AI SDR API (Jason)
Program Jason, Reply's autonomous AI SDR — knowledge bases, offers, playbooks, autopilot sequences, and the approval queue are all callable today.
The whole Jason surface is callable today — knowledge bases, offers, playbooks, AI SDR sequences, autopilot, and the approval queue. Most of it is marked beta in Reply's reference, so shapes may change without notice. Three things remain coming soon (targeted late August 2026): feedback on a pending approval, feedback on a preview step, per-contact AI insights, and AI web search. Verified 2026-08-14.
- Base URL
https://api.reply.io/v3- Official reference
- docs.reply.io/api-reference/ai-sdr-knowledge-bases/create-a-knowledge-base
- OpenAPI
- ai-sdr.openapi.yaml
- Markdown twin
- ai-sdr.md
- Scopes
ai-sdr:readai-sdr:write
What it does
This is the highest-altitude API in the platform. Instead of orchestrating individual APIs, your agent configures another agent — Jason, Reply’s autonomous AI SDR — and supervises it. The whole loop is callable today: define what Jason knows and sells, point it at a sequence, turn on autopilot, then supervise its drafts through the approval queue.
Callable today (scopes ai-sdr:read / ai-sdr:write / ai-sdr:operate):
- Knowledge bases — create, get, list, update, delete, and duplicate knowledge bases; upload, list, and delete documents; add, list, and delete links; manage reply handlers and reengagement cards, including media upload. Reengagement cards are organized into reengagement flows: create, update, delete, and duplicate a flow, mark one as the knowledge base's default, assign a flow to a contact in a sequence (which resets that contact's re-engagement timer), and read a flow's contact count or a single contact's current assignment.
- Offers — create, get, list, update, and delete the value propositions Jason pitches, and generate an offer from source material you upload. Duplicating an offer is the one operation still coming soon.
- Playbooks — create, get, list, update, and delete playbooks; upload and delete a style file that sets Jason’s voice. Duplicating a playbook is still coming soon.
- AI SDR sequences — create an AI SDR sequence, read and update its settings, attach or detach a playbook, connect or disconnect a knowledge base, set generated step types, set the approval mode, enable or disable autopilot, force-start an autopilot search, and preview autopilot results.
- The approval queue — list pending approvals, get the pending approval for a contact, send one or a batch, regenerate a draft, and reject one.
- Sequence preview — personalize the preview for a contact, and reset it.
- Strategist — start a strategist run.
- Intent signals — industry and technology typeaheads for intent-based targeting.
Most of these carry a beta marker in Reply’s reference: they work, but parameters and response shapes may change without notice.
Still coming soon (targeted late August 2026; verified 2026-07-30):
- Feedback endpoints — submit feedback on a pending approval, and on a preview step. Sending, regenerating, and rejecting all work today; only the feedback signal that tunes future generations is pending.
- Insights — get AI insights for a contact.
- Web search — start an AI web search and list AI web searches for a sequence.
The problem it solves
Composing Prospect Search, Sequences, and Conversations yourself means your agent owns targeting, copywriting, follow-up logic, and reply handling — a lot of orchestration state to hold correctly. The AI SDR API moves your agent up one level of altitude: it programs Jason’s inputs (what Jason knows, what it sells, how it writes) and supervises Jason’s outputs through approval gates. The approval queue is the contract that makes agent-supervising-agent workflows safe: with approvals on, nothing goes out unless the supervisor sends it, and a regenerate call gets a fresh draft when the first one misses.
How an agent starts using it
With an API key holding the ai-sdr:write scope, create a knowledge base with POST /v3/ai-sdr/knowledge-bases, upload product documents and add links to it, create an offer, then create a playbook and upload a style file. Those three objects fully define Jason’s behavior. Then close the loop: create an AI SDR sequence with POST /v3/sequences/ai-sdr, connect the knowledge base, attach the playbook, set the approval mode, and enable autopilot — the operate-level calls need ai-sdr:operate. From there, poll GET /v3/ai-sdr/approvals and send, regenerate, or reject each draft. Leave approval mode on until you trust the output; switching to autonomous means Jason sends without asking.
Typical agent tasks
- Create a knowledge base and load it with product documents and links so Jason writes from real source material
- Create and update offers that define exactly what Jason pitches
- Create a playbook and upload a style file so Jason matches your team's voice
- Duplicate a proven knowledge base as the starting point for a new market
- Group reengagement cards into a flow and assign it to a contact whose re-engagement timer needs resetting
- Review pending approvals and send, regenerate, or reject Jason's drafted messages
- Create an AI SDR sequence, enable autopilot, and supervise it through the approval queue
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
name | string | yes | Name for the knowledge base, offer, or playbook (create endpoints). |
documents | file[] | no | Source files uploaded to a knowledge base via the Upload a document endpoint. |
links | string[] | no | URLs added to a knowledge base for Jason to draw on, via the Add a link endpoint. |
styleFile | file | no | Writing sample uploaded to a playbook to calibrate Jason's tone. |
Outputs
| Name | Type | Description |
|---|---|---|
id | string | Knowledge base, offer, or playbook identifier — the handle an AI SDR sequence references. |
documents | Document[] | Files and links indexed into a knowledge base. |
pendingApprovals | PendingApproval[] | Jason's drafted outreach awaiting a send, regenerate, or reject decision. |
Authentication
API key as Bearer token. Send Authorization: Bearer <API_KEY> on every request. Get an API key in the
Reply.io app under Settings → API Key —
authentication reference.
Rate limits
100 requests/minute and 3,000 requests/hour per user (shared across all of the user's API clients). On 429, honor the Retry-After header.
Example
curl -X POST https://api.reply.io/v3/ai-sdr/knowledge-bases \
-H "Authorization: Bearer $REPLY_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "name": "Acme platform - product knowledge" }'
{
"id": 314,
"name": "Acme platform - product knowledge",
"createdAt": "2026-07-04T09:15:00Z"
}
{
"type": "https://docs.reply.io/api-reference/authentication",
"title": "Forbidden",
"status": 403,
"detail": "This API key does not have the required scope: ai-sdr:write."
}
Related APIs
Modules are designed to chain — combining them is the point.
Prospect Search API
Search Reply Data — 1B+ contacts and 60M+ companies — by ICP filters like job title, seniority, department, industry, and location, and add the matches straight into your prospect lists or a sequence.
Sequence API
Create, populate, and control multichannel outreach sequences — email, LinkedIn, and calls in one campaign object.
Conversations & Inbox API
The unified inbox as an API — read threads across email and LinkedIn, classify replies with categories, detect meeting intent, and respond.
Analytics API
Outcome data for optimizing agents — email, LinkedIn, call, and task overviews, activity feeds, team performance, channel efficiency, and the meetings list.
Frequently asked questions
What is the difference between a knowledge base, an offer, and a playbook?
A knowledge base is the source material Jason reads — documents, links, and (in beta) reply handlers and reengagement cards grouped into flows. An offer is the specific value proposition and call to action it pitches. A playbook is the strategy and voice — the outreach approach plus a style file that calibrates tone. An AI SDR sequence references all three once the sequence endpoints ship.
How does approval mode keep a human or supervising agent in the loop?
Each AI SDR sequence has an approval mode, and it is callable today. With approvals on, Jason queues drafted messages as pending approvals instead of sending. A supervisor — human or agent — lists them, then sends one or a batch, regenerates, or rejects each draft. Submitting feedback that steers future generations is the one part still coming soon. Note that rejecting a draft also removes the contact from the sequence, so regenerate is the right call when the wording is simply wrong.
When should an agent use this instead of composing the lower-level APIs itself?
Compose Prospect Search, Sequences, and Conversations directly when you need deterministic control of every step. Use the AI SDR API when you want to delegate execution — configure Jason once with a knowledge base, an offer, and a playbook, then supervise outcomes through approval gates instead of orchestrating each send yourself.
Start here: get an API key and make your first call, or explore workflows that combine this module with others.