Zatražite rani pristup

Unesite ime i imejl adresu ili broj telefona. Poslaćemo vam detalje o pristupu platformi Tajo.

Format specifikacije agenta

Tajo agenti se definišu u markdown datotekama. Svaka datoteka sadrži YAML frontmatter (identitet, alati, ograničenja) i markdown telo (uputstva, strategija, pravila). Ovaj format je inspirisan produkcijskim obrascima agenata koji se koriste u sistemima za orkestraciju više agenata.

Struktura datoteke

---
name: agent-name
description: What this agent does (max 160 chars)
version: 1.0.0
temperature: 0.2
max_tokens: 4096
tools:
- brevo_contacts
- brevo_email_campaign_management
- brevo_sms_campaigns
triggers:
- 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

PoljeTipOpis
namestringJedinstveni identifikator u kebab-case formatu (npr. cart-recovery-agent)
descriptionstringŠta ovaj agent radi (najviše 160 znakova)
versionstringSemantička verzija (npr. 1.0.0)
toolsarrayModuli Brevo MCP servera kojima ovaj agent može da pristupi

Polja ponašanja

PoljeTipPodrazumevanoOpis
temperaturefloat0.3Temperatura LLM-a. Niže = determinističkije. Koristite 0.1-0.2 za operacije nad podacima, 0.3-0.5 za osmišljavanje kampanja
max_tokensinteger4096Najveća dužina odgovora po jednom koraku
modelstringclaude-sonnet-4-6LLM model koji se koristi

Polja okidača

PoljeTipPodrazumevanoOpis
triggersarray[]Događaji, rasporedi ili webhook-ovi koji aktiviraju ovog agenta
triggers[].eventstring-Naziv događaja (npr. cart_abandoned, customer_created)
triggers[].schedulestring-Cron izraz (npr. 0 9 * * * za svaki dan u 9h)
triggers[].webhookstring-Putanja webhook-a (npr. /agents/cart-recovery/trigger)
triggers[].conditionsarray[]Uslovi filtriranja za okidač
triggers[].debouncestring-Prozor za odbijanje ponovljenih poziva (npr. 5m, 1h)

Polja dozvola

PoljeTipPodrazumevanoOpis
permissionsarray[]Obavezni opsezi dozvola za revizorski trag
related_agentsarray[]ID-jevi agenata kojima ovaj agent može da delegira posao
escalationstring-Kome se prosleđuje kada agent nije siguran (human, supervisor-agent)

Alati: mapiranje na Brevo MCP servere

Polje tools upućuje na nazive modula Brevo MCP servera. Svaki modul se mapira na određenu krajnju tačku 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/mcp

Tip

Koristite najmanji skup alata koji je vašem agentu potreban. Manje alata = bolje zaključivanje AI-ja i brži odgovori. Pogledajte Brevo MCP server za sve dostupne module.

Okidači

Okidači po događaju

Aktivirajte agenta kada se nešto dogodi u vašem sistemu:

triggers:
- event: cart_abandoned
conditions:
- cart_value: "> 50"
- items_count: ">= 1"
- time_since_activity: "> 30m"
debounce: 5m

Okidači po rasporedu

Pokrećite agenta po 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 month

Okidači preko webhook-a

Pozovite agenta putem HTTP-a:

triggers:
- webhook: /agents/win-back/trigger
method: POST
authentication: api_key

Markdown telo: uputstva

Telo specifikacije agenta čine uputstva na prirodnom jeziku. Napišite ih kao da dajete zadatak iskusnom marketaru:

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 efikasnih uputstava

Budite konkretni u vezi sa strategijom, ne samo sa ciljevima:

## Bad
Re-engage churned customers.
## Good
When a customer hasn't purchased in 90+ days:
1. Check their last 3 orders for product category preferences
2. Create a personalized discount based on AOV (10% if AOV > $100, 15% if < $100)
3. Send email with subject line referencing their preferred category
4. Wait 72 hours, if no open, send SMS with discount code
5. Wait 7 days, if no purchase, mark as deep-churn and stop sequence

Izričito definišite 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 review

Lanci sa više agenata

Za složene tokove rada povežite više agenata u lanac. Svaki agent obrađuje jednu fazu i prosleđuje kontekst sledećem:

chain.yaml
name: quarterly-retention-campaign
steps:
- 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.

Promenljive u lancu

PromenljivaOpis
{task}Prvobitni cilj ili zahtev
{previous}Rezultat prethodnog koraka
{step_N}Rezultat koraka N (numeracija počinje od 0)
{artifacts_dir}Direktorijum za izlazne datoteke

Unapred pripremljene specifikacije agenata

Campaign Orchestrator

---
name: campaign-orchestrator
description: Design and execute multi-channel campaigns from natural language prompts
version: 2.0.0
temperature: 0.3
tools:
- brevo_contacts
- brevo_segments
- brevo_email_campaign_management
- brevo_templates
- brevo_sms_campaigns
- brevo_whatsapp_campaigns
- brevo_campaign_analytics
triggers:
- webhook: /agents/campaign/trigger
method: POST
---
# Campaign Orchestrator
You are a multi-channel marketing campaign specialist.
Given a campaign brief, you design, build, and launch
campaigns across email, SMS, and WhatsApp via Brevo.
## Process
1. Parse the campaign brief (audience, message, goal, timeline)
2. Create or identify the target segment in Brevo
3. Select the best channel(s) based on audience preference data
4. Build campaign content using existing templates or creating new ones
5. Configure send schedule and A/B tests
6. 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 campaign

Customer Intelligence Agent

---
name: customer-intelligence
description: Autonomous segmentation, RFM scoring, and churn prediction
version: 1.5.0
temperature: 0.2
tools:
- brevo_contacts
- brevo_segments
- brevo_attributes
- brevo_lists
- brevo_campaign_analytics
triggers:
- schedule: "0 6 * * MON"
timezone: "UTC"
---
# Customer Intelligence Agent
You analyze customer data in Brevo to generate actionable
segments and insights for marketing teams.
## Weekly Analysis
1. Pull contact activity data from campaign analytics
2. 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
## Output
Produce 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 week

Postavljanje u rad

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 trail
console.log(result.metrics); // Events tracked

Pokretanje preko Claude Code-a

Terminal window
# Point to your agent spec and let Claude execute it
claude "Run the agent defined in ./agents/cart-recovery-agent.md for today's abandoned carts"

Zakazivanje pomoću cron-a

Terminal window
# Run the customer intelligence agent every Monday at 6am
0 6 * * MON claude --print "Run ./agents/customer-intelligence.md weekly analysis" >> /var/log/tajo-agents.log 2>&1

Sledeći koraci

Zatražite rani pristup

Unesite ime i imejl adresu ili broj telefona. Poslaćemo vam detalje o pristupu platformi Tajo.

automatsko prepoznavanje
AI asistent

Zdravo! Pitajte me o dokumentaciji.