The Second Project: Running an AI Agent for Real Users

---

Your team built an agent, and it works. The demo was convincing; the pilot went well. Then someone asked the operating questions: who signs in, who pays for each conversation, where do the files go, what happens when two hundred people use it at once, and how do we ship next month's version without breaking this one?

That is the second project. It is larger than the first, it is invisible on the original plan, and it has nothing to do with how clever the agent is.

01 What the second project actually contains

• Identity and access. Real users sign in; colleagues share the workspace without seeing each other's conversations, files, or budgets; outside automations get their own revocable keys instead of borrowing a person's.
• Money. Every paid step — a model call, a search, a report — is approved against a budget before it runs and attributed to a person after. Finance can answer "who spent this?" without an investigation.
• Company accounts. The agent works your mail and chat through accounts each user explicitly connected, with permissions they chose and can revoke — never through one all-powerful company token.
• Code the agent writes. Useful agents write code. That code runs in a confined workspace with nothing extra inside — an approval stands between it and anything real.
• Evidence. Every action leaves a record: who, on whose authority, what it cost, what it produced. Audits become lookups.
• Shipping. New versions deploy without a rebuild of the product around them; one deployment serves many apps and many users concurrently.

Each line above is months of engineering when built in-house — and all of it is undifferentiated: your users chose you for the first project, never the second.

02 The part your team keeps

The agent your team built stays. The framework it uses — LangGraph, CrewAI, the Claude Agent SDK, or your own code — stays. The product's interface and business services stay. The runtime surrounds that work with the operating layer, and adoption starts at a single seam: host the existing agent behind one interface, or move one risky capability into confined execution, and stop there if that is all you need this quarter.

That gradual shape is what de-risks the decision. There is no migration cliff, no rewrite, and each step pays for itself before the next one starts.

03 What it means for the business

• Time to market. The second project comes off the roadmap; the team ships product features instead of plumbing.
• Predictable spend. Budgets are enforced before actions run and attributed per person — the cost surprise is structurally impossible.
• Audit readiness. The records exist as a by-product of operation, in the shape auditors ask for.
• No lock-in. KDCube is self-hosted and open source, MIT licensed. It runs on your infrastructure; your data, credentials, and records never leave it. What you hold if you ever leave is: everything.

· Read the full story

This brief is the executive layer of a deeper piece — the architecture, the adoption paths, and what the runtime enforces at each boundary: