Convoship — Sketch your bot. Ship it in five minutes.

Convoship imports run through a single extraction pipeline: deterministic baseline parse -> optional AI extraction -> validation -> repair loop (up to N iterations) -> optional frontier escalation when configured. The result is always a ConversationFlow JSON shape shared by the builder, runtime, and embed SDK.

Where to import

Surface	Route	Use case
New assistant wizard	/app/assistants/new	Create a brand-new assistant from one or more sources.
Move → Import / Export	/app/assistants/{id}/import-export	Re-import into an existing assistant; export draft or published JSON/Draw.io.
API	POST /v1/imports/...	Programmatic imports from CI or migration scripts.

New assistant wizard (3 steps)

Source — drag-drop files, paste Draw.io XML, choose Use AI extraction, or choose Start blank.
Review — extraction preview per file (intent count, node count, warnings, model used). Wizard polls until the worker finishes.
Name & create — assistant name, description, default locale (en-US, etc.), optional channel chips (Web, WhatsApp, Voice, Webhook — informational today). POST creates the assistant and redirects to import review when applicable.

Import source step with upload, Draw.io paste, AI extraction toggle, and blank assistant option — Start from the Source step. Implementation teams can upload product artifacts, paste Draw.io XML, decide whether AI extraction should run, or begin with a blank assistant when the flow will be designed manually.

Supported source types

Type	Extensions / input	Pipeline notes
Draw.io	.drawio, .xml, pasted XML	Deterministic XML parse first; LLM enriches labels, slots, and service calls.
PDF	.pdf	Text extract + optional vision (page renders) for visual content.
Word	.docx	Document text extraction then same enrich/repair loop.
Plain text	.txt, .md	Direct text baseline.
Image	.png, .jpg, .webp	Vision model (OpenAI-compatible VLM) when configured.
Flow JSON	.json	Skips extraction — validates and loads existing ConversationFlow.

AI extraction

When Use AI extraction is on (default in production), every import must succeed at LLM extraction — deterministic-only fallback is rejected when EXTRACTION_REQUIRE_LLM=true. The UI shows model name, token cost, repair iterations, and models_tried when escalation ran.

Draw.io import review with the uploaded diagram and generated assistant flow — Draw.io review is the safest handoff point from process design to implementation. Compare the source diagram with the generated flow before accepting the import.

PDF import review with extracted flow preview — PDF review keeps long-form requirements attached to the generated assistant draft, making missing intents or unclear branches easier to spot before build work starts.

Image import review with visual source and extracted flow preview — Image review supports screenshots, whiteboard sketches, and other visual source material. Use readable source images and treat warnings as follow-up implementation tasks.

Import review gate

After a wizard import, you land on /app/assistants/{id}/imports/{importId}/review. Compare baseline vs enriched flow, resolve validation issues, and Approve before publishing when import_require_review_before_publish is enabled. Publish returns import_review_required with a link to review if approval is pending.

Import / Export tab (existing assistant)

Import card — same multi-format upload as the wizard; shows stepper (parse → enrich → validate → repair).
Export — download draft or published flow as .json; export draft as .drawio for round-trip editing.
Preview Draw.io — render current draft as Draw.io XML without leaving the app.
Recent imports table — filename, model, latency, cost, status.

Scoped node repair

From the flow builder, select a node and run repair (POST /v1/agents/{id}/flow/repair-node). The extraction client re-runs LLM repair scoped to that node's validation issues without requiring the original Draw.io file. Returns updated draft, model, cost, and remaining issues.