Python SDK

import decimalai
decimalai.init(api_key="dai_sk_...")

prompts = decimalai.get_replay_prompts(agent_name="my-agent", limit=10)

{
  "prompts": [
    {
      "trace_id": "trc_001",
      "input": "What flights go to Tokyo?",
      "manifest_id": "mfst_old",
      "verdict": "replay"
    }
  ],
  "total": 50,
  "limit": 10
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

replay

Export replay prompts

Export traces needing replay as a downloadable file.

Returns a list of prompts (user inputs) from traces that need to be re-run against the current agent version. Users download this file, run the prompts against their agent externally, then submit the new traces back to DecimalAI.

Each row includes a replay_context object explaining why the trace needs replay — what surfaces changed, which skills/tools were involved, and the compat reason. This metadata is informational and does not control agent behavior during replay.

Filter by verdict to get specific subsets:

replay: traces that can’t be mechanically repaired
drop: traces that are incompatible
repair: traces that need schema fixes

GET

api

replay

export

Python SDK

import decimalai
decimalai.init(api_key="dai_sk_...")

prompts = decimalai.get_replay_prompts(agent_name="my-agent", limit=10)

{
  "prompts": [
    {
      "trace_id": "trc_001",
      "input": "What flights go to Tokyo?",
      "manifest_id": "mfst_old",
      "verdict": "replay"
    }
  ],
  "total": 50,
  "limit": 10
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

Authorization

string

header

required

Enter your API key (e.g. dai_sk_test_key_001)

Headers

Authorization

string

Query Parameters

agent_name

string

required

Agent to export replay prompts for

verdict

string | null

Filter by verdict: replay, drop, repair

format

string

default:jsonl

Export format: jsonl or json

limit

integer

default:500

Required range: 1 <= x <= 5000

Cookies

decimal_session

string | null

Response

Successful Response

Submit a replay task result Export multi-turn sessions that need replay

agents

annotations

audit-log

auth

badges

billing

registry

public

changelog

contract-violations

costs

datasets

eval-scores

evaluators

evergreen

import

manifests

organization

playground

projects

regression

repair

replay

settings

api-keys

skills

skill-attachments

telemetry

traces

training

multi-agent-training

webhooks

workspaces

Export replay prompts

Authorizations

Headers

Query Parameters

Cookies

Response