Skip to main content
POST
/
alignment
/
scaffold
Scaffold alignment from a description
curl --request POST \
  --url https://api.mnemom.ai/v1/alignment/scaffold \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "description": "<string>",
  "hints": {}
}
'
{
  "ok": true,
  "manifest": "<string>",
  "reasoning": "<string>",
  "cached": true,
  "model": "<string>",
  "suggested_catalog_entries": [
    "<string>"
  ],
  "coverage_gaps": [
    {
      "note": "<string>",
      "axis": "<string>"
    }
  ],
  "parse_warnings": [
    "<string>"
  ]
}

Authorizations

​
Authorization
string
header
required

Supabase JWT token in Authorization: Bearer header

Body

application/json
​
description
string
required

Free-form description of the agent / scope. Untrusted input — the system prompt instructs the model not to follow embedded directives.

Required string length: 20 - 2000
​
scope
enum<string>

Hint to the model about which scope the manifest will live at.

Available options:
platform,
org,
team,
agent
​
hints
object

Free-form key/value hints (industry, risk_appetite, existing_tools, etc).

​
model
enum<string>

Claude model to invoke. haiku is the default; sonnet for prose-heavy reasoning.

Available options:
haiku,
sonnet

Response

Scaffold ready. Editable; never auto-commits.

​
ok
boolean
required
​
resource
enum<string>
required
Available options:
alignment
​
manifest
string
required

YAML body of the scaffolded manifest.

​
reasoning
string
required

Care-framed prose explanation.

​
cached
boolean
required

True when the response was served from the description-hash cache.

​
model
string
required

Claude model id used for the call.

​
suggested_catalog_entries
string[]
​
coverage_gaps
object[]
​
parse_warnings
string[]