, dostupni alati i konfiguracija poslužitelja
- Izrada prvog agenta, praktični vodič
- Referenca vještina, Tajo vještine koje se kombiniraju s agentima
- Pregled MCP arhitekture, kako se sve to uklapa