Aginera Takeoff & Estimation API
62
AI ReadinessAI-Aware (B-)62/100
Official vendor OpenAPI document · agent-readyData EnrichmentData Transformationoauth234 EndpointsREST
For Agents
Run takeoffs on construction drawings to extract measured items, routes, and schedules, review and override them, export to CSV/XLSX/JSON, and convert PDFs to CAD.
Use for: Run a takeoff on a construction drawing, Extract measured quantities from a PDF drawing, Review and adjust extracted takeoff items, Export a takeoff to Excel
Not supported: Does not handle project scheduling, procurement, or contractor payments. Use for extracting construction quantities, routes, and schedules from drawings and exporting them only.
The Aginera API extracts structured construction quantities from drawings so they can be measured, reviewed, and exported. A project holds drawing documents added from a URL or direct upload, and a takeoff run over a document returns measured items, routes such as conduit and pipe, and detected schedules. Extracted items can be accepted, rejected, or overridden while the raw extraction stays immutable, and the result exports to CSV, XLSX, or JSON for downstream estimating. It can also convert a PDF drawing to DXF or DWG and reports credit balance and per-request usage.
Install Jentic One Beta
Connect the Aginera Takeoff & Estimation API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Aginera Takeoff & Estimation API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Faginera.ai%2Faginera" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Faginera.ai%2Faginera" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Aginera Takeoff & Estimation API.
Create a project and attach drawing documents from a URL or a direct upload
Run a takeoff on a document to extract measured items, routes, and schedules
Review extracted items by accepting, rejecting, or overriding them
Read takeoff totals by trade, category, and unit
Export a takeoff to CSV, XLSX, or JSON
Convert a PDF drawing to DXF or DWG and get a time-limited download link
Check the account's credit balance and per-request usage
Use Cases
Patterns agents use Aginera Takeoff & Estimation API for, with concrete tasks.
★ Agent-Run Construction Takeoffs
An AI agent connecting through Jentic can turn a drawing into measured quantities without a human in the loop: it creates a project, adds the document, starts a takeoff, and polls until the summary is ready. Jentic injects the OAuth token at call time, so the agent runs the long-running takeoff flow without ever holding the credential in its prompt.
Create a project, add a drawing document, start a takeoff on it, then poll the takeoff until its summary resolves
Drawing-to-Quantities Extraction
Pull measured items, routes, and schedules straight from a construction drawing. The Aginera API runs a takeoff on a document and returns extracted items, measured routes like conduit, feeder, duct, pipe, and tray with endpoints and geometry, and detected schedules for panels, fixtures, and equipment, with totals broken out by trade, category, and unit.
Run a takeoff on a document, then read its items and routes and the summary totals by trade and unit
Takeoff Review and Export
Correct an extraction and hand it off to an estimating tool. The Aginera API lets you accept, reject, or override individual items while keeping the raw extraction immutable, then export the reviewed takeoff to CSV, XLSX, or JSON. An agent can clean up a takeoff and deliver a spreadsheet the estimator can price.
Override a mis-extracted item on a takeoff, then create an XLSX export and return its download link
PDF Drawing to CAD
Convert a PDF drawing into a CAD file an estimator or detailer can open. The Aginera API checks whether a document can be converted and what it costs the account, then converts the PDF to DXF or DWG and returns a time-limited download link, so an agent can produce a CAD deliverable from a flat drawing on demand.
Check the CAD conversion cost for a document, then convert its PDF to DXF and return the time-limited download link
Key Endpoints
34 endpoints — the aginera api extracts structured construction quantities from drawings so they can be measured, reviewed, and exported.
METHOD
PATH
DESCRIPTION
POST
/projects
Create a project
POST
/documents
Add a drawing document
POST
/takeoffs
Start a takeoff on a document
GET
/takeoffs/{takeoff_id}/items
List extracted items
GET
/takeoffs/{takeoff_id}/summary
Totals by trade, category, and unit
POST
/exports
Export a takeoff as CSV, XLSX, or JSON
POST
/documents/{document_id}/cad-files
Convert a PDF to DXF or DWG
POST
/projects
Create a project
POST
/documents
Add a drawing document
POST
/takeoffs
Start a takeoff on a document
GET
/takeoffs/{takeoff_id}/items
List extracted items
GET
/takeoffs/{takeoff_id}/summary
Totals by trade, category, and unit
POST
/exports
Export a takeoff as CSV, XLSX, or JSON
POST
/documents/{document_id}/cad-files
Convert a PDF to DXF or DWG
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
A
Aginera Takeoff & Estimation API
- AI-Aware (B-)62/100
61
Foundational Compliance63
Developer Experience & Jentic Compatibility42
AI-Readiness & Agent Experience94
Agent Usability85
Security66
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
61
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: B-Signals: 4
93%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
50%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
1%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
42
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D-Signals: 4
15%
Description Coverage
Coverage of descriptions across API elements.
100%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
54%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
85
Security
Trust, risk posture, and security compliance.
Grade: ASignals: 1
85%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
66
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: BSignals: 1
66%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Aginera API by hand means standing up its OAuth 2.0 client-credentials flow, requesting the right scopes, and polling long-running takeoffs and exports yourself. Through Jentic you install once, import Aginera from the API Directory, store the credential once, and your agent calls it.
Permission scoping
You choose which Aginera operations your agent may call, so it can create projects and run takeoffs while deleting a project or takeoff stays out unless you add it. Project and takeoff ids travel in the URL path (/projects/{project_id}), so a rule can also pin the agent to one project.
Credential isolation
Your Aginera credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'run a takeoff' or 'export a takeoff', and Jentic returns the matching Aginera operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Aginera Takeoff & Estimation API through Jentic.
What authentication does the Aginera API use?
The Aginera API authenticates with OAuth 2.0 per its OpenAPI spec, using the oauth2 client-credentials flow for backends and authorization-code with PKCE for interactive use, with granular scopes such as projects:read and takeoffs:run. The access token is sent as a bearer token. Through Jentic the token is injected at call time rather than living in the agent's prompt.
Can I extract measured quantities from a drawing with the Aginera API?
Yes. Running a takeoff on a document returns extracted items, measured routes like conduit, feeder, duct, pipe, and tray with endpoints and geometry, and detected schedules, plus totals by trade, category, and unit. You can accept, reject, or override items while the raw extraction stays immutable.
What are the rate limits for the Aginera API?
The OpenAPI spec does not specify rate limits, though takeoffs and exports consume credits and long-running work is polled. Check the Aginera developer documentation at https://aginera.ai/docs/developer for current limits and credit costs.
How do I run a takeoff with the Aginera API through Jentic?
Search Jentic for 'run a takeoff on a drawing' and it returns the takeoff operation with its input schema. Your agent creates a project, adds the document, starts the takeoff, and polls it until the summary is ready. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Aginera API?
Yes. Write a rule that allows only the read and takeoff-run operations, so the agent can run takeoffs and read results while deleting a project or takeoff stays out unless you add it, and every action it takes is logged. Because project and takeoff ids appear in the URL path, a rule can also pin the agent to one project.
Is there an Aginera MCP server?
You don't need an MCP server to give your agent the Aginera API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the project, document, takeoff, and export operations on demand without loading another server's tool definitions into its context.
GET STARTED