Contact Us
Changes Implementation
Core Order of Work
Move from requested change to implementation with a controlled trail. Small changes can stay lightweight. Larger changes can use Change Requests and AI Analyst Apply.
Choose the branch
Work in Main for direct production-line changes or in a feature branch when the change needs isolation before merge.
Update or prepare specs
Define the expected behavior manually or use AI Analyst to turn high-level inputs into reviewable changes across requirements, APIs, data entities, UI and wireframes.
Decide on CR scope
Use direct artifact keys for narrow changes. Use a Change Request when the work needs a visible package and review trail.
Hand off stable keys
Give the coding agent REQ-*, MOD-*, U-*, or CR-* keys instead of a loose paragraph.
Implement with MCP context
The agent reads Reqode through MCP: app manifest, specs, units, related files, and branch-aware change context.
Verify alignment
Run checks, review Findings, and confirm that code, units, and specifications still describe the same behavior.
Known spec or known change?
I know the spec. Update it directly, copy the artifact key, and ask the coding agent to implement against that context.
I know the change. Create or select a Change Request, use AI Analyst to prepare the spec delta, apply it, and hand off the CR key.
Implementation Paths
Choose the path that matches the amount of uncertainty and governance the change needs.
Direct spec-key flow
Use for small changes where the affected artifacts are already known.
- Update the relevant specs.
- Give the agent exact keys.
- Run tests and alignment checks.
Change Request first
Use when the change needs branch scope, affected specs, review trail, and AI task history.
- Create or select
CR-*. - Link AI Analyst before Apply.
- Hand off the CR key.
AI investigation
Use when the question is clear but the impact is not.
- Ask AI Expert.
- Review references and source files.
- Route spec changes to AI Analyst.
CR during Analyst work
Use when analysis starts before the team formalizes the work package.
- Start AI Analyst from context.
- Create or select CR in result area.
- Apply after review.
Finding-driven repair
Use when a verifier or review detects spec-code divergence.
- Open the Finding evidence.
- Decide code, spec, or unit fix.
- Re-run verification.
Issue-driven repair
Use when a person raises an idea, concern, bug, or other reason for change.
- Open the Issue context with AI Analyst.
- Decide the right fix or Change Request.
- Apply and verify when relevant.
Give the agent a key, not a wall of context
The coding agent can load the exact branch-aware context through Reqode MCP and work from the same product truth as the team.
Use Reqode MCP as a source of truth. Start from CR-123.
What Reqode Captures
Reqode keeps the parts of a change connected so AI output, human review, and code implementation do not drift apart.
Specification state
Change scope
AI work
Verification signals
Verification turns drift into work
After implementation, Reqode can compare software units with linked specifications and record concrete Findings when behavior diverges.
The team can then fix code, update specs, adjust unit metadata, or open the next Change Request with evidence.
Use Reqode when change control must keep up with AI speed
Keep requirements, Change Requests, AI work, coding context, and verification connected from the first product decision to the final implementation check.