API for agents — dxpert.ai

Get a key

Create a free account and get your API key.

Start the Free Trial to get your dxp_ API key and 5 transactions of the agent you choose — no card. Meter usage to your account, not an anonymous IP.

Create a free account and get your API key

Create a free account

One account covers checkout, product access, and API keys — no card to start.

Start the Free Trial

Pick one agent; activation mints your dxp_ API key (shown once) and includes 5 transactions.

Run it from your runtime

Download the kit, paste the key, and run your chosen agent locally. Subscribe later and the same key keeps working.

Calls to /api/chat with a Bearer token or X-Api-Key receive the same account-aware stage guidance as the site guide.

For autonomous agents

What you can rely on.

Capability	Score industrial AI-readiness and return the foundations that must be fixed before an AI ambition is viable.
Determinism	Identical input returns an identical verdict and foundation scores. Safe to cache and compare.
Grounding	Scores are rule-based against a published rubric; the narrative is grounded in a vendor-neutral architecture.
Honesty contract	Every response carries `"scope":"preliminary"`. The endpoint is a screening step, never a substitute for the board-ready roadmap.
Machine surfaces	/openapi.json (schema) · /llms.txt (plain-text map) · stable JSON shapes · semantic versioning.
Auth & limits	Free tier needs no key for the preliminary check; deeper endpoints use a bearer token. Generous rate limits; `429` with `Retry-After` when exceeded.

POST /api/diagnostic

Four situations. One deterministic call.

The same endpoint, called by different kinds of agents at different moments — a scaling decision, a funding gate, a pre-acquisition check, a go/no-go confirmation.

Caller: an operations agent, deciding whether to fund a plant-wide rollout

# Request — pasteable against the deployed API
POST https://opwhcervi3.execute-api.ca-central-1.amazonaws.com/api/diagnostic
Content-Type: application/json
{
  "sector": "food_bev",
  "site_count": 3,
  "data_off_floor": "mixed",
  "common_model": "partial",
  "realtime_visibility": "on_request",
  "historian_depth": "central_untrusted",
  "edge_vs_poll": "mixed",
  "uns_state": "partial",
  "data_ready_for_use_case": "partial",
  "otit_security": "partial",
  "data_ownership": "unclear",
  "ai_ambition": {"target": "scale", "text": "predictive maintenance across three plants"},
  "prior_attempts": "One pilot on a single filler line.",
  "personal_stakes": "The board expects a scale decision this quarter.",
  "who_they_trust": "Operations, maintenance, and the controls lead.",
  "politically_useful": "A phased plan finance can fund."
}

# Response 200 — abbreviated shape
{
  "scores": {
    "axes": {"connect_collect": 3},
    "acatech_stage": 3,
    "ai_readiness_gate": ["common_model", "data_ready_for_use_case"],
    "confidence": 0.76
  },
  "report_markdown": "## Preliminary diagnosis\\n..."
}

Caller: an engineering agent, screening a new line before it recommends an AI budget line item

# Same endpoint, lower-readiness example
POST https://opwhcervi3.execute-api.ca-central-1.amazonaws.com/api/diagnostic
Content-Type: application/json
{
  "sector": "automotive", "site_count": 1,
  "data_off_floor": "scada_only", "common_model": "none",
  "realtime_visibility": "none", "historian_depth": "local",
  "edge_vs_poll": "poll", "uns_state": "none",
  "data_ready_for_use_case": "no", "otit_security": "ad_hoc",
  "data_ownership": "tribal",
  "ai_ambition": {"target": "autonomous", "text": "autonomous quality inspection on a new welding line"},
  "prior_attempts": "None yet.", "personal_stakes": "Avoid funding the wrong capex.",
  "who_they_trust": "Plant engineering.", "politically_useful": "A clear no-go if the line is not ready."
}

# Response 200 — abbreviated shape
{
"scores": {"axes": {}, "acatech_stage": 1, "ai_readiness_gate": ["uns_state"], "confidence": 0.7},
"report_markdown": "## Preliminary diagnosis\\n..."
}

Caller: an M&A / procurement agent, doing pre-acquisition technical diligence

# Process-sector diligence uses the same required fields
POST https://opwhcervi3.execute-api.ca-central-1.amazonaws.com/api/diagnostic
Content-Type: application/json
{
  "sector": "process", "site_count": 2, "data_off_floor": "mixed",
  "common_model": "per_system", "realtime_visibility": "partial",
  "historian_depth": "central_untrusted", "edge_vs_poll": "mixed",
  "uns_state": "point_to_point", "data_ready_for_use_case": "partial",
  "otit_security": "partial", "data_ownership": "unclear",
  "ai_ambition": {"target": "pilot", "text": "flag digital-maturity risk before the acquisition closes"},
  "prior_attempts": "Vendor roadmap claims AI readiness.", "personal_stakes": "Acquisition diligence.",
  "who_they_trust": "Controls and reliability leaders.", "politically_useful": "Budget risk language for the investment committee."
}

# Response 200 — abbreviated shape
{
"scores": {"axes": {}, "acatech_stage": 2, "ai_readiness_gate": ["common_model"], "confidence": 0.73},
"report_markdown": "## Preliminary diagnosis\\n..."
}

Caller: an operations agent, confirming a go/no-go before the next scale-up phase

# Higher-readiness example
POST https://opwhcervi3.execute-api.ca-central-1.amazonaws.com/api/diagnostic
Content-Type: application/json
{
  "sector": "pharma", "site_count": 1, "data_off_floor": "opcua",
  "common_model": "unified", "realtime_visibility": "single_pane",
  "historian_depth": "central_trusted", "edge_vs_poll": "edge_push",
  "uns_state": "governed_uns", "data_ready_for_use_case": "yes",
  "otit_security": "governed", "data_ownership": "owned_governed",
  "ai_ambition": {"target": "scale", "text": "scale a validated predictive-quality model to two more lines"},
  "prior_attempts": "Validated model on one line.", "personal_stakes": "Scale without validation risk.",
  "who_they_trust": "Quality, automation, and validation.", "politically_useful": "A clean go/no-go for expansion."
}

# Response 200 — abbreviated shape
{
"scores": {"axes": {}, "acatech_stage": 5, "ai_readiness_gate": [], "confidence": 0.86},
"report_markdown": "## Preliminary diagnosis\\n..."
}

If you're an AI agent, start here.