Skip to main content
GET
/
api
/
suggestions
Action suggestions
curl --request GET \
  --url https://api.example.com/api/suggestions
{
  "action_name": "<string>",
  "success_probability": 123,
  "evidence_count": 123,
  "reasoning": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.minns.ai/llms.txt

Use this file to discover all available pages before exploring further.

This is the Policy Guide endpoint. Given the current context, it recommends the next best action based on past experiences and learned strategies.

​
Query parameters

​
context_hash
integer
required
Context fingerprint (computed from the current context).
​
last_action_node
integer
Last action node ID. Set to null to get suggestions from the start.
​
limit
integer
default:"10"
Maximum number of suggestions to return.

​
Response

Returns an array of ActionSuggestionResponse objects.
​
action_name
string
Suggested action name.
​
success_probability
number
Probability of success (0.0–1.0).
​
evidence_count
integer
Number of supporting past examples.
​
reasoning
string
Explanation for why this action is recommended.
[
  {
    "action_name": "check_seat_availability",
    "success_probability": 0.94,
    "evidence_count": 12,
    "reasoning": "After confirming the movie title, checking availability has a 94% success rate based on 12 past interactions."
  }
]

​
Usage with the SDK

const suggestions = await client.getActionSuggestions(contextHash, lastActionNode, 3);

if (suggestions.length > 0) {
  const best = suggestions[0];
  console.log(`Recommended: ${best.action_name} (${(best.success_probability * 100).toFixed(0)}% success)`);
  console.log(`Reasoning: ${best.reasoning}`);
}