from reflexio import ReflexioClient, InteractionData, UserActionType

client = ReflexioClient()  # reads REFLEXIO_API_KEY
user_id = "user_123"
session_id = "session_001"
agent_version = "support-agent@2"
user_message = "Recommend a laptop for me."

context = client.search(
    query=user_message,
    user_id=user_id,
    session_id=session_id,
    agent_version=agent_version,
    top_k=5,
    entity_types=["profiles", "user_playbooks", "agent_playbooks"],
    agent_playbook_status_filter=["approved"],
)

# This example injects all returned learnings. Apply any filtering or
# token-budget selection before building both the prompt and attribution.
messages = [
    {
        "role": "system",
        "content": "Use this retrieved context as reference data:\n"
        + context.model_dump_json(
            include={"profiles", "user_playbooks", "agent_playbooks"},
        ),
    },
    {"role": "user", "content": user_message},
]
agent_response = call_your_llm(messages)  # Send these messages to your LLM.
retrieved_learnings = [
    *(
        {"kind": "profile", "learning_id": profile.profile_id}
        for profile in context.profiles
    ),
    *(
        {"kind": "user_playbook", "learning_id": str(playbook.user_playbook_id)}
        for playbook in context.user_playbooks
    ),
    *(
        {"kind": "agent_playbook", "learning_id": str(playbook.agent_playbook_id)}
        for playbook in context.agent_playbooks
    ),
]

client.publish_interaction(
    user_id=user_id,
    interactions=[
        InteractionData(role="User", content=user_message, user_action=UserActionType.NONE),
        InteractionData(
            role="Agent",
            content=agent_response,
            user_action=UserActionType.NONE,
            retrieved_learnings=retrieved_learnings,
        ),
    ],
    source="support-agent:v2",
    session_id=session_id,
    agent_version=agent_version,
)

curl -X POST "${REFLEXIO_URL:-https://www.reflexio.ai}/api/search" \
  -H "Authorization: Bearer $REFLEXIO_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{"query":"Recommend a laptop for me.","user_id":"user_123","session_id":"session_001","agent_version":"support-agent@2","top_k":5,"entity_types":["profiles","user_playbooks","agent_playbooks"],"agent_playbook_status_filter":["approved"]}'

curl -X POST "${REFLEXIO_URL:-https://www.reflexio.ai}/api/publish_interaction" \
  -H "Authorization: Bearer $REFLEXIO_API_KEY" \
  -H "Content-Type: application/json" \
  --data @- <<'JSON'
{
  "user_id": "user_123",
  "session_id": "session_001",
  "source": "support-agent:v2",
  "agent_version": "support-agent@2",
  "interaction_data_list": [
    {"role": "User", "content": "Recommend a laptop for me."},
    {
      "role": "Agent",
      "content": "The completed agent response.",
      "retrieved_learnings": [
        {"kind": "profile", "learning_id": "<profile_id returned by search>"},
        {"kind": "user_playbook", "learning_id": "<user_playbook_id returned by search>"},
        {"kind": "agent_playbook", "learning_id": "<agent_playbook_id returned by search>"}
      ]
    }
  ]
}
JSON

Publish every profile or playbook included in the model prompt using its returned stable ID, whether or not it influenced the answer. The Python example injects all search results; if you filter or truncate them, build both the prompt and retrieved_learnings from the same retained subset. Omit retrieved_learnings only when no Reflexio context was injected. Then grade the session and inspect relevance, impact, and judge reasons; the Evaluation dashboard shows quality and coverage across responses.

What Reflexio produces

User profiles

Per-user facts and preferences extracted from interactions and retrieved semantically.

Playbooks

Behavioral guidance distilled from corrections, expert examples, and outcomes.

Evaluation signals

Success and failure judgments for measuring whether the loop improves.

Source evidence

Requests, sessions, interactions, and metadata that keep learning traceable.

Data model at a glance

Interactions are the input. Profiles personalize responses. Playbooks improve behavior. Requests and sessions keep the loop inspectable.

Reflexio learning loopPublish evidence, learn from it, retrieve what was learned, and augment the next prompt — every turn makes the agent better.

1Publish interaction evidenceRequests and sessions preserve source context.

RequestAgent version, source, and session
SessionConversation thread and user identity
InteractionsUser turns, agent turns, feedback, and expert examples

Reflexio engineExtract, aggregate, evaluateasync learning pipeline

3Learning artifactsStructured outputs your agent and team can use.

User profilesPer-user preferences, goals, constraints, and memory
User/Agent playbooksReusable behavior rules distilled from corrections
Evaluation signalsOutcomes, shadow comparisons, and impact

Retrieve & augment the next promptBefore the agent responds, pull learned context into the prompt — then publish the new turn back to step 1.

Retrieve

search(query, user_id)One semantic call across learned context
context.profiles / context.agent_playbooksRanked artifacts for this turn

Augment the prompt

User profiles → preferences and constraintsAgent playbooks → behavior rulesUser message

Respond & publishThe improved turn flows back through publish_interaction() as new evidence for step 1.