CHATBOTS
Natural-Language Voice IVR with Intent Routing
Transcribes a caller's spoken request, classifies intent with an LLM, and either answers order status by voice from Postgres or routes other intents to a human queue.
How it runs
The automated pipeline, trigger to output.
- TriggerProvider posts transcribed caller utteranceHTTP webhook
- ActionClassify caller intent with OpenAIOpenAI
- LogicRoute on order-status vs. other intent
- ActionLook up order in PostgresPostgres
- ActionSynthesize spoken status reply via ElevenLabsElevenLabs
- OutputReturn audio URL or queue-routing directiveHTTP webhook
What it does
Replaces rigid press-1-for-this menus with natural speech. The caller says what they want in their own words; an LLM classifies the intent, and the bot answers order-status questions directly with synthesized voice while handing off everything else (returns, billing, complaints) to the right queue.
When to use it
Use it when a single-purpose order-status bot is too narrow and you want one voice entry point that understands free-form requests. Requires a telephony provider that posts a transcript of the caller's utterance.
How it works
- 1The provider posts the caller's transcribed utterance and order context to the webhook.
- 2OpenAI classifies the intent into order-status or another category.
- 3A logic step routes on the classified intent.
- 4For order-status, Postgres is queried and ElevenLabs speaks the result.
- 5For other intents, a routing instruction (target queue) is returned to the provider instead of audio.
- 6The response — audio URL or routing directive — goes back to the telephony provider.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Connect ElevenLabsText-to-speech, voice cloning.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Chatbots workflows
Discord WAF False-Positive Triage from Ray ID
When a user posts a Cloudflare ray ID in a Discord support channel, the bot looks up the blocked request's WAF event, classifies whether it looks like a genuine false positive.
Agentic WAF Investigator with Discord Approval Gate
An autonomous agent investigates a Discord-reported WAF block end to end: pulls Cloudflare logs, correlates with PagerDuty incidents, decides if an allowlist is safe.
Discord Onboarding Completion to CRM Sync
The moment a member finishes Discord onboarding, captures their submitted profile answers, creates or updates a contact in HubSpot.
Draft WAF Allowlist Proposal to Linear from Discord Report
Lets a support engineer confirm a Discord WAF report is a false positive, then auto-drafts a scoped Cloudflare allowlist rule proposal and files it as a Linear ticket…
Discord FAQ Free-Text Answer Grader
When a member submits a free-text answer in their onboarding thread, an agent grades it against the canonical FAQ knowledge base, replies with targeted feedback.
Discord FAQ-Gated Role Concierge
Greets each new Discord member in a private onboarding thread, walks them through required FAQ steps one at a time.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.