Integration · Developer tools

Connect Claude & ChatGPT to Keywords AI

Ask your AI what your LLM app did yesterday, and it reads the request logs, traces and usage totals from Keywords AI, now called Respan. It can open a single request with its prompt, response, tokens and cost, and see usage per end customer. It can also create prompts and new prompt versions, deploy a version, and build datasets from your logs.

Connect Keywords AI free

Free plan, no credit card. Takes about a minute.

Try asking

“How many requests, tokens and dollars did we use in the last 24 hours?”
The AI reads the usage summary for that period with total requests, tokens, cost and latency.
“Show me the failed requests from production this morning.”
It lists request logs in that time range for the production environment, filtered on status, with model and cost.
“Open log abc123 and show what the model answered.”
It reads that request log with the prompt, the response, the model, tokens, cost and latency.

What your AI can do

Logs, traces and usage

List and read request logs and traces, and get totals for requests, tokens, cost and latency over any period.

Prompts

List and read managed prompts and their versions, create prompts and versions, and deploy a version to production.

Datasets and evaluations

Create datasets from logs, and read datasets, testsets, evaluators, experiments and end customers.

“Which of our customers used the most this month?”
It lists your end customers with their usage and can open one customer to see cost and budget.
“Walk me through the trace for last night's failed agent run.”
It finds the trace in the time range and reads all its spans in order.
“Add a version of the support-reply prompt with temperature 0.2, but don't deploy it yet.”
It creates a new prompt version with the messages, model and settings you give. The live version stays the same until you deploy the new one.

178 tools for Keywords AI

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

cancel_batchMoves moneyCancel a batch (batch id). Financial or irreversible action; may require approval.
create_a_scoreChanges dataCreate a new score. API summary: Create a score.
create_an_openrouter_chat_completionChanges dataCreate a new completion. Required: model or messages. API summary: Create an OpenRouter chat completion.
create_batchVisible to othersCreate a new batch. Required: input file id, endpoint, completion window or provider id. Has effects visible outside this system. API summary: Create a batch.
create_breakdownChanges dataCreate a new breakdown. API summary: List metrics broken down by dimension.
create_bulkVisible to othersCreate a new bulk. Required: logs. Has effects visible outside this system. API summary: Bulk create spans.
create_bulk_datasets_bulk_create_dataset_logsVisible to othersCreate a new bulk. Required: logs. Has effects visible outside this system. API summary: Bulk create dataset logs.
create_bulk_prompts_process_prompt_bulk_operationsVisible to othersCreate a new bulk. Required: requests. Has effects visible outside this system. API summary: Bulk update, commit, or deploy prompts.
create_bulk_traces_bulk_delete_tracesVisible to othersCreate a new bulk. Required: filters. Has effects visible outside this system. API summary: Bulk delete traces.
create_cacheChanges dataCreate a new cache. API summary: List cached responses with filters.
create_cache_hit_metricChanges dataCreate a new cache hit metric. API summary: List cache hit metrics.
create_completionChanges dataCreate a new completion. API summary: Create chat completion.
create_createChanges dataCreate a new create. Required: evaluator ids. API summary: Run evaluators on a dataset.
create_datasetChanges dataCreate a dataset with `name` and `description`, either empty (`is_empty`) or sampled from logs between `start_time` and `end_time`, or copied from `source_dataset_id`.
create_dataset_logChanges dataCreate a new log for a dataset. Required: input. API summary: Create a dataset log.
create_embeddingChanges dataCreate a new embedding. Required: model or input. API summary: Create embeddings.
create_eval_resultChanges dataCreate a new eval result. API summary: List evaluation scores.
create_evaluatorChanges dataCreate a new evaluator. Required: name. API summary: Create an evaluator.
create_evaluator_runChanges dataCreate a new run for a evaluator. Required: inputs. API summary: Run an evaluator.
create_evaluator_versionChanges dataCreate a new version for a evaluator. API summary: Create evaluator version.
create_experimentChanges dataCreate a new experiment. Required: dataset id or workflow. API summary: Create an experiment.
create_experiment_histogramChanges dataCreate a new histogram for a experiment. Required: evaluator id. API summary: Get experiment score histogram with filters.
create_groupChanges dataCreate a new group. API summary: Filter span groups.
create_ingestChanges dataCreate a new ingest. API summary: Ingest spans from traces (v1 legacy).
create_limit_policyChanges dataCreate a new limit policy. Required: name, scope value, metric or rules. API summary: Create a limit policy.
create_llm_metricChanges dataCreate a new llm metric. API summary: List LLM metrics.
create_log_scoreChanges dataCreate a new score for a log. API summary: Create or update a log score.
create_log_threadChanges dataCreate a new log thread. API summary: List thread.
create_messageChanges dataCreate a new message. Required: anthropic version, model, max tokens or messages. API summary: Create an Anthropic message.
create_modelChanges dataCreate a new model. Required: model name. API summary: Create or update a custom model.
create_promptChanges dataCreate a new managed prompt with a `name` and optional `description`. Add content with create_prompt_version.
create_prompt_commitChanges dataCreate a new commit for a prompt. API summary: Commit a prompt version.
create_prompt_versionChanges dataCreate a new version of a prompt by `prompt_id` with `messages`, `model`, `temperature` and other settings. `deploy` true makes it live immediately.
create_providerChanges dataCreate a new provider. Required: provider id or provider name. API summary: Create a custom provider.
create_quantileChanges dataCreate a new quantile. API summary: List latency / TTFT / TPS quantiles.
create_request_logChanges dataCreate a new request log. API summary: Create a span.
create_responseChanges dataCreate a new response. Required: input. API summary: Create a response.
create_response_format_presetChanges dataCreate a new response format preset. Required: name or response format content. API summary: Create a response-format preset.
create_scoreChanges dataCreate a new score. Required: span or behaviors. API summary: Score behaviors with Span-01.
create_speechChanges dataCreate a new speech. Required: model, input or voice. API summary: Text to speech.
create_summary_experiments_filter_experiment_spans_summaryChanges dataCreate a new summary. API summary: Filter experiment trace summary.
create_summary_experiments_filter_experiments_summaryChanges dataCreate a new summary. API summary: Filter experiments summary.
create_summary_models_filter_models_summaryChanges dataCreate a new summary. API summary: Filter models summary.
create_systemoneChanges dataCreate a new systemone. API summary: Evaluate state with TypeSafe Jev.
create_temporary_keyChanges dataCreate a new temporary key. API summary: Create an API key.
create_testsetChanges dataCreate a new testset. Required: name. API summary: Create a testset.
create_testset_rowChanges dataCreate a new row for a testset. Required: testset rows. API summary: Create testset rows.
create_total_summaryChanges dataCreate a new total summary. API summary: Get lifetime cache hit totals.
create_traceChanges dataCreate a new trace. Required: resource spans. API summary: Create a trace (OTLP).
create_transcriptChanges dataCreate a new transcript. Required: audio url. API summary: Create an AssemblyAI transcript.
create_user_experiments_list_experiment_spansChanges dataCreate a new user. API summary: Filter experiment traces.
create_user_models_filter_modelsChanges dataCreate a new user. API summary: Filter models.
create_user_scores_filter_scoresChanges dataCreate a new user. API summary: Filter scores.
create_user_workflows_filter_workflowsChanges dataCreate a new user. API summary: Filter workflows.
create_workflowChanges dataCreate a new workflow. Search workflows first to avoid duplicates. API summary: Create a workflow.
create_workflow_commitChanges dataCreate a new commit for a workflow. API summary: Commit a workflow draft.
create_workflow_deploymentChanges dataCreate a new deployment for a workflow. API summary: Deploy a workflow version.
create_workflow_validationChanges dataCreate a new validation for a workflow. API summary: Validate a workflow.
create_workflow_versionChanges dataCreate a new version for a workflow. API summary: Create a workflow draft.
delete_bulksMoves moneyPermanently delete a bulk. Financial or irreversible action; may require approval. API summary: Bulk delete cached responses.
delete_cacheDeletesPermanently delete a cache by cache key. Destructive action; may require approval. API summary: Delete a cached response.
delete_datasetDeletesPermanently delete a dataset by dataset id. Destructive action; may require approval.
delete_dataset_logDeletesPermanently delete a log by unique id. Destructive action; may require approval. API summary: Delete a dataset log.
delete_documentMoves moneyPermanently delete a document by document id. Financial or irreversible action; may require approval. API summary: Delete a file.
delete_evaluatorDeletesPermanently delete a evaluator by evaluator id. Destructive action; may require approval. API summary: Delete an evaluator.
delete_experimentDeletesPermanently delete a experiment by experiment id. Destructive action; may require approval. API summary: Delete an experiment.
delete_limit_policyDeletesPermanently delete a limit policy by limit policy id. Destructive action; may require approval.
delete_log_scoreDeletesPermanently delete a score by score id. Destructive action; may require approval. API summary: Delete a log score.
delete_modelDeletesPermanently delete a model by model name. Destructive action; may require approval. API summary: Delete a custom model.
delete_promptDeletesPermanently delete a prompt by prompt id. Destructive action; may require approval.
delete_prompt_versionDeletesPermanently delete a version by version. Destructive action; may require approval. API summary: Delete a prompt version.
delete_providerDeletesPermanently delete a provider by provider id. Destructive action; may require approval. API summary: Delete a custom provider.
delete_response_format_presetDeletesPermanently delete a response format preset by response format preset id. Destructive action; may require approval. API summary: Delete a response-format preset.
delete_scoreDeletesPermanently delete a score by score id. Destructive action; may require approval.
delete_temporary_keyDeletesPermanently delete a temporary key by temporary key id. Destructive action; may require approval. API summary: Delete an API key.
delete_testsetDeletesPermanently delete a testset by testset id. Destructive action; may require approval.
delete_testset_rowDeletesPermanently delete a row by row index. Destructive action; may require approval. API summary: Delete a testset row.
delete_testset_rowsMoves moneyPermanently delete a row by testset id. Financial or irreversible action; may require approval. API summary: Delete testset rows.
delete_traceDeletesPermanently delete a trace by trace unique id. Destructive action; may require approval.
delete_userDeletesPermanently delete a user by customer identifier. Destructive action; may require approval. API summary: Delete a customer.
delete_workflowDeletesPermanently delete a workflow by workflow id. Destructive action; may require approval.
delete_workflow_deploymentsMoves moneyPermanently delete a deployment by workflow id. Financial or irreversible action; may require approval. API summary: Undeploy a workflow.
deploy_prompt_versionChanges dataMake a prompt `version` the live version for `prompt_id`. Production calls using this prompt switch to it right away.
get_batchGet one batch by batch id. API summary: Retrieve a batch.
get_cacheGet one cache by cache key. API summary: Retrieve a cached response.
get_cache_hit_summaryChanges dataCreate a new summary. API summary: Get cache hit summary.
get_customerGet one end customer by `customer_identifier`: usage, cost and budget.
get_datasetGet one dataset by `dataset_id`.
get_dataset_logGet one log for a dataset by unique id. API summary: Retrieve a dataset log.
get_documentGet one document by document id. API summary: Retrieve a file.
get_evaluation_scores_summaryChanges dataCreate a new summary. API summary: Get evaluation scores summary.
get_evaluatorGet one evaluator by `evaluator_id` with its configuration.
get_evaluator_versionGet one version for a evaluator by version. API summary: Retrieve evaluator version.
get_experimentGet one experiment by `experiment_id` with its status and results.
get_experiment_logGet one log for a experiment by log id. API summary: Retrieve an experiment trace.
get_filtered_cache_summaryChanges dataCreate a new summary. API summary: Get filtered cache summary.
get_filtered_dataset_logs_summaryChanges dataCreate a new summary. API summary: Get filtered dataset logs summary.
get_filtered_evaluators_summaryChanges dataCreate a new summary. API summary: Get filtered evaluators summary.
get_filtered_testsets_summaryChanges dataCreate a new summary. API summary: Get filtered testsets summary.
get_limit_policyGet one limit policy by limit policy id. API summary: Retrieve a limit policy.
get_llm_metrics_summaryChanges dataGet dashboard LLM usage metrics for a period, using `summary_type` (daily, weekly, monthly, last_24h and more) or `start_time`/`end_time`, with optional filters.
get_log_scoreGet one score for a log by score id. API summary: Retrieve a log score.
get_modelGet one model by model name. API summary: Retrieve a model.
get_model_statusGet the current status of a model by model name. API summary: Get model status.
get_model_status_statusChanges dataGet the current status of a model by model name. API summary: Filter model status.
get_paymentGet one payment by payment id. API summary: Retrieve a credit transaction.
get_promptGet one prompt by `prompt_id`, including its current version.
get_prompt_versionGet one version of a prompt by `prompt_id` and `version`: messages, model and settings.
get_prompts_summary_with_filtersChanges dataCreate a new summary. API summary: Get prompts summary with filters.
get_providerGet one provider by provider id. API summary: Retrieve a custom provider.
get_quantiles_summaryChanges dataCreate a new summary. API summary: Get quantiles summary.
get_request_logGet one request log by `unique_id`: prompt, response, model, tokens, cost and latency.
get_request_logs_summaryChanges dataGet totals (requests, tokens, cost, latency) for request logs in a time range, with optional `filters` and `environment`.
get_response_format_presetGet one response format preset by response format preset id. API summary: Get a response-format preset.
get_scoreGet one score by score id. API summary: Retrieve a score.
get_temporary_keyGet one temporary key by temporary key id. API summary: Retrieve an API key.
get_testsetGet one testset by `testset_id`.
get_testset_rowGet one row for a testset by row index. API summary: Retrieve a testset row.
get_total_unique_usersChanges dataCreate a new user. API summary: Get total unique users.
get_traceGet one trace by `trace_unique_id` with all its spans.
get_transcriptGet one transcript by transcript id. API summary: Retrieve AssemblyAI transcript.
get_workflowGet one workflow by workflow id. API summary: Get a workflow.
get_workflow_versionGet one version for a workflow by version. API summary: Get a workflow version.
list_active_users_over_timeChanges dataCreate a new user. API summary: List active users over time.
list_batchesList batches. Optional filters: provider id. Results are paginated.
list_credit_transactionsList users. Results are paginated. API summary: List credit transactions.
list_customersChanges dataList your end customers (the users of your AI app) with their usage, optionally filtered by `environment`.
list_dataset_logsChanges dataList the logs in a dataset by `dataset_id`, with optional filters.
list_datasetsChanges dataList datasets, with optional filters and sorting.
list_document_contentsList contents for a document. Optional filters: provider id. API summary: Retrieve file content.
list_documentsList documents. Optional filters: provider id. API summary: List files.
list_evaluator_versionsList versions for a evaluator. Results are paginated. API summary: List evaluator versions.
list_evaluatorsChanges dataList evaluators, with optional filters and sorting.
list_experimentsChanges dataList experiments, with optional filters and sorting.
list_groupsList groups. Optional filters: group by, sort by, start time, end time or environment. Results are paginated. API summary: List span groups.
list_limit_policiesList limit policies. Optional filters: ordering. Results are paginated.
list_log_scoresList scores for a log. Results are paginated. API summary: List log scores.
list_platform_statsList platform stats. Optional filters: breakdown by. API summary: Get public platform stats.
list_prompt_versionsList the versions of a prompt by `prompt_id`.
list_promptsChanges dataList managed prompts, optionally filtered by name, tags or dates. Use to find a prompt_id.
list_providersList providers. Results are paginated. API summary: List custom providers.
list_publicsList publics. Optional filters: unnest. API summary: List public model catalog.
list_request_logsChanges dataList LLM request logs, filtered by `start_time`, `end_time`, `environment`, `log_type` and `filters` (e.g. model, status, cost, customer). Use to find a log's unique_id.
list_response_format_presetsList response format presets. Optional filters: sort by. Results are paginated. API summary: List response-format presets.
list_storage_volumesList storage volumes. Optional filters: summary type, date or timezone offset.
list_summariesList summaries. Optional filters: summary type, date or timezone offset. API summary: Get storage volume summary.
list_temporary_keysList temporary keys. API summary: List API keys.
list_testset_rowsList the rows of a testset by `testset_id`.
list_testsetsChanges dataList testsets, with optional filters and sorting.
list_tracesChanges dataList traces (multi-step agent or workflow runs) in a time range, with optional `filters` and sorting.
list_usersList users. Results are paginated. API summary: List dataset evaluation runs.
list_workflow_versionsList versions for a workflow. Optional filters: sort by. Results are paginated. API summary: List workflow versions.
remove_logs_from_a_datasetMoves moneyImport a log (dataset id). Financial or irreversible action; may require approval. API summary: Remove logs from a dataset.
retrieve_a_public_traceGet one trace by trace unique id. API summary: Retrieve a public trace.
search_workflowsSearch workflows by sort by, type, trigger event type, search or is including public workflows. Use this to find existing workflows before creating a new workflow. Results are paginated. API summary: List workflows.
update_cacheChanges dataUpdate an existing cache identified by cache key. Only the fields you pass are changed. API summary: Update a cached response.
update_datasetChanges dataUpdate an existing dataset identified by dataset id. Only the fields you pass are changed. API summary: Update a dataset.
update_dataset_logChanges dataUpdate an existing log identified by unique id. Only the fields you pass are changed. API summary: Update a dataset log.
update_evaluatorChanges dataUpdate an existing evaluator identified by evaluator id. Only the fields you pass are changed. API summary: Update an evaluator.
update_evaluator_versionChanges dataUpdate an existing version identified by version. Only the fields you pass are changed. API summary: Update evaluator version.
update_experimentChanges dataUpdate an existing experiment identified by experiment id. Only the fields you pass are changed. API summary: Update an experiment.
update_experiment_logChanges dataUpdate an existing log identified by log id. Only the fields you pass are changed. API summary: Resume a wait workflow trace.
update_limit_policyChanges dataUpdate an existing limit policy identified by limit policy id. Only the fields you pass are changed. API summary: Update a limit policy.
update_log_scoreChanges dataUpdate an existing score identified by score id. Only the fields you pass are changed. API summary: Update a log score.
update_modelChanges dataUpdate an existing model identified by model name. Only the fields you pass are changed. API summary: Update a custom model.
update_promptChanges dataRename a prompt or change its description by `prompt_id`.
update_prompt_versionChanges dataUpdate an existing version identified by version. Only the fields you pass are changed. API summary: Update a prompt version.
update_providerChanges dataUpdate an existing provider identified by provider id. Only the fields you pass are changed. API summary: Update a custom provider.
update_response_format_presetChanges dataUpdate an existing response format preset identified by response format preset id. Only the fields you pass are changed. API summary: Update a response-format preset.
update_scoreChanges dataUpdate an existing score identified by score id. Only the fields you pass are changed. API summary: Update a score.
update_temporary_keyChanges dataUpdate an existing temporary key identified by temporary key id. Only the fields you pass are changed. API summary: Update an API key.
update_testsetChanges dataUpdate an existing testset identified by testset id. Only the fields you pass are changed. API summary: Update a testset.
update_testset_rowChanges dataUpdate an existing row identified by row index. Only the fields you pass are changed. API summary: Update a testset row.
update_traceChanges dataUpdate an existing trace identified by trace unique id. Only the fields you pass are changed. API summary: Share a trace publicly.
update_userChanges dataUpdate an existing user identified by customer identifier. Only the fields you pass are changed. API summary: Update a customer.
update_workflowChanges dataUpdate an existing workflow identified by workflow id. Only the fields you pass are changed. API summary: Update a workflow.
update_workflow_versionChanges dataUpdate an existing version identified by version. Only the fields you pass are changed. API summary: Update a workflow version.
upload_logChanges dataImport a log (dataset id). API summary: Import existing logs into a dataset.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Keywords AI from the app list.
2
Paste your key
Paste a Respan (Keywords AI) API key. Keywords AI is now called Respan: log in at platform.respan.ai, open Settings > API keys, click Create new key, choose the environment and copy the key when it is shown.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Keywords AI?

The AI can list and read request logs, traces, prompts, prompt versions, datasets, testsets, evaluators, experiments and end customers, and get usage and metrics summaries. It can create datasets, prompts and prompt versions, rename a prompt, and deploy a prompt version so it becomes live.

Does the AI see my Keywords AI credentials?

No. Your Keywords AI credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with only reading logs and usage. Deploying a prompt version switches production calls that use the prompt right away, so it can require your approval before it runs. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Keywords AI (Respan) account.

Keywords AI is now called Respan. Does this still work?

Yes. It connects to the same account under the new name. You create the API key at platform.respan.ai under Settings > API keys, and choose which environment the key belongs to when you create it.