ChanlChanl
EngineeringAI-powered solution

Build and deploy AI agents with full control

An API-first platform that lets you build custom AI agents, connect any tool, and monitor everything in production — with the developer experience you expect.

How Chanl Helps

Ship AI agents
with confidence.

API-first platform

RESTful APIs and MCP protocol support for everything. Build agents, manage tools, and control behavior programmatically.

Custom tools

Connect any API, database, or service as a tool your AI agents can call. HTTP, JavaScript, or code actions — your choice.

Full observability

Every API call logged, every tool execution traced, every conversation scored. Debug production issues with complete context.

Developer Experience

APIs and SDKs that just work

TypeScript SDK, REST APIs, and MCP server support. Integrate Chanl into your existing stack in minutes, not weeks.

  • TypeScript/JavaScript SDK with full type safety
  • REST API with Swagger documentation
  • MCP protocol for Claude Desktop and AI tools
  • Webhooks for real-time event notifications
system-prompt.md
v2.3 → v2.4
# System Prompt
You are a helpful customer support agent.
- Be polite and professional
+ Be warm, empathetic and professional
- Response time target: 5 seconds
+ Response time target: 3 seconds
Always verify customer identity.
+ Ask for preferred contact method.
Tests
All passing
CSAT Impact
+2.4%
Deployed
2 min ago
Extensibility

Connect anything, customize everything

Build custom tools that let your AI agents interact with your systems. HTTP endpoints, JavaScript functions, or full code actions — all supported.

  • Custom tool builder with HTTP, JS, and code actions
  • Knowledge base with document upload and RAG
  • Agent memory that persists across conversations
  • Prompt templates with variable substitution
Connected Integrations12 active
SalesforceSalesforce
SlackSlack
GoogleGoogle
StripeStripe
HubSpotHubSpot
IntercomIntercom
ZapierZapier
ShopifyShopify
GitHubGitHub
JiraJira
GmailGmail
PostgreSQLPostgreSQL
Observability

Debug production issues in minutes

Full conversation transcripts, tool call traces, and automated scoring. When something goes wrong, find the root cause fast.

  • Searchable conversation transcripts with speaker turns
  • Tool call tracing with inputs, outputs, and latency
  • Automated quality scoring with custom scorecards
  • Real-time analytics and alerting
test-runner
$ chanl test --suite stress-test --agent production
Rapid-fire Q&A (23 questions)142ms
Interruption handling (mid-sentence)89ms
Accent variation (12 accents)256ms
Background noise (construction)FAIL
Long conversation (45 min)312ms
Emotional escalation (angry → calm)98ms
Multi-topic switching167ms
6 passed, 1 failed
85%

Ready to build?

Start building AI agents with an API-first platform designed for engineers. Free tier, no credit card required.