Monitor, evaluate, and iterate on the quality of every function in yourenvironment. Function Accuracy bundles two complementary loops:## Evaluations (`/v3/eval`)Trigger and retrieve per-transformation evaluations. Evaluations runasynchronously and score each transformation's output against thefunction's schema for confidence, per-field hallucination detection,and relevance. Supported for `extract`, `transform`, `analyze`, and`join` events.1. **Trigger** — `POST /v3/eval` queues jobs for a batch of transformation IDs.2. **Poll** — `GET /v3/eval/results` returns the current state of each requested ID, partitioned into `results`, `pending`, and `failed`. Accepts either `eventIDs` (preferred) or `transformationIDs` as a comma-separated query parameter, and always keys the response by event KSUID.Up to 100 IDs may be submitted per request.## Metrics, review, regression (`/v3/functions/{metrics,review,regression,compare}`)Roll evaluation results and user corrections up into actionablefunction-level signal:- **`GET /v3/functions/metrics`** — aggregate accuracy, precision, recall, F1, and confusion-matrix counts per function.- **`POST /v3/functions/review`** — sample-size estimation, confidence-bucketed distribution, PR-AUC, and per-threshold confidence intervals (Wald or Wilson) for picking review cutoffs.- **`POST /v3/functions/regression`** — replay corrected historical inputs against a new function version, producing a labeled regression dataset.- **`POST /v3/functions/regression/corrections`** — propagate baseline corrections onto the regression dataset so it can be scored.- **`POST /v3/functions/compare`** — compute aggregate and field-level lift between any two versions, optionally scoped to the regression dataset.All five endpoints support `extract` end-to-end on both the visionand OCR paths, alongside the legacy `transform` / `analyze` / `join`types.
Bem Function Accuracy API is one of 22 APIs that Bem publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Function Accuracy. The published artifact set on APIs.io includes an OpenAPI specification.
This API exposes
10 operations
across 10 paths,
and defines 43 schemas.
It is described by OpenAPI 3.1.0, at version 1.0.0.
Requests are made against 2 base URLs: https://api.bem.ai, https://api.eu1.bem.ai.
10 operations10 paths43 schemas3 GET7 POST
Metadata
The identity and technical contract details declared by the specification.
Specification
OpenAPI 3.1.0
API Version
1.0.0
Base URL
https://api.bem.ai
Authentication
API Key
Resource Areas
1
Authentication & Security 1
Bem Function Accuracy API declares
1 security scheme
for authenticating requests.
An API key is passed in the header as x-api-key (API Key).
By default, every request must be authenticated.
API Key — Authenticate using API Key in request header
Paths & Operations 10
Across 10 paths, the API surfaces 10 operations — 3 GET, 7 POST. Each is listed below with its method, path, parameters, and response codes.
Function Accuracy 10
Monitor, evaluate, and iterate on the quality of every function in your environment. Function Accuracy bundles two complementary loops: Evaluations (/v3/eval) Trigger and retrieve…
POST
/v3/eval
Trigger Transformation Evaluations
v3-trigger-transformation-evaluationsbody→ 202400
GET
/v3/eval/results
Get Evaluation Results
v3-get-evaluation-results3 params→ 200400
POST
/v3/eval/score
Score Function Against (input, expected) Pairs
v3-eval-score-createbody→ 202400
GET
/v3/eval/score/{scoreRunID}
Get Score Run
v3-eval-score-get1 param→ 200404
POST
/v3/eval/score/{scoreRunID}/cancel
Cancel Score Run
v3-eval-score-cancel1 param→ 200404
POST
/v3/functions/compare
Compare Metrics Between Function Versions
v3-function-version-comparebody→ 200400404500
GET
/v3/functions/metrics
Get Function Metrics
v3-get-function-metrics7 params→ 200
POST
/v3/functions/regression
Run Function Regression Testing
v3-function-regressionbody→ 200400404
POST
/v3/functions/regression/corrections
Apply Baseline Corrections to Regression Transformations
v3-apply-baseline-correctionsbody→ 200400404500
POST
/v3/functions/review
Function Review
v3-function-reviewbody→ 200400500
Schemas 43
The contract defines 43 schemas that model the data the API accepts and returns. The most detailed are EvalScoreAggregateV3 (10 properties), ThresholdResult (10 properties), FunctionReviewRequest (10 properties), functionVersionCompareResponse (10 properties). Each schema is shown below with its type and property counts.
EvaluationResultsResponseV3
object
Batched response containing the evaluation state for every requested ID, partitioned into completed results, still-running pending, and terminal failed groups.…
4 properties1 required
FieldMetrics
object
Enhanced field metrics with comprehensive analytics
2 properties1 required
functionVersionCompareResponse
object
Response containing metrics comparison between two function versions Shows absolute differences, lift percentages, and field-level changes.
10 properties3 required
functionRegressionResult
object
Detailed regression test results and tracking information Contains function call IDs for monitoring progress. When all function calls complete, use the transfo…
3 properties2 required
EvalScoreRunResponseV3
object
Full status payload returned by GET /v3/eval/score/{scoreRunID}.
8 properties7 required
fieldMetricsComparison
object
Comparison of field-level metrics
2 properties2 required
FunctionMetricsResponse
object
2 properties2 required
EvalScoreRunStatusV3
string
Status values for an eval-score run.
FunctionReviewResponse
object
Response containing review requirements estimate
4 properties3 required
EvalMatchConfigV3
object
Comparator configuration. All fields optional; conservative defaults.
5 properties
functionRegressionResponse
object
Response from initiating a regression test Contains the function call IDs created for async processing and tracking information. Use the returned function call…
2 properties2 required
EvalScoreRequestV3
object
Request body for POST /v3/eval/score. Submits a list of (input, expected) pairs to score against the named function.
4 properties2 required
FailedEvaluationV3
object
An event whose evaluation failed or was not found.
3 properties3 required
functionRegressionRequest
object
Request parameters for function regression testing Configures which function to test, sample size, and version comparison settings. All parameters except funct…
5 properties1 required
RateConfidenceInterval
object
Confidence interval for a rate/proportion using Wald (normal approximation) method by default. Wald confidence intervals use the normal approximation to the bi…
5 properties2 required
EvalScorePairStatusV3
string
Per-pair status.
regressionFunctionCall
object
Call created for regression testing Links the original historical reference ID to the new call ID created for testing. Use the call ID with standard call endpo…
2 properties2 required
EvalScoreFieldResultV3
object
One leaf in expected ∪ actual.
5 properties2 required
EvalScoreCreateResponseV3
object
Returned by POST /v3/eval/score.
2 properties2 required
TriggerEvaluationsRequestV3
object
Request to queue evaluation jobs for a batch of transformations. Evaluations assess a transformation's output against the function's schema-defined ground trut…
2 properties1 required
EvalScoreProgressV3
object
Counts across all pairs.
3 properties3 required
metricComparison
object
Comparison of a single metric between two versions
4 properties
FunctionReviewRequest
object
Request for estimating review requirements for a function
10 properties1 required
functionVersionCompareRequest
object
Request to compare metrics between two function versions Compares metrics from two versions of a function to show lift or regression.
4 properties1 required
TriggerEvaluationsResponseV3
object
Summary of the trigger call. Evaluations run asynchronously; use GET /v3/eval/results to poll for results.
3 properties2 required
MetricsDetails
object
Detailed performance metrics and analysis
3 properties
EvaluationResultV3
object
A completed evaluation result for a single transformation.
6 properties6 required
metricsComparison
object
Comparison of metrics between two versions
4 properties
applyBaselineCorrectionsResponseV3
object
V3 response from applying baseline corrections to regression transformations. Identifiers are surfaced as event KSUIDs — the externally-stable IDs used everywh…
4 properties4 required
FunctionType
string
The type of the function.
applyBaselineCorrectionsRequest
object
Request to apply baseline corrections to regression transformations Specifies which function and versions to use for copying corrected JSON data from baseline…
3 properties3 required
EvalScorePairV3
object
One (input, expected) pair.
2 properties2 required
FunctionMetrics
object
4 properties4 required
EvalScorePairResultV3
object
Per-pair result.
5 properties2 required
InputType
string
The input type of the content you're sending for transformation.
FieldMetricV3
object
Metrics for a single field inside a transformation's output.
4 properties4 required
PendingEvaluationV3
object
An event whose evaluation is still running.
2 properties2 required
Metrics
object
Comprehensive performance metrics
8 properties
FileInput
object
A single file input with base64-encoded content. When using the Bem CLI, use @path/to/file in the inputContent field to automatically read and base64-encode th…
2 properties2 required
ThresholdResult
object
Results for a specific confidence threshold analysis
10 properties5 required
HTTPError
object
Standard HTTP error response
3 properties1 required
ReviewEstimate
object
Detailed review requirements estimate
6 properties6 required
EvalScoreAggregateV3
object
Aggregate accuracy metrics.
10 properties10 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.
Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.
MCP tools for apis
4 tools reach this content
search_api_evangelistSearch every content type across the network at once.
find_relatedThe shared-tag relevance graph — what else covers this.
get_tagEverything one tag labels, across all content types.
guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
A second provider on the same verified email joins the account you already have.
Your account
ⓘWhere this information came from
This is an independent, third-party profile of Bem Function Accuracy API, published by
API Evangelist. We do not operate, host, resell, or
support these APIs, and we are not affiliated with or endorsed by the company unless stated above.
Everything here is built from publicly available information — the company's own site,
developer portal, documentation, public repositories, and the specifications it publishes for public use.
Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's
public API artifacts, scored against a published rubric. They are not certifications,
endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and
you do not need to justify the request. A removed company is recorded as unrated, never scored
zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy → On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.
