AI Pipelines
17 built-in AI pipelines for lead generation, client delivery, and agency operations.
AI Pipelines
GridWork HQ includes 17 AI pipelines that automate agency workflows end-to-end. Each pipeline is a Markdown definition file that the pipeline server reads at runtime — no code changes are needed to add or modify pipelines.
How Pipelines Work
- You trigger a pipeline from Mission Control, the dashboard API, or a cron schedule
- The pipeline server reads the pipeline definition from the knowledge vault (
system/rules/pipelines/) - It spawns a Claude Code CLI process with the pipeline instructions as the system prompt
- Claude executes the steps: reading files, calling tools, generating output
- Results stream back to the dashboard via SSE and are saved to the
.output/directory
Pipeline Categories
Lead Generation
| Pipeline | Trigger | Description |
|---|---|---|
| Prospect | prospect [type] in [area] | Find and score local business leads |
| Outreach | outreach [business] | Draft personalized outreach emails |
| Audit | audit [business] | Free external site audit for prospects |
Client Delivery
| Pipeline | Trigger | Description |
|---|---|---|
| Propose | propose [business] | Generate proposals from completed briefs |
| Spec | spec [client] | Requirements, design, and task breakdown |
| Plan | plan [business] | Create detailed site build plans |
| Build | build [business] | Execute build plans across 5 phases |
| Brand | brand [business] | Generate full brand identity systems |
| SEO | seo [business] | Post-launch SEO analysis and optimization |
| Content | content [business] | Generate a month of blog posts, social, and email content |
| Report | report [business] | Monthly maintenance reports for retainer clients |
| Follow-Up | follow-up [client] | 30-day post-launch check-in with retainer pitch |
Operations
| Pipeline | Trigger | Description |
|---|---|---|
| Internal Audit | internal-audit [site] | Deep 10-category technical QA |
| KB Librarian | kb-librarian | Knowledge vault audit and maintenance |
| Archive Outputs | archive-outputs | Archive old output files |
| Friday Update | Cron only | Weekly client update emails |
| Scope Audit | Cron only | Detect scope creep against build plans |
Model Routing
Each pipeline specifies its model tier in YAML frontmatter. Multi-pass pipelines use different models per pass:
| Model | Typical Use |
|---|---|
| Haiku | Lightweight maintenance (kb-librarian, archive-outputs) |
| Sonnet | Implementation, drafting, technical analysis |
| Opus | Planning, review gates, high-quality final output |
Multi-Pass Pipelines
Several pipelines use multiple passes with different models. For example, the audit pipeline uses Sonnet for technical analysis (Pass 1) and Opus for sales framing (Pass 2). The spawner runs each pass sequentially, with intermediate results saved to .output/.
Adding Custom Pipelines
See the Advanced Extensions guide for instructions on creating new pipeline definitions.