Verify: Pipeline Agents - FY27
**Epic Owner:** TBD (Product Manager - Verify Stage)\
**Engineering Owner:** TBD (Engineering Manager - Pipeline Execution or CI Platform)\
**FY27 Company Objective:** AI Modernization Journey\
**FY27 CTO Program:** Duo Agent Platform Adoption\
**Key Result:** DevOps agents: 140K LLM requests from DevOps first-party agents
---
## Overview
Launch a suite of AI-powered **capabilities** that transform how users interact with GitLab CI/CD pipelines, starting with pipeline authoring assistance and expanding into pipeline failure remediation, optimization, observability, and configuration management.
## Business Objective
Address GitLab's CI adoption gap by providing intelligent assistance that guides users from pipeline creation through advanced configuration, optimization at scale, reducing time-to-first-pipeline and improving pipeline efficiency for existing users.
## Timeline
* **Phase 1 (MVC)**: Foundational Agent; Pipeline Authoring/Builder Agent
* **Phase 2**: Test Intelligence Agent
* **Phase 3**: Configuration Agent & Fix a Failing Pipeline Agent
## Foundational Agent Scope
Note - we need a build a foundational Agent for CI as a pre-requisite
## Agent Portfolio - Use Cases Prioritized for Delivery
| Ordinal Priority Ranking | Pipeline Lifecycle | Pipeline Agent Use Cases | Target Delivery | Problem to Solve | Notes |
|--------------------------|--------------------|--------------------------|-----------------|------------------|-------|
| 1 | Authoring | Pipeline Builder | Q1 - 18.11 | Auto-create a GitLab CI pipeline in GitLab UI for new projects. Foundational for projects migrating from GitHub. | High confidence in delivery. For clarity - this is referring to the Agent required for the Pipeline Builder |
| 2 | Execution | [Fix a failing pipeline- Auto-retry on Infrastructure Failures](https://gitlab.com/groups/gitlab-org/-/work_items/20623) | Q2 | Auto-retry failing pipelines for infrastructure failures | Build using the Fix a failing pipeline flow that exists today. |
| 3 | Execution | https://gitlab.com/groups/gitlab-org/-/work_items/21181+s | Q1 | Trigger the flow automatically on GitLab Internal projects only (No auto-retry) | Build using the Fix a failing pipeline flow that exists today. |
| 4 | Execution | Fix a failing pipeline - auto trigger the flow (Customer projects) | TBD | Trigger the flow automatically on customer projects | |
| 5 | Execution | [Fix a failing pipeline- Auto-retry on Flaky Test Failures](https://gitlab.com/groups/gitlab-org/-/work_items/20921) | Q3 | Auto-retry failing pipelines on flaky test failures | Required: Building a Flaky Test Detection feature |
| ~~4~~ | ~~Execution~~ | ~~Fix a failing pipeline- Preventative~~ | ~~Q4~~ | ~~Investigation into preventing a failing pipeline.~~ | ~~Build using the Fix a failing pipeline flow that exists today.~~ |
| 6 | Execution | Pipeline Optimization - Run tests that are only relevant to code changes | Q4 | Deliver intelligence to improve pipeline efficiency. | Medium confidence in delivery. Need to determine if we need more data. |
| ~~6~~ | ~~Execution~~ | ~~Pipeline Optimization~~ | ~~Q4~~ | ~~Deliver features for pipeline cost and speed optimization.~~ | ~~Low confidence in delivery.~~ |
| 7 | Authoring | Pipeline Configuration | Q4 | | Low confidence in delivery. |
## Critical Go/No-Go Decision Points
| Decision Point | Date | Impact if NO-GO |
|----------------|------|-----------------|
| Fix Failing Pipeline Spike | April 11, 2026 | Q2 delivery at risk; may pivot to alternate agent or extend timeline |
| Test Intelligence Spike | June 20, 2026 | Q3 delivery at risk; may pivot or extend timeline |
| Pipeline Optimization Spike | September 11, 2026 | Q4 delivery at risk; may pivot or reduce to single Q4 agent |
| Fix Failing - Preventative Spike | September 18, 2026 | Q4 delivery at risk; may pivot or reduce to single Q4 agent |
## Success Metrics / Business Outcomes
- {placeholder}
## Important Reference Links - Please Read if new to Duo Development
#### AI links
- [Building with Duo Agent Platform](https://docs.google.com/presentation/d/1RLj4LIt8yPnjN5OWYAsP4tSNqQJMXJ_e819yHUdE0us/edit?slide=id.g375873d1863_0_0#slide=id.g375873d1863_0_0)
- [Flow Registry Framework Developer Guide](https://gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/-/tree/main/docs/flow_registry)
- [Tools](https://gitlab.com/groups/gitlab-org/ai-powered/-/wikis/home/Agentic-IDE#tools-agenticidetool)
- [Interaction methods epic](https://gitlab.com/groups/gitlab-org/-/epics/18712)
- [Agents & flows](https://gitlab.com/groups/gitlab-org/-/epics/19001)
- [DAP tracker](https://gitlab.com/groups/gitlab-org/ai-powered/-/wikis/home/Program-Duo-Agent-Platform/DAP-Enablement/)
- [Duo Agent Platform Features](https://gitlab.com/gitlab-org/ai-powered/duo-agent-platform/-/wikis/product-engineering/platform-roadmap/Duo-Agent-Platform-Features)
- [Duo Agent Platform Docs](https://docs.gitlab.com/development/ai_features/duo_agent_platform/)
- [Instrumentation](https://gitlab.com/groups/gitlab-org/-/epics/19545) -[Deep Research Agent Prototype](https://gitlab-research-agent.michaelangelo.io/)
- Knowledge Graph
- https://gitlab.com/gitlab-org/rust/knowledge-graph
- https://gitlab-org.gitlab.io/rust/knowledge-graph/
epic