Scope
PM / Head of AI
Matt D. on Feb 3
Build
Engineering
Simon R. on Feb 17
GRC
Compliance/Legal
Jamie L. on Mar 2
Production
DevOps
5Monitoring
Operations
Current owner: DevOps
Agent Schema
The contract definition this agent was registered against. The schema defines the expected inputs, outputs, and capabilities.
Schema ID
code-analysis-v1
Version
1.0.0
Last Updated
Feb 3, 2026 by Matt D.
Compliant
Input Schema
{
"prompt":"string (required)"
"context":"enum: code_review | debugging | architecture (required)"
"repo":"string"
"files":"array<file_ref>"
}
Output Schema
{
"analysis":"string"
"suggestions":"array<string>"
"severity":"enum: info | warning | critical"
"references":"array<url>"
}
Capabilities
- Code review and static analysis
- Debugging analysis
- Architecture recommendations
- GitHub context (read-only)
Schema History
v1.0.0Feb 3Initial schema
Version & Instance
Where this agent sits in the version tree and its relationship to other instances.
Type
Global Agent (canonical definition)
Version
v2.1.0
Registered
Jan 20, 2026 by Matt D.
Last Deployed
Mar 25, 2026
Runtime
Python 3.11 / ECS
Repository
acme/chatgpt-copilot (main branch)
Instance Tree
ChatGPT (GA-002) ← you are here
└──
Carol's ChatGPT (UA-003)
Schema: code-analysis-v1 · Stage: Monitoring
Config: Synced (Scoped to product team context)
Last sync: Mar 25
Version History
v2.1.0Mar 25Add architecture context mode
v2.0.0Mar 1Upgrade to Assistants v2 API⚠️ Breaking
v1.1.0Feb 10Add file context support
v1.0.0Jan 20Agent registered
Service Access
Which services and MCP connections this agent is authorised to use.
| Service | Auth | Data Scope | Last Access | |
|---|---|---|---|---|
ApprovedGitHub-MCP | OAuth token | acme/chatgpt-copilot (read), acme/shared-prompts (read/write) | Mar 30 16:28 |
Data Access Policies
What data this agent can read, write, and process. Violations are logged to the audit trail.
Read OnlySource Code
GitHub repos in acme org
Read OnlyInternal Docs
Engineering wiki, product briefs
BlockedCustomer Data
No access to customer PII or claims
BlockedFinancial Records
No financial access
Model Access
Which AI models this agent is authorised to use.
GPT-4oPrimary
80%
GPT-4o miniFallback
20%
Claude SonnetNot authorised
Claude OpusNot authorised
Gemini ProNot authorised
Credentials
API keys and auth tokens used by this agent. Managed by Engineering.
| Credential | Type | Created | Expires | Status | |
|---|---|---|---|---|---|
| OpenAI API Key | API Key | Jan 20 | None | Active | |
| GitHub OAuth | OAuth 2.0 | Jan 22 | Jul 22 | Active |
