Drop-off heatmap
Every node shows the share of sessions that abandon there, overlaid on the flow you edit.
your model, not just your agent
Every workspace graduates to its own model.
Renting frontier intelligence forever is a tax. Convoship turns every resolved conversation into equity: a small language model that is yours — fast and predictable on the routine work, deployable where your data must live, and wrapped in the same guardrails from day one.
- 1
Start on day one
Launch on a frontier model, or deploy a Convoship vertical model — telecom, IT support, finance, healthcare — before you have a single conversation of history.
- 2
Your traffic becomes your training set
Resolved conversations export with the tool calls behind them — consent-gated, PII-scrubbed twice. No traffic yet? Convoship simulates multi-turn customers against your agent's own capabilities.
- 3
Fine-tune, then prove it
A LoRA fine-tune on an open-weight base, replayed against your own eval set before it can serve a single customer. No pass, no promotion.
- 4
Deploy on our side — or yours
One click onto Convoship's serving pool, or a self-host bundle inside your VPC. Optional fallback to the frontier model stays off until you switch it on.
Workspace · Models
vertical catalogConvoship vertical models · day-one start
- convoship-telecom-7btelecom
- convoship-itsupport-7bit support
- convoship-finance-7bfinance
- convoship-healthcare-7bhealthcare
LoRA fine-tunes · open-weight base · versioned
Golden-set replay gate — promote only on pass
- Convoship cloud · frontier modelzero setup
- Convoship-hosted SLMper-workspace adapter
- Self-host bundleinference stays in your VPC
- Private trainingdata never leaves your network
Guardrails, OTP checks, spend limits & redaction live in the runtime — model-independent.
ships better every week
The only builder that shows you where to improve.
Shipping is the start, not the finish. Convoship turns live traffic into your next fix — a per-node drop-off heatmap right on the canvas, plus the tools to act on it.
AI flow doctor
A pre-publish gate that catches dead ends, unreachable nodes, and missing slots before they ship.
Persona simulation
Stress-test against synthetic customer personas and find where the agent struggles before customers do.
Visual version diff
Compare any two versions node-by-node, so every change is deliberate and reviewable.
✣ migrate any bot -> AI agent
Get off your legacy bot.
Ship an AI agent this week.
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.