Work channels
Telegram and scheduled routines
AI Operations for ShenQi
An AI system built into ShenQi’s daily work.
The internal system brings company knowledge, product analytics, current work and recurring routines together. It prepares operating briefs, supports weekly review and helps the team carry approved changes into the product.
My roleArchitecture and end-to-end implementationTodayWorking internal systemOne systemKnowledge, analytics, work, Telegram and ShenQi
The task
Bring together operating context that lived across separate services.
Product performance, search data, content, email activity, documents and current work lived in different tools. Regular reviews required manual assembly. AI Operations connects those sources and prepares a result in the channels where the team already works.
Sources
Google Drive holds the canonical knowledge base. Analytics and work systems add current performance and active work.
Google DriveDocuments and company knowledgeGA4Product behaviour and performanceSearch ConsoleSearch performance and visibilityYouTubeContent performanceSendPulseEmail campaigns and activityLinearCurrent work and projects
How the work moves
The system gathers context, prepares a result and delivers it to the team.
Orchestration
Hermes Agent, memory, routing and recurring tasks
Sources
Documents, analytics, search, content, email and Linear
ShenQi connection
Explicit capabilities for products, courses, content and pages
Product
Approved changes are applied in ShenQi
Recurring work
Workflows built into the team’s operating rhythm.
Each morning the system gathers current performance, active work and notable product changes. The finished brief arrives in Telegram.
The system shows what changed during the week, where results diverged and which questions need the team’s decision.
Company knowledge and source data support drafts, analysis and working materials.
The team receives a prepared change, reviews it and applies it to ShenQi after approval.
Working with the product
Access follows the job at hand.
The system works through explicit product capabilities instead of unrestricted access to internal application surfaces. Each workflow defines which context it can read and which change it may prepare.
The system gathers permitted context and prepares findings independently.
A result is presented before anything changes in the product.
Consequential changes run after the team has reviewed them.
Completed actions are retained and can be reviewed later.
What I built
From source systems to a working product connection.
- Configured Hermes Agent, schedules, memory and Telegram delivery.
- Connected Google Drive, GA4, Search Console, YouTube, SendPulse and Linear.
- Built a dedicated integration layer between the agent and the ShenQi backend.
- Defined access to products, courses, content, pages and other ShenQi resources.
- Added change approval, safe retries and execution history.
- Established a model for tasks, revisions, review and agent handoffs.
Technology
Hermes Agent · MCP · Rust · Laravel/PHP · Google APIs · Linear · SendPulse · Telegram Bot API · PostgreSQL · Redis
Still assembling an important workflow by hand?
We can start by mapping the process and building one bounded workflow that gives the team a useful result without rebuilding everything around it.