apply_loantenure?amount?credit_check
Sketch the conversation
Draw a flow in Draw.io the same way your team whiteboards it. Boxes, arrows, decision diamonds, and service-call labels all become structured flow primitives.
✣sketch -> bot
Sketch your bot.
Ship it in five minutes.
Drop a Draw.io diagram, PDF, Word file, or image. Convoship extracts intents, entities, decisions, and service calls into a runnable agent. Edit on the canvas, simulate live, then embed anywhere with one line of script.
The same workspace also offers AI Agents (mission, tools, guardrails) and Workflows to chain assistants, agents, and webhooks — for when a sketch is the start, not the whole story.
Audit log & MFA·Workspace roles·Encrypted secrets·Omni-channel deploy
how convoship works
From sketch to shipping in three moves.
A deterministic Draw.io parser gives Convoship the baseline. A single model pass cleans labels, infers slots, and lifts service calls. You review the result on a familiar visual canvas.
Llama 3.3 70B
groq · OpenAI-compatible
✓12 nodes
✓14 edges
✓4 labels cleaned
✓2 slots inferred
412ms · 1.2k tokens · $0.004
Convoship parses it
Run the extractor, clean labels, infer entity slots, and wrap HTTP nodes as real tool calls with auth, retries, and response mapping.
<script src=
"https://embed.convoship.org/v1.js">
</script>
ConvoshipQueue.push(['init', agent])
Edit and embed
Tune prompts and decisions on the canvas, simulate live in the corner panel, then paste a one-line script tag on any website.
product tour
One workspace for the whole agent lifecycle.
Build, simulate, deploy, and measure in one workspace. No tab-juggling, no second tool. The same canvas that holds your sketch is where you review production analytics. Need LLM reasoning or multi-bot orchestration? AI Agents and Workflows live here too — without replacing the sketch-first path.
Visual builder
React Flow canvas with library and inspector
Live simulator
Send messages, inspect context, and replay history
Channels
Embed widget, voice, WhatsApp, and webhook
Analytics
Sessions, completion, fallback, and funnel
AI Agents
Agentic runtime with mission, tasks, tools, persona, and guardrails
Workflows
Chain triggers, assistants, agents, decisions, and webhooks
app.convoship.org/agents/loan-app/builder
Intent · Entry
apply_loan
12 phrases · 2 params
Entity
Capture amount
@number -> loan_amount
Tool
credit_check
POST /credit/check
Script
Compose reply
templates {{rate}}
built for builders
The product details, in one screen.
Everything in Convoship is built around the same canonical conversation-flow schema. Import, edit, simulate, deploy, and measure all read the same JSON. AI Agents and workflow chains sit alongside scripted assistants in one workspace.
Multi-source import
Draw.io, PDF, Word, and image uploads. One shared flow schema with source-specific parsers.
Visual flow editor
React Flow canvas with library and inspector. Intents are first-class. Subflows compose.
Sandboxed code nodes
Python with session-scoped variables. No more glue scripts living elsewhere.
Real tool integration
HTTP nodes with auth, templated body, JSONPath output mapping, retries, and encrypted secrets.
Entity-aware slot filling
System types for numbers, dates, emails, and durations. Custom list entities with synonyms.
Embed anywhere
Small IIFE bundle, one script tag, queue snippet, tunable theme, lifecycle hooks, public API.
Built-in analytics
Conversation counts, session health, latency, fallback rates, completion, and audit history.
Live simulator + debug
Open any conversation history in the simulator and inspect the full runtime context in a popup.
Production foundations
Workspace auth, MFA, audit log, secrets vault, versioned drafts, and usage metering.
AI Agents
LLM playground with tool calls, daily spend caps, evals, and knowledge sources when flows are not enough.
Workflow chains
Orchestrate assistants, agentic agents, webhooks, and branches — e.g. qualify with an agent, hand off to a scripted intake flow.
Median extraction latency
~500ms
Llama 3.3 70B · Groq
Cost per Draw.io import
$0.004
~1.2k tokens
Node F1 on eval gold
>= 0.99
CI gate · 30 gold flows
Embed SDK bundle size
~15 kB
IIFE · gzip
under the hood
One schema. Every surface reads it.
The importer, runtime engine, embed SDK, and eval harness all share a single canonical conversation-flow schema. Export it, version it, and migrate it across workspaces.
loan-application.drawioXML
<mxGraphModel>
<root>
<mxCell id="n1" type="intent" value="apply_loan"/>
<mxCell id="n2" type="decision" value="amount > 50000?"/>
<mxCell id="n3" type="api" value="credit_check"/>
</root>
</mxGraphModel>agents/loan-app/v8.jsonJSON
{
"id": "agt_loan-app",
"version": 8,
"intents": [{
"name": "apply_loan",
"phrases": 12,
"parameters": ["loan_amount"]
}]
}~/acme-bank
Studio · Deploy · loan-application
-> import · drawio · llama-3.3-70b (groq) · 412ms · $0.004
-> validate · 12 nodes · 14 edges · 0 errors
-> publish · version 8 · simulate ok
-> token · cdp_8c2...ke7 · embed snippet ready
✓ live on acme.bank · 42 sessions today
chat widget
One line of script. Any website.
The embed SDK renders the same runtime your team tested in Studio, so what passes in the simulator is the behavior your customers see.
acme.bank
ACME BANK
Personal loans, on your terms.
Rates from 6.9% APR. Apply in five minutes. No hidden fees.
Apply now
Loan Application
How much would you like to borrow?
25 thousand
Built for enterprise teams.
Convoship is sold on annual agreements with the security, scale, and support your organization expects. Every workspace ships on the Enterprise plan — no agent count caps on imports or sessions.
Enterprise
Customannual agreement
For regulated industries and high-volume conversational programs.
- Unlimited agents, imports, and runtime sessions
- Workspace roles, MFA, and audit log
- Encrypted workspace secrets vault
- WhatsApp, voice, webhooks, and web embed
- AI Agents, workflows, and knowledge (RAG)
- Dedicated onboarding and support
✣ sketch -> bot
Sketch your bot.
Ship it in five minutes.
See how your team can go from whiteboard sketch to production agent in a single working session.