Enterprise conversational AI · BYO model
Migrate the bot you already have — or describe a brand-new agent in plain English. Either path lands in one governed runtime with tasks, tools, guardrails, and evals.
how convoship works
A deterministic parser reads your existing bot's export — or a Draw.io sketch — into a typed baseline. A single model pass cleans labels, infers slots, and lifts service calls. You review the result on a familiar visual canvas.
Upload your existing bot's export — Convoship auto-detects its structure from the archive itself, no manual mapping. (No bot? Draw the flow in Draw.io.) Intents, entities, decisions, and service calls all become structured flow primitives.
Claude Sonnet 4.6
anthropic · claude api
Auto-detect the source, clean labels, infer entity slots, and wrap HTTP nodes as real tool calls with auth, retries, and response mapping — then materialize it as a deterministic Assistant or an AI Agent, your choice.
<script src=
"https://embed.convoship.org/v1.js">
</script>
ConvoshipQueue.push(['init', agent])
Tune prompts and decisions on the canvas, simulate live, watch the per-node drop-off heatmap, then paste a one-line script tag on any website.
try it yourself
No signup, no sandbox to configure. Walk the exact path your team will: drop a diagram, watch Convoship parse it, then talk to the agent it produced — runtime trace and all.
Deterministic parser first, then one Claude pass to clean it up.
Auto-detected from the export
any bot
no manual mapping or rebuild
Import to working agent
minutes
auto-detected · no manual mapping
Conversion fidelity (node F1)
>= 0.99
CI gate · 30 gold flows
Cost per import
$0.004
one bounded model pass
why convoship
Plenty of tools build a new bot. Convoship is the one that takes the bot you already run, makes it deterministic or agentic, gives it memory, and shows you where to improve.
Bring any existing bot's export off the platforms that only let you build new and never leave — and we add new formats on request.
Ship a scripted Assistant or an autonomous AI Agent from the same import — and upgrade one to the other in a click.
Cross-session memory plus a per-node heatmap and flow doctor — not a separate analytics add-on.
Every number — node F1 ≥ 0.99, ~500ms extraction — comes from CI eval gates, not a pitch deck.
Graduate from frontier models to a fine-tuned SLM trained on your own traffic — served by us, or inside your VPC for full data residency.
Row-level isolation, MFA, immutable audit logs, and encrypted secrets in every workspace — no add-on tier.
explore the platform
The essentials are above. Each area below has its own page with the full detail — open the ones your team cares about.
The visual builder, diagram-to-schema import, channels, and the governed runtime architecture.
ExploreIndustry use cases — banking, retail, healthcare and more — and the outcomes teams ship.
ExploreGraduate from a BYO provider API to a fine-tuned small model you own, trained on resolved conversations.
ExploreTenant isolation, encrypted secrets, audit trails, eval gates, and publish approvals.
ExploreFounding design-partner terms, what's included, and answers to common questions.
Explore✣ migrate any bot -> AI agent
See your own bot's export become a production AI agent in a single working session — reasoning, cross-session memory, and a drop-off heatmap included.