Showcase

Meet the agents we have already built.

Most AI agency websites show concept slides. We show production agents, three of them, with names, full specs, eval suites, and integration details. These are the same agents we customize and deploy in client engagements. Names changed to protect client data; mechanics are real. For the full catalogue of 14 agent types we build across the three organisational levels, see AI across three organisational levels.

Four small matte-ceramic AI agent figures: the Executive-tier agent holding a bar-chart sculpture, Nova (sales) holding a medallion, Orion (support) wearing a headset, and Lyra (inbox) holding a pen and papers.
Tier 1 · Executive · coming next Nova · Sales Orion · Support Lyra · Inbox

What are theagency47's showcase agents?

theagency47 maintains three production AI agents as reference deployments: Nova (sales outreach, Operational tier), Orion (customer support, Operational tier), and Lyra (email triage, Task tier). Each runs on the right model for each task, chosen per client, has a full one-page specification, a 20+ case eval suite re-run on every change, real tool integrations (Gmail, Slack, HubSpot, Zendesk), and is live in production. When clients sign Spark or Workforce engagements, we typically use one of these three as the starting template, customizing the system prompt, knowledge base, and integrations to the client's specific business. The agents are showcased here as proof-of-work, not as products you can buy off-the-shelf.

theagency47 · Updated October 2026
The three agents

One agent at each tier. Live in production.

Nova, the AI sales agent: a beige ceramic figure with a headset, holding a medallion.
Operational tier · Sales

NovaAI AGENT

What she does: Researches prospects, drafts personalized cold outreach in your voice, schedules follow-ups, hands hot replies to a human. Eats 8 hours of SDR work per day, surfaces the 30 minutes of human judgment that still matters.

  • Runs on Workers AI in your own Cloudflare account
  • Integrations: Gmail + HubSpot + Apollo
  • Eval: 93% on our internal eval (how we test)
  • Throughput: 50–100 personalized emails/day
Autonomy
Acts with approval
Eval
93% on our internal eval (how we test)
Cost
€30–€150 per month in model usage at typical volume
Connects
Gmail, Outlook, HubSpot
See Nova's full spec
Orion, the AI support agent: a grey ceramic figure with a headset, gesturing as if explaining.
Operational tier · Support

OrionAI AGENT

What he does: Reads inbound support tickets, resolves tier-1 questions (order status, account access, basic troubleshooting) autonomously, escalates the rest with full context, maintains the FAQ knowledge base from new patterns he sees.

  • Runs on Workers AI in your own Cloudflare account
  • Integrations: Zendesk + Slack + product DB
  • Resolves routine tier-1 tickets autonomously
Autonomy
Acts on its own
Eval
Suite re-run on every change
Price
€0.05–€0.15 per resolution, €50–€300/month, +€500 per language
Connects
Zendesk, Intercom, Gorgias
See Orion's full spec
Lyra, the AI inbox agent: a charcoal ceramic figure holding a pen and papers.
Task tier · Inbox

LyraAI AGENT

What she does: Watches your inbox in the background. Categorizes mail by urgency and topic, drafts replies to common patterns (intro requests, scheduling, vendor questions), surfaces only what actually needs you. Reclaims 60–90 minutes per day (typical estimate).

  • Fast, low-cost models
  • Integrations: Gmail + Cal.com + Notion
  • Eval: 97% on our internal eval, incl. phishing and prompt-injection cases (how we test)
  • Daily volume: 100–300 emails processed
Autonomy
Acts with approval
Eval
97% on our internal eval (how we test)
Cost
~€0.002–€0.007 per email
Connects
Gmail, Outlook, Google Calendar
See Lyra's full spec
The full catalogue

Every AI agent we build, by the outcome you need.

Nova, Orion, and Lyra are the three we show in full. They are not the only three we build. Here is the complete catalogue of AI agents and automations we deploy for clients, grouped by what each one does for the business. Every one runs on a mix of LLMs matched to the task, is wired into your tools, and ships with an eval suite.

01 · Find customers · 6 agents

Agents that bring in and qualify new business.

Sales · Operational tier

Sales Outreach Agent

Researches prospects, writes personalised outreach in your voice, sequences follow-ups, and books meetings. Built for B2B teams with a defined ICP. Nova is the live showcase.

Autonomy
Acts with approval
Eval
93% on our internal eval (how we test)
Cost
€30–€150 per month in model usage at typical volume
Connects
Gmail, Outlook, HubSpot
See the full spec
Sales · Operational tier

Lead Generation Agent

Builds target lists from your ICP, enriches them with firmographic and contact data, and runs first-touch personalised outreach, from scraping to send.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Apollo, HubSpot, Salesforce
How it works
Voice · Operational tier

Voice Agent (EL / EN)

Handles inbound and outbound calls in natural Greek or English (appointment confirmations, lead qualification, customer-feedback calls) with hand-off to a human when needed.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Twilio, Your phone system (SIP), Google Calendar
How it works
Sales / Ops · Operational tier

CRM Automation Agent

Enriches records, scores leads, logs activity, and drafts the next follow-up so your pipeline never goes stale between touches.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
HubSpot, Salesforce, Pipedrive
How it works
Marketing · Operational tier

Content Production Agent

Takes a brief to a publish-ready draft (blog posts, social, newsletters) in your brand voice, with internal-link discipline and SEO structure.

Autonomy
Suggests
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
WordPress, Webflow, Notion
How it works
Marketing · Operational tier

SEO Automation Agent

Keyword research, content briefs, and content-gap analysis that feed your editorial calendar, the research layer behind a content engine.

Autonomy
Suggests
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Google Search Console, Ahrefs, Semrush
How it works
02 · Serve customers · 4 agents

Agents that answer, book and resolve, around the clock.

Support · Operational tier

Customer Support Agent

Resolves tier-1 tickets across chat, email, and WhatsApp from your knowledge base, resolving routine ones autonomously and escalating the rest with full context. Orion is the live showcase.

Autonomy
Acts on its own
Eval
Suite re-run on every change
Price
€0.05–€0.15 per resolution, €50–€300/month, +€500 per language
Connects
Zendesk, Intercom, Gorgias
See the full spec
Voice · Operational tier

Call Answering Agent

Answers your phone line around the clock, handles routine questions, captures details, and transfers live to a human with the full conversation as context.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Twilio, Your phone system (SIP), WhatsApp
How it works
Operations · Operational tier

Appointment Booking Agent

Books, reschedules, and confirms appointments over chat, email, or call, synced to your calendar, with reminders and no double-bookings.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Cal.com, Google Calendar, Microsoft Calendar
How it works
Web · Task tier

Website / WhatsApp Chatbot

A site or WhatsApp chatbot grounded in your knowledge base, answering in Greek and English, with a clean handoff to a human when it hits its limits.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Website widget, WhatsApp Business, Messenger
How it works
03 · Run the company · 8 agents

Agents that clear the inbox, the paperwork and the reporting.

Inbox · Task tier

Email Triage Agent

Categorises your inbox by urgency and topic, drafts replies to common patterns, and surfaces only what needs you. Lyra is the live showcase.

Autonomy
Acts with approval
Eval
97% on our internal eval (how we test)
Cost
~€0.002–€0.007 per email
Connects
Gmail, Outlook, Google Calendar
See the full spec
Inbox · Task tier

Email Automation Agent

Drafts, sends, and follows up on transactional and outreach email from templates and triggers, the sending layer behind a workflow.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Gmail, Outlook, HubSpot
How it works
Documents · Task tier

Document Processing Agent

OCR, extraction, and classification of invoices, contracts, and forms into structured records your systems can use.

Autonomy
Acts with approval
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Email inbox, Google Drive, SharePoint
How it works
Knowledge · Task tier

Knowledge Base Agent

Builds and maintains a searchable knowledge base for your team or customers from the documents you already have, and keeps it current.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Google Drive, SharePoint, Notion
How it works
Integration · Task tier

Workflow Automation

Connects your tools (n8n, Make, Zapier, or custom) so no one copies data between systems by hand again. Usually the fastest ROI of the set.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
n8n, Make, Zapier
How it works
Reporting · Executive tier

Reporting Agent

Turns raw data from your tools into a clean executive summary on the schedule you set (daily, weekly, or month-end) ready to forward.

Autonomy
Acts on its own
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
HubSpot, GA4, Stripe
How it works
Analytics · Executive tier

Data Analysis Agent

Answers ad-hoc questions over your own data in plain language. No SQL, no waiting on an analyst, ask, get the chart and the takeaway.

Autonomy
Suggests
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
BigQuery, Postgres, GA4
How it works
Assistant · Executive tier

Business Assistant

A role-specific assistant trained on one person's processes, documents, and decisions, a force-multiplier for a founder, partner, or department head.

Autonomy
Suggests
Eval
Must pass 90%+ of our internal eval before go-live (how we test)
Connects
Google Workspace, Microsoft 365, Notion
How it works
+ · Foundations · 3 agents

The groundwork that makes the rest stick.

Enablement

ChatGPT / Claude for Business

Workflows, a prompt library, and team training so your people use frontier models safely and effectively in their day-to-day.

How it works
Build

Custom AI Tools

Purpose-built tools for when off-the-shelf doesn't fit the workflow, scoped, built, and owned by you.

How it works
Delivery

AI Implementation

End-to-end delivery from proof-of-concept to production, evals, integrations, monitoring, and the handover docs to run it.

How it works
What every build includes

No matter which agent, you get the same foundation.

  • The agent scoped to one clear use case (sales, support, ops, or task)
  • Your knowledge base wired in (RAG), answers come from your data, not guesses
  • Integrations with your CRM, helpdesk, email, or phone system
  • Greek and English where the workflow needs it
  • Human escalation with full context, never a dead end
  • A metrics dashboard: volume, resolution rate, time saved
  • A 20+ case eval suite, so you see the pass rate before go-live
  • Documentation and a monthly tuning review
Describe the agent you need
How showcase agents work

How showcased agents map to engagements.

The three showcase agents are reference deployments that demonstrate the shape of work we do. When you sign an engagement, we use the relevant showcase as a starting template and customize it to your business. Specifically:

  • Spark engagements typically start from one of Nova, Orion, or Lyra. The agent is rebuilt for your data, integrations, and voice. Same shape, different brain.
  • Workforce Starter engagements combine one operational agent (Nova or Orion), one executive-tier agent (custom built for you), and Lyra (or her equivalent), covering all three organizational tiers.
  • Workforce Pro engagements typically expand the showcase trio with two additional agents specific to your department (e.g., Renewal Drafter for customer success, Account Health Analyst, etc.).

If you want to see what a custom version of Nova/Orion/Lyra would look like for your business, that is exactly what the discovery call is for, or you can describe the agent you have in mind in plain language and we'll send back a structured brief. For the broader catalogue of 14 named agent types we build across the three tiers, see AI across three organisational levels. In a whole-company setup, your team sees and approves every department agent's work in OS47.

Why three agents specifically

One agent per organizational tier.

Each showcase agent is deliberately positioned at one of the three tiers of our workforce framework, so you experience all three when reviewing the work.

Tier 1, Executive (not yet showcased)

Decision-support agents that read your data and produce briefings. We build these case-by-case during engagements because they are too client-specific to template (your "executive brief" is not the same as anyone else's). Examples we have built privately: weekly competitive-intel digest, pipeline health analyst.

Tier 2, Operational (Nova + Orion)

Departmental-flow agents. Nova handles sales outreach, Orion handles tier-1 customer support. Both are productizable enough to template, customizable enough to be useful per business.

Tier 3, Task (Lyra)

Lyra handles email triage, the work no team actually wants to own. Task agents are the highest-volume, lowest-customization tier; the same agent template fits many businesses with minor tuning.

Next: See engagement tiers →

Free · 30 minutes · No deck, no pitch

Find the 3 processes eating most of your team's hours.

In a 30-minute discovery call we map how your team's week actually goes, name the three processes that cost the most hours, and tell you honestly whether an AI agent is the right fix. If it isn't, we'll say so.

Book a free discovery call →Or get the €297 AI Audit

We reply within one business day with a calendar link. Want it in writing? The AI Audit adds a written report with ROI projections, and the €297 is credited in full if you start a project within 30 days.

Prefer to write it down? Describe your agent in 2 minutes →

Part of