Behind the Build · July 2026 · 8 min read

Inside a 23-Agent AI System We Built for a Software Agency Client

Running a software agency means juggling five departments at once: sales, finance, engineering, marketing, and client success — often with a team far smaller than the workload demands. One of our clients, a software agency, came to us with exactly that problem. Instead of hiring for every gap or duct-taping together a dozen SaaS subscriptions, we built them a multi-agent operating system: 23 specialized AI agents, each responsible for one job, coordinated by a self-healing orchestration layer that runs on a standard laptop.

This is the architecture end to end — how the agents are organized, how the system recovers from failures automatically, how cost stays controlled, and how we rolled it out in production.

The core design decision: hybrid, not all-cloud

Most multi-agent frameworks assume everything runs in the cloud, or everything runs locally. We split the difference deliberately:

This split matters for two reasons. Cost: local orchestration means no server bills for the parts of the system that don't need heavy compute — SQLite, not a managed database; local Docker, not a cloud sandbox service. Control: the client's code, proposals, and CRM data never leave the machine except as a stateless text prompt to a model — nothing sits in a third party's application layer.

Model routing: two clusters, two jobs

Not every agent needs the same kind of intelligence. Work routes to two model tiers based on what the task actually demands:

Every call through this router is metered in real time against a hard per-session cost ceiling. Cross the budget, execution halts immediately and an alert fires — no runaway bill, ever.

The 23-agent matrix

The agents are organized into five departments, mirroring how the agency itself is structured:

The orchestration layer: a cyclic state machine

Instead of a rigid pipeline, the system runs as a cyclic, checkpointed graph (LangGraph). Several loops are load-bearing to the design:

Built to survive crashes, not just handle success

Rolling it out: one agent at a time

We didn't flip on all 23 agents simultaneously — risk stayed proportional to trust earned. Lead intake and CRM went live first (zero external side effects, immediate pipeline visibility), then sales drafting (always human-reviewed before reaching a client), then the engineering core, then the QA safety net once the coding loop was trusted, then delivery polish, then memory and marketing once there was a real backlog worth indexing. Anything external-facing — scraping or posting under the agency's name — went live last, only after every upstream step had been reviewed by hand for weeks.

What this actually buys the client

Not "AI replaces the team" — a structured, auditable layer between "a lead exists" and "a project ships," where every drafting step is AI-assisted but every consequential action — approving scope, signing off architecture, sending a contract — stays a deliberate human decision. The system drafts everything; a person still owns every send.

Written by Kasa Tech. We build AI automation and custom software for startups and SMEs. About us

Want something like this built for your business?

Get a Free Consultation