2026: AI employees and MCP connectors

Today the work is AI employees, systems that hold a real job inside a business, deployed where the business already lives: WhatsApp, Gmail, the phone, and the AI tools a team already uses. 20 repositories by the end of August, 11 of them private.¹

What happened

• AI employees. A task-execution employee and a manager agent that works a Gmail inbox (reads mail, answers questions, produces research and reports) in January; a backend-developer employee that writes and ships backend code the same month; WhatsApp-based employees in February and March, one of them a WhatsApp assistant that builds custom AI agents, with container isolation and agent swarms.²
• Cold-outreach automation. An agent pipeline that runs cold email campaigns, in February.
• A voice agent. Real-time, phone-style conversation on the OpenAI Realtime API, in March.
• Self-hosted infrastructure. A Honcho memory server on Hugging Face Spaces backed by Postgres, in May.
• A marketing connector. A remote MCP server for marketing work, with the procedures and the orchestration logic it follows, in June.
• Agency systems. Four systems built for the agency, all private and not described here.

The MCP connectors

An MCP connector is a remote server that ChatGPT, Claude, Codex or Claude Code can attach to. Each one packages a company's process and rules, so any AI that connects behaves like a trained employee of that company. The connectors built for the agency in 2026 are the agency's own: this record does not name them, count them, or describe what they do. What a connector is, and what one refuses, is explained with an invented example on what I build.

The Forward Deployed work

From July 2026 the job is Forward Deployed Engineering: AI staff placed inside a business's own delivery, with a person at the approval gate. Which business, what runs there, and how it is built are deliberately outside this record.

The public repositories

Private work

Eleven private repositories: a family of AI-employee builds (a task-execution employee, a manager agent on Gmail, a backend-developer employee, two WhatsApp-based employees), a cold-outreach automation, a co-founder experiment, and four systems built for a marketing agency.¹ They are counted here and never named or described.

The pattern behind all of them

The server enforces the process. These systems do not rely on the AI behaving. The pipeline rejects skipped steps, unverified claims and invented facts, which is what makes them safe to hand to a business.²

What this era is teaching

Real deployment is 20% model and 80% process, integration and accountability. That is the actual job of a Forward Deployed Engineer.²

Back to the journey overview, or on to the journey in numbers.

Footnotes

1. GitHub API, repositories owned by rrizwan98, read 26 August 2026: 20 repositories created between 1 January and 26 August 2026 (9 public, 11 private). ↩ ↩²

2. From Predictive AI to Forward Deployed Engineer: My 6-Year Journey, Raza Rizwan, July 2026. ↩ ↩² ↩³