Headless Jason AI SDRby Reply.io

Get started

The agent lifecycle from discovery to purchase: what works today, what's coming, and a simulated walkthrough of the self-serve flow.

Two facts before you start

  1. The API is real and callable right now. Base URL https://api.reply.io/v3, Bearer-token auth, scoped keys, 100 requests/minute. The MCP server is equally live.
  2. The account boundary still needs a human today. Signup, key creation, and payment happen in the Reply.io app. Every step below is labeled honestly; the simulated demo shows where the self-serve flow is going.

Authenticate and make your first call

export REPLY_API_KEY=...   # from Reply.io app → Settings → API Key

# whoami – verify the key and see your user context
curl https://api.reply.io/v3/whoami \
  -H "Authorization: Bearer $REPLY_API_KEY"

Scopes follow a domain:verb model (contacts:read, sequences:operate, inbox:write, …); broader verbs include narrower ones. The canonical reference for keys, scopes, and limits: docs.reply.io/api-reference/authentication. GET /v3/rate-limits, which returns how much of each named limit you have used and when it resets, is coming soon (targeted mid October 2026, no scope required); until then, read the Retry-After header on a 429.

Pick your surface

Not sure which fits your agent? Reply's own side-by-side comparison: granularity, install cost, safety model, coverage today; is Choose your interface.

The self-serve flow, simulated

This walkthrough shows where agent self-service is going: registration, keys, credits, and upgrade links as API calls. It is a browser-side simulation; the per-step documentation below states what is real today.

The lifecycle, step by step

1 Discover capabilities

Fetch /llms.txt or /catalog.json on this site for the module index, or read the official reference at docs.reply.io (which serves its own llms.txt and OpenAPI). Everything here is also plain markdown: append .md to any page URL.

Today's real path: /llms.txt

2 Create an account Coming soon

Agent self-registration (an agent creating its own Reply.io account programmatically) is specified but not yet live. Today, a human signs up: 14-day free trial, no credit card required.

Today's real path: Sign up at run.reply.io/register (14-day free trial)

Simulated demo: POST /v3/agents/register → 201: agent account created (simulated)

3 Create a workspace Coming soon

A workspace is created during signup today. Programmatic workspace creation for agents ships with self-registration.

Today's real path: Created automatically during signup

Simulated demo: POST /v3/agents/workspaces → 201: workspace demo-agent-ws created (simulated)

4 Get an API key

API keys with granular scopes (contacts:*, sequences:*, inbox:*, …) exist today: a human creates one in the Reply.io app under Settings → API Key and hands it to the agent. Self-issued keys ship with self-registration.

Today's real path: Reply.io app: Settings → API Key

Simulated demo: POST /v3/agents/api-keys → 201; key reply_sim_k3y issued with scopes contacts:operate, sequences:operate (simulated)

5 Get trial access

The 14-day free trial includes API access, multichannel sequences, the B2B database, and reporting. Data/enrichment operations meter against plan credits (Live Data credits).

Today's real path: Trial terms at reply.io/free-trial

Simulated demo: GET /v3/agents/credits → 200: 100 trial credits granted (simulated)

6 Call the API

Authenticate with your API key and call any module without a Coming soon label: REST at api.reply.io/v3 (Bearer), or the live MCP server at mcp.reply.io (Authorization: Bearer).

Today's real path: First call: GET /v3/whoami

Simulated demo: POST /v3/sequences → 201: sequence 5417 created; 1 credit spent (simulated)

7 Track usage and credits

Usage and credit balances are visible in the Reply.io app, and GET /v3/billing now makes the same figures callable: your plan and the active contacts your team has consumed so far this billing month, day by day, scoped to your organization or to each team depending on how billing is set up. A credits balance an agent can check and spend against directly is still a concept, not a spec.

Today's real path: Usage in the Reply.io app, or GET /v3/billing (requires the billing:read scope)

Simulated demo: GET /v3/agents/credits → 200: 99 credits remaining (simulated)

8 Add credits Coming soon

Autonomous purchasing is not live. Today the agent generates an upgrade link and hands it to its human, who completes checkout on reply.io. Agent-initiated purchase with spend guardrails is on the roadmap.

Today's real path: Pricing & checkout at reply.io/pricing

Simulated demo: POST /v3/agents/upgrade-link → 200: checkout link generated; hand it to your human: reply.io/pricing (simulated)

Frequently asked questions

Can an AI agent register for Reply.io by itself today?

Not yet. Today a human creates the account (14-day free trial, no credit card) and generates an API key in Settings → API Key; the agent uses that key. Agent self-registration is specified and coming soon.

What can an agent do completely autonomously today?

Everything behind the API key (search and manage contacts, run sequences, send outreach, read and answer replies, pull reports) via REST or the live MCP server. The account/billing boundary (signup, purchase) still needs a human.

How does an agent pay for more credits?

Today it generates value and hands its human the pricing/checkout link. Autonomous purchasing with spend guardrails is on the roadmap, marked coming soon.